https://ax-news.com/?article=216160178 AX-NEWS en 2026-10-15T04:46:59+00:00 Anthropic Planson: Open AI Model is more risky than our model. https://ax-news.com/?article=216160179 AX-NEWS en 2026-10-15T04:43:48+00:00 OpenAI, London Division last year earned over £2.3 million per person. https://ax-news.com/?article=216160180 AX-NEWS en 2026-10-15T04:43:18+00:00 Nauta secures €60 million first close for sixth fund to back European software and DeepTech startups https://ax-news.com/?article=216160181 AX-NEWS en 2026-10-15T04:41:27+00:00 Avita 06 Re-opened: semi-hidden doorknob, safe and comfortable configuration upgrade, time-limited equity, 20.59 million https://ax-news.com/?article=216160182 AX-NEWS en 2026-10-15T04:38:48+00:00 Bitcoin drops below $81,000 as risk-off sentiment weighs on Asian equities https://ax-news.com/?article=216160183 AX-NEWS en 2026-10-15T04:30:00+00:00 Figma announces new features to define how agents work on its platform https://ax-news.com/?article=216160186 AX-NEWS en 2026-10-15T04:05:00+00:00 APOD: 2026 October 15 – The Milky Way over Manhattan https://ax-news.com/?article=216085174 AX-NEWS en 2026-10-15T04:01:23+00:00 Before VCs, a university writes the first cheque https://ax-news.com/?article=216160187 AX-NEWS en 2026-10-15T04:01:00+00:00 Fires Arrive in the Amazon Rainforest https://ax-news.com/?article=216160188 AX-NEWS en 2026-10-15T04:00:28+00:00 Quinlan Manway launch of the world's first consumer video video video game, synchronised open source https://ax-news.com/?article=216086642 AX-NEWS en 2026-10-15T04:00:00+00:00 ProximalFM: Amortized Proximal Causal Inference under Hidden Confounding https://ax-news.com/?article=216086729 AX-NEWS en 2026-10-15T04:00:00+00:00 Predicting how model propensities generalize out of distribution https://ax-news.com/?article=216086751 AX-NEWS en 2026-10-15T04:00:00+00:00 Continuous Risk-Based Scheduling for Food Safety Inspection: Integrating Historical Decay with Event-Driven Consumer Review Signals https://ax-news.com/?article=216087129 AX-NEWS en 2026-10-15T04:00:00+00:00 Toward System One Clinical Intelligence: Parameter-Efficient Fine-Tuning and Counterfactual Explainability of Decision Foundation Models https://ax-news.com/?article=216087163 AX-NEWS en 2026-10-15T04:00:00+00:00 A Sovereign, Indic-First, Reasoning Model https://ax-news.com/?article=216085557 AX-NEWS en 2026-10-15T04:00:00+00:00 Physical Layer Anomaly Detection via Adaptive Gaussian Mixture Model https://ax-news.com/?article=216086054 AX-NEWS en 2026-10-15T04:00:00+00:00 Beyond Size: How Gradients Shape Pruning Decisions in Large Language Models https://ax-news.com/?article=216086373 AX-NEWS en 2026-10-15T04:00:00+00:00 Virtual-Alloy Physics-Aware Semantic System for extrapolative prediction of perovskite solar cells https://ax-news.com/?article=216086477 AX-NEWS en 2026-10-15T04:00:00+00:00 Hierarchical Residual Policy Learning for Real-World Mobile Manipulation with Sparse Human Guidance https://ax-news.com/?article=216086495 AX-NEWS en 2026-10-15T04:00:00+00:00 SWE-Spot: Building Small Repo-Experts with Repository-Centric Learning https://ax-news.com/?article=216086974 AX-NEWS en 2026-10-15T04:00:00+00:00 When and How Order-Flow Interventions Work After Dealers Adapt https://ax-news.com/?article=216087664 AX-NEWS en 2026-10-15T04:00:00+00:00 Reading the Room: Foundations, Design, and Challenges of Normative Competence in LLMs https://ax-news.com/?article=216086713 AX-NEWS en 2026-10-15T04:00:00+00:00 LYNX: Analytical Program Synthesis via Grounding and Closed-Loop Refinement https://ax-news.com/?article=216087912 AX-NEWS en 2026-10-15T04:00:00+00:00 Same Illness, Different Voice: Restating the Patient's Account Narrows Narrative Anchoring in Clinical Language Models https://ax-news.com/?article=216087960 AX-NEWS en 2026-10-15T04:00:00+00:00 LLM Alignment--Utility Asymmetry under Semantic-Preserving Transformations https://ax-news.com/?article=216085177 AX-NEWS en 2026-10-15T04:00:00+00:00 The Cost of Context: Profiling the Energy Footprint of Input Tokens in Large Language Models https://ax-news.com/?article=216085189 AX-NEWS en 2026-10-15T04:00:00+00:00 Prioritizing Microservice Requests via Retries https://ax-news.com/?article=216087442 AX-NEWS en 2026-10-15T04:00:00+00:00 ShoeFit: A New Dataset and Dual-image-stream DiT Framework for Virtual Footwear Try-On https://ax-news.com/?article=216086759 AX-NEWS en 2026-10-15T04:00:00+00:00 ClinEdge: An Expert-Graded Benchmark of Real Patient Edge Cases Where Frontier Multimodal Models Fail https://ax-news.com/?article=216085636 AX-NEWS en 2026-10-15T04:00:00+00:00 CAFE: Conducting-Cell-Aware Adaptive Differential Encoding for Robust DNN Inference in FeFET-Based Compute-in-Memory https://ax-news.com/?article=216087309 AX-NEWS en 2026-10-15T04:00:00+00:00 From Conceptual EneMonIE to an Executable Backend: A Modular Architecture for Energy Information Extractionand Grounded Question Answering https://ax-news.com/?article=216086724 AX-NEWS en 2026-10-15T04:00:00+00:00 MARL-BattleGrounds: A Novel JAX-native Benchmark for Heterogeneous and Competitive Multi-agent RL https://ax-news.com/?article=216086586 AX-NEWS en 2026-10-15T04:00:00+00:00 Beyond Size: How Gradients Shape Pruning Decisions in Large Language Models https://ax-news.com/?article=216086768 AX-NEWS en 2026-10-15T04:00:00+00:00 A Decade of PhotoMappers: A Longitudinal Study of Crowdsourced Disaster Photos Geolocalization with Vision-Language Models and Geospatial Reasoning https://ax-news.com/?article=216086770 AX-NEWS en 2026-10-15T04:00:00+00:00 CoverSynth: Coverage-Guided Generation of Retrieval Evaluation Sets https://ax-news.com/?article=216087206 AX-NEWS en 2026-10-15T04:00:00+00:00 AutoSec-RAN: Specification-Grounded LLM Fine-Tuning for Automated Security Analysis of O-RAN https://ax-news.com/?article=216087435 AX-NEWS en 2026-10-15T04:00:00+00:00 LiFUSE: Frequency-Spatial Unified Self-Supervised Pretraining for Liver Disease Analysis on Non-contrast CT https://ax-news.com/?article=216087508 AX-NEWS en 2026-10-15T04:00:00+00:00 Tev: Scaling Long-Horizon Agentic Environments with Dense Progress Rewards https://ax-news.com/?article=216087451 AX-NEWS en 2026-10-15T04:00:00+00:00 Agaram 2.5B: The First Tamil-First Language Model Trained from Scratch with Tool Calling. A Playbook for Under-Represented Languages https://ax-news.com/?article=216086050 AX-NEWS en 2026-10-15T04:00:00+00:00 TreeFlex: Agents Navigating Their Own Search Trees https://ax-news.com/?article=216087867 AX-NEWS en 2026-10-15T04:00:00+00:00 ScholarQuest: A Taxonomy-Guided Benchmark for Agentic Academic Paper Search in Open Literature Environments https://ax-news.com/?article=216086808 AX-NEWS en 2026-10-15T04:00:00+00:00 Revocation Is Not Complete at Receipt: An Executable Outcome Contract for Distributed Agent-Tool Gateways https://ax-news.com/?article=216086811 AX-NEWS en 2026-10-15T04:00:00+00:00 Computational Reflective Equilibrium for Agentic AI: A Rawlsian Alignment Scaffold for Governance https://ax-news.com/?article=216086064 AX-NEWS en 2026-10-15T04:00:00+00:00 LLMs Can Get "Brain Rot": A Pilot Study on Twitter/X https://ax-news.com/?article=216086703 AX-NEWS en 2026-10-15T04:00:00+00:00 How to Build a Benchmark That Actually Measures Taste https://ax-news.com/?article=216087790 AX-NEWS en 2026-10-15T04:00:00+00:00 Feed-Forward 3D Scene Modeling: A Problem-Driven Perspective https://ax-news.com/?article=216086737 AX-NEWS en 2026-10-15T04:00:00+00:00 Certify the Decision, Not Every Score: Exact Top-k Selection from Few Evaluations https://ax-news.com/?article=216087474 AX-NEWS en 2026-10-15T04:00:00+00:00 Nudge the Judge: Uncovering Program Decision Hijacking in Real-World Jev Applications https://ax-news.com/?article=216087833 AX-NEWS en 2026-10-15T04:00:00+00:00 When LLM Reward Design Fails: Diagnostic-Driven Refinement for Sparse Structured RL https://ax-news.com/?article=216086092 AX-NEWS en 2026-10-15T04:00:00+00:00 ANCHOR-RE: An Agentic Biomedical Relation Extraction Framework with Retrieval Augmentation and Error-Driven Verification https://ax-news.com/?article=216087020 AX-NEWS en 2026-10-15T04:00:00+00:00 EmoXpt: Analyzing Emotional Variances in Human Comments and LLM-Generated Responses https://ax-news.com/?article=216160189 AX-NEWS en 2026-10-15T04:00:00+00:00 Pricing India’s storage demand gap https://ax-news.com/?article=216086228 AX-NEWS en 2026-10-15T04:00:00+00:00 Policy-Verified Self-Training: Learning Agent Compliance from Verifiable Policy Rewards https://ax-news.com/?article=216085593 AX-NEWS en 2026-10-15T04:00:00+00:00 From Training to Escalation: Forensic Analysis and Local Recreation of RL/RLHF-Induced Privilege Escalation in AI Agents (CVE-2026-65616) https://ax-news.com/?article=216085645 AX-NEWS en 2026-10-15T04:00:00+00:00 Agronomic Characterization and Time-Series UAV Phenotyping to Support Field Pea Breeding in Iowa https://ax-news.com/?article=216085737 AX-NEWS en 2026-10-15T04:00:00+00:00 Quantifying privacy risks in foundation model representations of brain MRI https://ax-news.com/?article=216085913 AX-NEWS en 2026-10-15T04:00:00+00:00 One Block Ahead: Promoting Sampler State in Diffusion Language Models https://ax-news.com/?article=216087933 AX-NEWS en 2026-10-15T04:00:00+00:00 DualOPSD: Closing the Feedback Loop in On-Policy Self-Distillation https://ax-news.com/?article=216086232 AX-NEWS en 2026-10-15T04:00:00+00:00 Fully sequential Gaussian process regression for preference learning https://ax-news.com/?article=216086001 AX-NEWS en 2026-10-15T04:00:00+00:00 Manac\'a-1B-Instruct-2: Reproducible Safety Alignment for a Native Brazilian-Portuguese LLM. Negative DPO Results, a Controlled Composition Scan, and a Silent Failure Mode of the LLM Judge https://ax-news.com/?article=216086400 AX-NEWS en 2026-10-15T04:00:00+00:00 Learning to Select Features with Manifold Deep Unfolding PCA https://ax-news.com/?article=216086464 AX-NEWS en 2026-10-15T04:00:00+00:00 Posterior Frequencies and the Cost of Not Fitting: A Correction to a Memorization Lower Bound https://ax-news.com/?article=216086519 AX-NEWS en 2026-10-15T04:00:00+00:00 When and Why Adversarial Training Improves PINNs: A Neural Tangent Kernel Perspective https://ax-news.com/?article=216086909 AX-NEWS en 2026-10-15T04:00:00+00:00 Budgeted KV-Cache Repair for Evolving Contexts https://ax-news.com/?article=216087251 AX-NEWS en 2026-10-15T04:00:00+00:00 PatTransBench: an ipc-stratified, multi-dimensional benchmark for patent machine translation evaluation https://ax-news.com/?article=216087411 AX-NEWS en 2026-10-15T04:00:00+00:00 Can Machine Learning Potentials Be More Accurate Than the Methods They Are Trained On? https://ax-news.com/?article=216087412 AX-NEWS en 2026-10-15T04:00:00+00:00 Scaling Vision Transformers Without Training: Prune-and-Merge Token Compression https://ax-news.com/?article=216087457 AX-NEWS en 2026-10-15T04:00:00+00:00 MemoryVLN: From Ego-Aware Memory Representation to Cross-Context Memory Reuse in Vision-Language Navigation https://ax-news.com/?article=216087476 AX-NEWS en 2026-10-15T04:00:00+00:00 Knowledge Graphs as Files: An Agent Harness Where Tool Creation and Tool Use Co-Evolve https://ax-news.com/?article=216087809 AX-NEWS en 2026-10-15T04:00:00+00:00 APEX: Assumption-free Projection-based Embedding eXamination Metric for Generative Distribution Evaluation https://ax-news.com/?article=216087815 AX-NEWS en 2026-10-15T04:00:00+00:00 Revealing the Gap in Human and VLM Scene Description through Counterfactual Semantic Saliency https://ax-news.com/?article=216087898 AX-NEWS en 2026-10-15T04:00:00+00:00 Never Too Late for Force: Accelerating VLA Post-Training with Reactive Force Injection https://ax-news.com/?article=216086154 AX-NEWS en 2026-10-15T04:00:00+00:00 The Dice Roll Method: A Standardized Protocol for Repeated-Query Auditing of Large Language Model Brand Recommendations https://ax-news.com/?article=216086263 AX-NEWS en 2026-10-15T04:00:00+00:00 CAST: History-Adaptive Spectral Clipping for LLM Pretraining https://ax-news.com/?article=216086158 AX-NEWS en 2026-10-15T04:00:00+00:00 Self-Retrospection Distillation: Turning Post-hoc Experiences into Prior Foresight https://ax-news.com/?article=216085248 AX-NEWS en 2026-10-15T04:00:00+00:00 Exact analytical spectra of an effective field-modified radial Schr\"odinger equation by the Nikiforov--Uvarov method https://ax-news.com/?article=216085342 AX-NEWS en 2026-10-15T04:00:00+00:00 Quantum simulation of traversable-wormhole-inspired quantum teleportation in a chaotic binary sparse SYK model https://ax-news.com/?article=216085484 AX-NEWS en 2026-10-15T04:00:00+00:00 FINGR: Learning Dexterous Hand Control for Real-World Rubik's Cube Solving https://ax-news.com/?article=216085487 AX-NEWS en 2026-10-15T04:00:00+00:00 VICON: Visual-Inertial-Contact based Hand-Object Tracking for Manipulation Datasets https://ax-news.com/?article=216085515 AX-NEWS en 2026-10-15T04:00:00+00:00 MolLean: A Process-Verifiable Language for Chemical Reasoning https://ax-news.com/?article=216085585 AX-NEWS en 2026-10-15T04:00:00+00:00 Tulva: Practical Asynchronous Threshold FHE https://ax-news.com/?article=216085684 AX-NEWS en 2026-10-15T04:00:00+00:00 SceneAE: Scene Generation and Reconstruction in Queryable 3D-Anchored Latent Space https://ax-news.com/?article=216085811 AX-NEWS en 2026-10-15T04:00:00+00:00 Capability $\neq$ Interpretability: Human Interpretability of Vision Foundation Models https://ax-news.com/?article=216085872 AX-NEWS en 2026-10-15T04:00:00+00:00 Following the Flow the Law Requires: Training Voice Agents to Transfer to Unseen Regulated Procedures in Debt Collection https://ax-news.com/?article=216085874 AX-NEWS en 2026-10-15T04:00:00+00:00 Can LLMs Access their World Knowledge for Event Prediction? https://ax-news.com/?article=216085919 AX-NEWS en 2026-10-15T04:00:00+00:00 REWIND: Uncertainty-Guided Trajectory Repair for Test-Time Reasoning https://ax-news.com/?article=216086027 AX-NEWS en 2026-10-15T04:00:00+00:00 ActICL: Post-Training for Agentic Multimodal In-Context Learning https://ax-news.com/?article=216086124 AX-NEWS en 2026-10-15T04:00:00+00:00 Prompt Stability Matters: Evaluating and Optimizing Auto-Generated Prompt in General-Purpose Systems https://ax-news.com/?article=216086236 AX-NEWS en 2026-10-15T04:00:00+00:00 Comprehensive Comparisons of Reinforcement Learning Algorithms in Autonomous Driving https://ax-news.com/?article=216086244 AX-NEWS en 2026-10-15T04:00:00+00:00 Test-Time Forecasting: Recurrent Depth Enables In-Context Dynamics Prediction https://ax-news.com/?article=216086247 AX-NEWS en 2026-10-15T04:00:00+00:00 InstructPro2: Natural Language and Biological Grounding Guided De Novo Protein Design https://ax-news.com/?article=216086280 AX-NEWS en 2026-10-15T04:00:00+00:00 On the Limits of Representation-Based Test-Time Adaptation for Multimodal LLMs https://ax-news.com/?article=216086294 AX-NEWS en 2026-10-15T04:00:00+00:00 On the Convergence of Semi-Gradient TD: A Mean Field Perspective https://ax-news.com/?article=216086319 AX-NEWS en 2026-10-15T04:00:00+00:00 From Plato to Aristotle: Toward a General Theory of Representation Hypotheses https://ax-news.com/?article=216086328 AX-NEWS en 2026-10-15T04:00:00+00:00 Beyond Expert Rankings: Contrast Calibration for Mixed-Precision MoE Quantization https://ax-news.com/?article=216086362 AX-NEWS en 2026-10-15T04:00:00+00:00 Distinguishing Process Change, Instrument Fault and Data-Path Corruption in Streaming Telemetry: A Reference Implementation and Benchmark https://ax-news.com/?article=216086371 AX-NEWS en 2026-10-15T04:00:00+00:00 Physical Layer Anomaly Detection via Adaptive Gaussian Mixture Model https://ax-news.com/?article=216086425 AX-NEWS en 2026-10-15T04:00:00+00:00 Articulation Upper Bounds for Language Models https://ax-news.com/?article=216086427 AX-NEWS en 2026-10-15T04:00:00+00:00 Analyzing and Mitigating Poisoning Attacks on Flow-Based Intrusion Detection https://ax-news.com/?article=216086447 AX-NEWS en 2026-10-15T04:00:00+00:00 Cross-Model In-Context Neurofeedback Reveals (Limited) Activation Control in LLMs https://ax-news.com/?article=216086453 AX-NEWS en 2026-10-15T04:00:00+00:00 Contrastive uncertainty learning for robust multi-structure segmentation in lower-pelvic MR https://ax-news.com/?article=216086460 AX-NEWS en 2026-10-15T04:00:00+00:00 Hypothesis Selection via Weighted Medians https://ax-news.com/?article=216086482 AX-NEWS en 2026-10-15T04:00:00+00:00 Spectral structure learning for clinical time series https://ax-news.com/?article=216086528 AX-NEWS en 2026-10-15T04:00:00+00:00 A Unifying Framework for Concept-Based Representational Similarity https://ax-news.com/?article=216086628 AX-NEWS en 2026-10-15T04:00:00+00:00 The Zero Pattern of a Design Matrix Drives Multiple Descent in Over-parameterized Regression https://ax-news.com/?article=216086632 AX-NEWS en 2026-10-15T04:00:00+00:00 Equilibrium Forcing: Adaptive Video Generation Without Noise Conditioning https://ax-news.com/?article=216086690 AX-NEWS en 2026-10-15T04:00:00+00:00 Learning after Execution with Action-Specific Credit https://ax-news.com/?article=216086731 AX-NEWS en 2026-10-15T04:00:00+00:00 MCPDisCo: Seesaw-Mitigated Tuning for MCP-Native Agents https://ax-news.com/?article=216086774 AX-NEWS en 2026-10-15T04:00:00+00:00 MemeLogos: Knowledge-Driven Retrieval-Augmented Reasoning for Harmful Meme Detection https://ax-news.com/?article=216086826 AX-NEWS en 2026-10-15T04:00:00+00:00 ProCARE: Real-World Study Automation via Profile-Grounded Evidence Contracts https://ax-news.com/?article=216086933 AX-NEWS en 2026-10-15T04:00:00+00:00 Encounter-Driven City-Scale Human Mobility Generation with Large Language Models https://ax-news.com/?article=216087593 AX-NEWS en 2026-10-15T04:00:00+00:00 SearchMaster: Grounded and Regulated Self-Play for Search Agents https://ax-news.com/?article=216087109 AX-NEWS en 2026-10-15T04:00:00+00:00 Integrating AIRL-Based Reward Estimation into a Control Method Using Fuzzy Inference and Policy Gradient https://ax-news.com/?article=216087278 AX-NEWS en 2026-10-15T04:00:00+00:00 Comparing GenAI to Machine Learning and Manual Review for eDiscovery https://ax-news.com/?article=216087333 AX-NEWS en 2026-10-15T04:00:00+00:00 Assessing the Performance of AI Models in Misinformation Detection Using Predefined Social Noise Constructs https://ax-news.com/?article=216087356 AX-NEWS en 2026-10-15T04:00:00+00:00 LatentRiskBench: Measuring State-Dependent Risks in Enterprise Agents https://ax-news.com/?article=216087619 AX-NEWS en 2026-10-15T04:00:00+00:00 Style Over Substance: Content-Invariant Wrappers Flip LLM Safety-Judge Verdicts https://ax-news.com/?article=216087450 AX-NEWS en 2026-10-15T04:00:00+00:00 Resource-Efficient 3D Shape and Orientation Estimation of Road Users using Roadside RGB Camera and 3D Radar https://ax-news.com/?article=216087473 AX-NEWS en 2026-10-15T04:00:00+00:00 Jev-ToM: Evaluating Theory of Mind in Typed Decision Models https://ax-news.com/?article=216087497 AX-NEWS en 2026-10-15T04:00:00+00:00 Where Do LLM Ensemble Gains Come From? Decomposing Candidate Value, Diversity, and Aggregation https://ax-news.com/?article=216087658 AX-NEWS en 2026-10-15T04:00:00+00:00 GraphDecisionBench: Benchmarking System One Models on Graph Tasks https://ax-news.com/?article=216087722 AX-NEWS en 2026-10-15T04:00:00+00:00 Batch Bayesian Active Learning with Partial Batch Label Sampling https://ax-news.com/?article=216087792 AX-NEWS en 2026-10-15T04:00:00+00:00 Beyond Single-Model Optimization: Preserving Plasticity in Continual Reinforcement Learning https://ax-news.com/?article=216087811 AX-NEWS en 2026-10-15T04:00:00+00:00 When and How to Canonize: A Generalization Perspective https://ax-news.com/?article=216087819 AX-NEWS en 2026-10-15T04:00:00+00:00 $\alpha$-TCAV: A Unified Framework for Testing with Concept Activation Vectors https://ax-news.com/?article=216087821 AX-NEWS en 2026-10-15T04:00:00+00:00 LoopQ: Quantization for Looped Language Models https://ax-news.com/?article=216087879 AX-NEWS en 2026-10-15T04:00:00+00:00 Federated Learning with Energy-Based Structured Probabilistic Inference https://ax-news.com/?article=216087905 AX-NEWS en 2026-10-15T04:00:00+00:00 Activation Steering with Jungian Cognitive Functions https://ax-news.com/?article=216087945 AX-NEWS en 2026-10-15T04:00:00+00:00 Divide, Consult, Conquer: Capability Laundering Through Aligned LLMs https://ax-news.com/?article=216087962 AX-NEWS en 2026-10-15T04:00:00+00:00 ESTHER: Egocentric Stereo Hand Estimation and Reconstruction in the Wild https://ax-news.com/?article=216086260 AX-NEWS en 2026-10-15T04:00:00+00:00 TIMERSI: Towards Self-Improved Agentic Deployment for Time-Series Foundation Models https://ax-news.com/?article=216085175 AX-NEWS en 2026-10-15T04:00:00+00:00 Parallel Sparse Outputs for Tensor Compilers https://ax-news.com/?article=216085176 AX-NEWS en 2026-10-15T04:00:00+00:00 Scaling LLM Inference via Parallelism: Throughput-Latency Trade-off https://ax-news.com/?article=216085178 AX-NEWS en 2026-10-15T04:00:00+00:00 JointServe: Serving Multi-Model Agents on Memory-Constrained GPUs https://ax-news.com/?article=216085187 AX-NEWS en 2026-10-15T04:00:00+00:00 Computational compressive imaging reconstruction with a simulated-annealing-based Ising solver https://ax-news.com/?article=216085188 AX-NEWS en 2026-10-15T04:00:00+00:00 Delta Tokenizer: Reference-Identical Tokenization of Session Deltas and Segment-Parallelism for Long Prompts on Multicore CPUs https://ax-news.com/?article=216085193 AX-NEWS en 2026-10-15T04:00:00+00:00 Native Dual Pools or Shared Paging? Memory Organization for Concurrent Hybrid LLM Serving https://ax-news.com/?article=216085197 AX-NEWS en 2026-10-15T04:00:00+00:00 sGLP: Simulating People with Stochastic Agents https://ax-news.com/?article=216085198 AX-NEWS en 2026-10-15T04:00:00+00:00 Design and Analysis of Temporal Representations in Neural Networks https://ax-news.com/?article=216085201 AX-NEWS en 2026-10-15T04:00:00+00:00 How Long Is the Coast of a Neuron? Resolution-Dependent Interaction Order and Computational Capacity https://ax-news.com/?article=216085202 AX-NEWS en 2026-10-15T04:00:00+00:00 Position: Hippocampal Explicit Memory Is the Cornerstone for AGI https://ax-news.com/?article=216085203 AX-NEWS en 2026-10-15T04:00:00+00:00 Invertible subalgebras for chiral semion topological order https://ax-news.com/?article=216085205 AX-NEWS en 2026-10-15T04:00:00+00:00 Stabilizer R\'enyi Entropy Without a Phase Reference https://ax-news.com/?article=216087838 AX-NEWS en 2026-10-15T04:00:00+00:00 Real2SAM2Real: Generative 3D Caches as Complementary Context for Video Diffusion https://ax-news.com/?article=216085211 AX-NEWS en 2026-10-15T04:00:00+00:00 A modular quantum computer based on Cornucopia codes https://ax-news.com/?article=216085212 AX-NEWS en 2026-10-15T04:00:00+00:00 Federated Unlearning of Quantum Data via Classical Shadows https://ax-news.com/?article=216085215 AX-NEWS en 2026-10-15T04:00:00+00:00 Selective Control and Imaging of Higgs and Goldstone Modes with a Quantum Simulator https://ax-news.com/?article=216085218 AX-NEWS en 2026-10-15T04:00:00+00:00 Gap-Priced $|T\rangle$-States: Dynamic $|T\rangle$ Post-Selection and Budget-Aware Factory Provisioning https://ax-news.com/?article=216085222 AX-NEWS en 2026-10-15T04:00:00+00:00 Shot- and Noise-Aware Pauli Correlation Encoding for Max-Cut Experiments on IBM Heron Quantum Processor https://ax-news.com/?article=216085223 AX-NEWS en 2026-10-15T04:00:00+00:00 A Reconstruction of Michelson Interference from On--Off Detection Statistics https://ax-news.com/?article=216085227 AX-NEWS en 2026-10-15T04:00:00+00:00 Void-Free Through-Glass Vias for Multilayer Surface-Electrode Ion Traps https://ax-news.com/?article=216085233 AX-NEWS en 2026-10-15T04:00:00+00:00 On the structure of low-rank PPT entangled states violating Peres conjecture https://ax-news.com/?article=216085234 AX-NEWS en 2026-10-15T04:00:00+00:00 Quantum Folding in Chebyshev-Based Quantum Subspace Diagonalization https://ax-news.com/?article=216085236 AX-NEWS en 2026-10-15T04:00:00+00:00 Deterministic and Programmable Fusion for Scalable Generation of Photonic Graph States https://ax-news.com/?article=216085240 AX-NEWS en 2026-10-15T04:00:00+00:00 Testing graph isomorphism using simple quantum circuits https://ax-news.com/?article=216085241 AX-NEWS en 2026-10-15T04:00:00+00:00 Hyperentanglement in intermediate phase-space planes: benchmarking a photon-pair source for quantum key distribution https://ax-news.com/?article=216085242 AX-NEWS en 2026-10-15T04:00:00+00:00 Multi-Instantons and Exact-WKB Stokes Jumps in Multi-Well Quantum Mechanics https://ax-news.com/?article=216085244 AX-NEWS en 2026-10-15T04:00:00+00:00 Advances in quantum optomechanical control based on cavity cold-atom systems https://ax-news.com/?article=216085245 AX-NEWS en 2026-10-15T04:00:00+00:00 Strong subadditivity of topological entropy on the torus: R\'enyi order and non-Abelian structure https://ax-news.com/?article=216085247 AX-NEWS en 2026-10-15T04:00:00+00:00 Pinning of a High-Energy Wavepacket by a Single Impurity https://ax-news.com/?article=216085249 AX-NEWS en 2026-10-15T04:00:00+00:00 Geometric-resource bounds and permutation-averaged success probabilities for the WZP algorithm https://ax-news.com/?article=216085258 AX-NEWS en 2026-10-15T04:00:00+00:00 Logical CCZ state cultivation https://ax-news.com/?article=216085260 AX-NEWS en 2026-10-15T04:00:00+00:00 Stabilizer entropy cones as self-dual slices of linear rank cones: a five-party gap and dependence on the local dimension https://ax-news.com/?article=216085263 AX-NEWS en 2026-10-15T04:00:00+00:00 Gravity from generalized entropy https://ax-news.com/?article=216085266 AX-NEWS en 2026-10-15T04:00:00+00:00 A note on the A.C. spectrum of limit-periodic Jacobi matrices https://ax-news.com/?article=216085268 AX-NEWS en 2026-10-15T04:00:00+00:00 Coherent-State Integrals Beyond the Domain of Operator Products https://ax-news.com/?article=216085269 AX-NEWS en 2026-10-15T04:00:00+00:00 Quantum-enhanced Search for Galactic Dark Photons Using Cat-State Cavities https://ax-news.com/?article=216085270 AX-NEWS en 2026-10-15T04:00:00+00:00 Observation of correlations beyond the single-particle picture in fermionic counting statistics https://ax-news.com/?article=216085271 AX-NEWS en 2026-10-15T04:00:00+00:00 Preservation of photon statistics upon selective molecular modulation in hollow-core fibers https://ax-news.com/?article=216085276 AX-NEWS en 2026-10-15T04:00:00+00:00 Degeneracy graph determinants and higher-dimensional Young diagrams https://ax-news.com/?article=216085279 AX-NEWS en 2026-10-15T04:00:00+00:00 A quantum annealing approach to the minimum distance problem of quantum codes https://ax-news.com/?article=216085280 AX-NEWS en 2026-10-15T04:00:00+00:00 Relativistic generalization of Feynman's path integral on the basis of extended Lagrangians https://ax-news.com/?article=216085282 AX-NEWS en 2026-10-15T04:00:00+00:00 Reliable Entropy Estimation from Observed Statistics for Device-Independent Quantum Cryptography https://ax-news.com/?article=216085287 AX-NEWS en 2026-10-15T04:00:00+00:00 Rare Event Simulation of Quantum Error-Correcting Circuits https://ax-news.com/?article=216085289 AX-NEWS en 2026-10-15T04:00:00+00:00 Objectivity, basis ambiguity, and the classical simulability of concordant quantum computation https://ax-news.com/?article=216085292 AX-NEWS en 2026-10-15T04:00:00+00:00 Fundamental Limitations of QAOA on Constrained Problems and a Route to Exponential Enhancement https://ax-news.com/?article=216085293 AX-NEWS en 2026-10-15T04:00:00+00:00 Mirror subspace diagonalization: A real-time quantum Krylov algorithm with near-optimal sampling cost https://ax-news.com/?article=216085303 AX-NEWS en 2026-10-15T04:00:00+00:00 Sequential vs. Synchronized Entanglement Swapping: QKD Secret-Key Rate under Optimized Link-Layer Control https://ax-news.com/?article=216085313 AX-NEWS en 2026-10-15T04:00:00+00:00 Photon localization: a comparative study https://ax-news.com/?article=216086369 AX-NEWS en 2026-10-15T04:00:00+00:00 Wong--Zakai Convergence and FNO Learning for Stochastic Volterra Equations https://ax-news.com/?article=216085314 AX-NEWS en 2026-10-15T04:00:00+00:00 State-resolved quantum-information fingerprints of partial dynamical symmetry in the interacting boson model https://ax-news.com/?article=216085323 AX-NEWS en 2026-10-15T04:00:00+00:00 SQD-Agent: LLM-driven agentic framework for Quantum Chemistry workflows https://ax-news.com/?article=216085327 AX-NEWS en 2026-10-15T04:00:00+00:00 Causal memory and structural complexity of correlated quantum sequences https://ax-news.com/?article=216085332 AX-NEWS en 2026-10-15T04:00:00+00:00 Riemannian Formulation of Sample-Based Quantum Krylov Solvers for Elliptic Problems: Energy-Norm Guarantees and Duct-Flow Applications https://ax-news.com/?article=216085333 AX-NEWS en 2026-10-15T04:00:00+00:00 Autonomous optomechanical Maxwell Demon engine https://ax-news.com/?article=216085334 AX-NEWS en 2026-10-15T04:00:00+00:00 PULSUS: Direct Frequency-Domain Multidimensional Spectroscopy Beyond the Impulsive Rotating-Wave Approximation https://ax-news.com/?article=216085336 AX-NEWS en 2026-10-15T04:00:00+00:00 Statistical Description of Fermi System over a Surface in a Uniform External Field https://ax-news.com/?article=216085339 AX-NEWS en 2026-10-15T04:00:00+00:00 Strong-field regime within effective field theory https://ax-news.com/?article=216085341 AX-NEWS en 2026-10-15T04:00:00+00:00 Structured-Light Magnetometry in a Coherently Controlled Atomic Medium https://ax-news.com/?article=216085348 AX-NEWS en 2026-10-15T04:00:00+00:00 Placement-driven reversal of preferred spin alignment in monolayer hBN vacancy pairs https://ax-news.com/?article=216085349 AX-NEWS en 2026-10-15T04:00:00+00:00 Coherent Release Fronts in Krylov Chains and Thermal AdS$_2$ Response https://ax-news.com/?article=216085350 AX-NEWS en 2026-10-15T04:00:00+00:00 Competitive scaling of small-subsystem-optimization heuristics for LABS https://ax-news.com/?article=216085352 AX-NEWS en 2026-10-15T04:00:00+00:00 $\lambda_0$: Scaling Open-World Egocentric Human Data for Humanoid Loco-Manipulation https://ax-news.com/?article=216085355 AX-NEWS en 2026-10-15T04:00:00+00:00 Tread: A Visuo-Inertial Framework for Terrain and Locomotion Context-Aware Gait-Phase and Speed Estimation in Wearable Robotics https://ax-news.com/?article=216085356 AX-NEWS en 2026-10-15T04:00:00+00:00 Receding-Horizon Next-Best-View Planning for Highly Occluded Target Perception https://ax-news.com/?article=216085357 AX-NEWS en 2026-10-15T04:00:00+00:00 DexMimic: A Generalist Dexterous Hand-Object Tracking Policy via Value-Guided Reset Allocation https://ax-news.com/?article=216085358 AX-NEWS en 2026-10-15T04:00:00+00:00 Benchmarking 3D Reconstruction for Under-Ice Robotic Perception in Arctic Environments https://ax-news.com/?article=216085360 AX-NEWS en 2026-10-15T04:00:00+00:00 Collective Learning for Unified Robotic Manipulation via Predictive Dynamics Adaptation https://ax-news.com/?article=216085362 AX-NEWS en 2026-10-15T04:00:00+00:00 FACT: A Multimodal Force-Action-Track Foundation Model for Human-to-Robot Dexterity https://ax-news.com/?article=216085363 AX-NEWS en 2026-10-15T04:00:00+00:00 A Mode-Unified, Continuous, and Biomimetic Control Strategy of a Robotic Lower Limb Prosthesis https://ax-news.com/?article=216085367 AX-NEWS en 2026-10-15T04:00:00+00:00 MIND: Instruction-Conditioned Incremental Grounding for Robots https://ax-news.com/?article=216085368 AX-NEWS en 2026-10-15T04:00:00+00:00 Learning Keypoint Constraints from Visual Demonstrations for Safe Motion Planning https://ax-news.com/?article=216085370 AX-NEWS en 2026-10-15T04:00:00+00:00 Beyond Kinematic Tracking: Preserving Expressive Characteristics in Humanoid Whole-Body Control https://ax-news.com/?article=216085371 AX-NEWS en 2026-10-15T04:00:00+00:00 A Master-to-Simulation Interface with Demonstration-Trajectory Guidance for Vascular Intervention https://ax-news.com/?article=216085373 AX-NEWS en 2026-10-15T04:00:00+00:00 A VR Training System for Robot-Assisted Vascular Intervention with Dual-Mode Control and Model-Based Interaction Response https://ax-news.com/?article=216085374 AX-NEWS en 2026-10-15T04:00:00+00:00 From Failures to Learnable Worlds: Policy-Conditioned Environment Generation for Navigation Agents https://ax-news.com/?article=216085375 AX-NEWS en 2026-10-15T04:00:00+00:00 $S^3$-Nav: Structured Spatial-Semantic Decision Making for Language-Guided Robot Navigation https://ax-news.com/?article=216085376 AX-NEWS en 2026-10-15T04:00:00+00:00 Paraphrase Consensus Is Not Self-Consistency: Instruction Reliance and Robustness in VLA Policies https://ax-news.com/?article=216085378 AX-NEWS en 2026-10-15T04:00:00+00:00 Active Generative Simulation: Meta-Learning What to Simulate for Sim-and-Real Policy Co-Training https://ax-news.com/?article=216085379 AX-NEWS en 2026-10-15T04:00:00+00:00 IMU-Bench: Benchmarking Wrist IMU Representations Across Kinematic, Semantic and Clinical Tasks https://ax-news.com/?article=216085382 AX-NEWS en 2026-10-15T04:00:00+00:00 Dungeon and Visibility World Generator https://ax-news.com/?article=216085383 AX-NEWS en 2026-10-15T04:00:00+00:00 Dual-arm Cooperation for Tabletop Wiping with Temporal Object Removal https://ax-news.com/?article=216085386 AX-NEWS en 2026-10-15T04:00:00+00:00 RoboSpan: Learning Modular Coordination Policies for High-DoF Whole-Body Mobile Manipulation with Teleoperation https://ax-news.com/?article=216085387 AX-NEWS en 2026-10-15T04:00:00+00:00 Cracking Mobile Manipulation: From Failure Diagnosis to Agentic Robot System https://ax-news.com/?article=216085389 AX-NEWS en 2026-10-15T04:00:00+00:00 PolyMorph: Learning Locomotion Policy for Cross-Embodiment Adaptation https://ax-news.com/?article=216085390 AX-NEWS en 2026-10-15T04:00:00+00:00 Instruction-Conditioned Motion Control for Robotic Arms: Language-to-Code Decomposition and Reinforcement Learning https://ax-news.com/?article=216085393 AX-NEWS en 2026-10-15T04:00:00+00:00 Eye, Robot: Learning Expressive Gaze Dynamics via a VLM-Guided Transformer-VAE https://ax-news.com/?article=216085394 AX-NEWS en 2026-10-15T04:00:00+00:00 Accelerating VLA Inference with Perturbation Informed Execution https://ax-news.com/?article=216085396 AX-NEWS en 2026-10-15T04:00:00+00:00 Uncertainty-Driven Self-Play for Robust Multi-Agent Driving Policies https://ax-news.com/?article=216085397 AX-NEWS en 2026-10-15T04:00:00+00:00 One-shot Human Video-Guided Adaptation for Vision-Language-Action Models https://ax-news.com/?article=216085400 AX-NEWS en 2026-10-15T04:00:00+00:00 Refine Actions If Needed: Adaptive Action Chunk Refinement for Robot Manipulation https://ax-news.com/?article=216085403 AX-NEWS en 2026-10-15T04:00:00+00:00 What Matters for World Modeling in Vision-Language-Action Models? https://ax-news.com/?article=216085404 AX-NEWS en 2026-10-15T04:00:00+00:00 FOMI: A Force-Feedback Manipulation Interface for Teaching Contact-Rich Manipulation https://ax-news.com/?article=216085406 AX-NEWS en 2026-10-15T04:00:00+00:00 MUCO: A Mani-Unit-Structured Manipulation Framework for Compositional Long-Horizon Robot Tasks https://ax-news.com/?article=216085407 AX-NEWS en 2026-10-15T04:00:00+00:00 Complementary Future Token Pruning for World Action Models https://ax-news.com/?article=216085408 AX-NEWS en 2026-10-15T04:00:00+00:00 MorphAct: Robot Policies Morphing with the Worlds They Act In https://ax-news.com/?article=216085409 AX-NEWS en 2026-10-15T04:00:00+00:00 FoveaVLA: Foveation Actions Replace the Wrist Camera in VLAs https://ax-news.com/?article=216085410 AX-NEWS en 2026-10-15T04:00:00+00:00 HM3D-M3: A Benchmark for Multi-Agent, Multi-Modal, Multi-Object Goal Navigation https://ax-news.com/?article=216085411 AX-NEWS en 2026-10-15T04:00:00+00:00 Tactile-Guided Robot Learning: From Representation Learning to Foundation Models https://ax-news.com/?article=216085412 AX-NEWS en 2026-10-15T04:00:00+00:00 Enabling Tidying Tasks in Robotic Vacuum Cleaners via a Geometry-Induced Self-Locking Deployable Linkage https://ax-news.com/?article=216085414 AX-NEWS en 2026-10-15T04:00:00+00:00 Investigating Behavior Cloning from Few Demonstrations for Autonomous Driving based on Bird's-Eye View in Simulated Cities https://ax-news.com/?article=216085419 AX-NEWS en 2026-10-15T04:00:00+00:00 Learning-Based Adaptive MPC for Magnetorquer-Only Satellite Attitude Control https://ax-news.com/?article=216085420 AX-NEWS en 2026-10-15T04:00:00+00:00 Efficient Test-Time Adaptation For Robot Policies https://ax-news.com/?article=216085421 AX-NEWS en 2026-10-15T04:00:00+00:00 TacClaw-Infinity: A Large-Scale Vision-Tactile-Language-Action Dataset for Dexterous Manipulation https://ax-news.com/?article=216085425 AX-NEWS en 2026-10-15T04:00:00+00:00 When Do Discrete Actions Make Good Continuous Controllers? https://ax-news.com/?article=216085428 AX-NEWS en 2026-10-15T04:00:00+00:00 Tiered-Resolution Volumetric Mapping for Real-Time Simultaneous Planning and Mapping on Natural Outdoor Environments https://ax-news.com/?article=216085429 AX-NEWS en 2026-10-15T04:00:00+00:00 Towards Certifiable State Estimation under Observability Degeneracy https://ax-news.com/?article=216085434 AX-NEWS en 2026-10-15T04:00:00+00:00 PingpongDuo: Agile Humanoid Table Tennis Doubles with Safe Team Coordination https://ax-news.com/?article=216085436 AX-NEWS en 2026-10-15T04:00:00+00:00 Modeling and Understanding Neural Weights of Humanoid Policies with Diffusion https://ax-news.com/?article=216085438 AX-NEWS en 2026-10-15T04:00:00+00:00 SafeDriveVLA: Navigation-Conditioned World Model Dreaming for Conflict-Aware End-to-End Autonomous Driving https://ax-news.com/?article=216085439 AX-NEWS en 2026-10-15T04:00:00+00:00 All-St3R SLAM: Real-time RGB Dynamic SLAM with Pixel-wise Motion Masking https://ax-news.com/?article=216085440 AX-NEWS en 2026-10-15T04:00:00+00:00 DiffGIPC: Differentiable Mixed-Coordinate Contact Dynamics on GPU https://ax-news.com/?article=216085444 AX-NEWS en 2026-10-15T04:00:00+00:00 Seeing, Maintaining, and Learning: The Evolution of Multimodal Agent Memory https://ax-news.com/?article=216085445 AX-NEWS en 2026-10-15T04:00:00+00:00 VLRLA: Deployment-Time Adaptation of Vision-Language-Action Models through In-Context Reinforcement Learning https://ax-news.com/?article=216085446 AX-NEWS en 2026-10-15T04:00:00+00:00 What Happens to the Goal? Distinct Failures of Policy Alignment in Goal Misgeneralization https://ax-news.com/?article=216085448 AX-NEWS en 2026-10-15T04:00:00+00:00 Why 3D Reconstruction Breaks Down on Under-Ice AUV Video, and How to Predict It https://ax-news.com/?article=216085449 AX-NEWS en 2026-10-15T04:00:00+00:00 FPTAS for Polygonal Multi-Robot Motion Planning https://ax-news.com/?article=216085453 AX-NEWS en 2026-10-15T04:00:00+00:00 Don't Run with Scissors: Pruning Breaks VLA Models but They Can Be Recovered https://ax-news.com/?article=216085457 AX-NEWS en 2026-10-15T04:00:00+00:00 TGPO: Trace-Guided Policy Optimization for Robot Task Planning via Verifiable Subgoal Generation https://ax-news.com/?article=216085465 AX-NEWS en 2026-10-15T04:00:00+00:00 LEGS: Fine-Tuning Teleop-Free VLAs for Humanoid Loco-manipulation in an Embodied Gaussian Splatting World https://ax-news.com/?article=216085471 AX-NEWS en 2026-10-15T04:00:00+00:00 SPARC: Reliable Spatial Annotations from Robot Demonstrations at Scale https://ax-news.com/?article=216085472 AX-NEWS en 2026-10-15T04:00:00+00:00 Driving, Fast or Slow? Neuro-Symbolic Guidance for Motion Prediction in Multi-Modal Ground Mobility https://ax-news.com/?article=216085473 AX-NEWS en 2026-10-15T04:00:00+00:00 PoLAR: Factorizing Extent and Mode in Latent Actions for Robot Policy Learning https://ax-news.com/?article=216085477 AX-NEWS en 2026-10-15T04:00:00+00:00 Soft Robotic Exogloves for Dexterous Mobility -- Towards Personalized Rehabilitation https://ax-news.com/?article=216085479 AX-NEWS en 2026-10-15T04:00:00+00:00 PRISM: Polynomial Representations for Interaction-Structured Motor Control https://ax-news.com/?article=216085480 AX-NEWS en 2026-10-15T04:00:00+00:00 FACT: Failure-Aware Causal Training for World-Action Models https://ax-news.com/?article=216085482 AX-NEWS en 2026-10-15T04:00:00+00:00 VGM-VS: Rethinking Visual Geometry Model for High-Precision Visual Servoing https://ax-news.com/?article=216085485 AX-NEWS en 2026-10-15T04:00:00+00:00 Scale and Selection: What Makes Automatic Harness Evolution Work for Visual-Interface Robot Agents https://ax-news.com/?article=216085488 AX-NEWS en 2026-10-15T04:00:00+00:00 What the Elevation Map Cannot See: Semantic-Aware Locomotion and Execution-Aware Navigation for Humanoid Robot https://ax-news.com/?article=216085492 AX-NEWS en 2026-10-15T04:00:00+00:00 MultiFly: A Real-World Multimodal Aerial Dataset with Annotation-Efficient Label Transfer and Cross-Modal Semantic Consistency https://ax-news.com/?article=216085496 AX-NEWS en 2026-10-15T04:00:00+00:00 Test-Time Compute for Humanoid Behavior Foundation Models https://ax-news.com/?article=216085498 AX-NEWS en 2026-10-15T04:00:00+00:00 ReEnvision: Future-Guided Selective Action Repair for Long-Horizon Manipulation https://ax-news.com/?article=216085499 AX-NEWS en 2026-10-15T04:00:00+00:00 Data-Free Continual Learning for World Action Model with Rectified Generative Replay https://ax-news.com/?article=216085502 AX-NEWS en 2026-10-15T04:00:00+00:00 EmbodiedEvo: Self-Evolving Coding Agent For Physical Intelligence https://ax-news.com/?article=216085503 AX-NEWS en 2026-10-15T04:00:00+00:00 Verification and Forward Invariance of Control Barrier Functions for Differential-Algebraic Systems https://ax-news.com/?article=216085505 AX-NEWS en 2026-10-15T04:00:00+00:00 CorrelationFlow: A Training-Free Geometric Approach for LiDAR Scene Flow Estimation https://ax-news.com/?article=216085506 AX-NEWS en 2026-10-15T04:00:00+00:00 Colon3R: Cross-Domain 3D Reconstruction from Monocular Colonoscopic Video https://ax-news.com/?article=216085507 AX-NEWS en 2026-10-15T04:00:00+00:00 Imagine the Future, Internalize the Gist: Efficient VLA Reasoning via Internalized Spatiotemporal Imagination https://ax-news.com/?article=216085510 AX-NEWS en 2026-10-15T04:00:00+00:00 Thinker-WM: A Unified World Model with Shared Multimodal Representations for Embodied Intelligence https://ax-news.com/?article=216085514 AX-NEWS en 2026-10-15T04:00:00+00:00 LLMs program using Reusable and Composable Abstract Representations https://ax-news.com/?article=216085517 AX-NEWS en 2026-10-15T04:00:00+00:00 LLMON: An LLM-native Markup Language to Leverage Structure and Semantics at the LLM Interface https://ax-news.com/?article=216085518 AX-NEWS en 2026-10-15T04:00:00+00:00 Explorable Proofs: Making Written Proofs Explorable by Grounding Them in Formal Representations https://ax-news.com/?article=216085519 AX-NEWS en 2026-10-15T04:00:00+00:00 Cover Semantics for Intuitionistic Modalities https://ax-news.com/?article=216085520 AX-NEWS en 2026-10-15T04:00:00+00:00 Formalizing Flag Algebras in Lean https://ax-news.com/?article=216085525 AX-NEWS en 2026-10-15T04:00:00+00:00 OS-Bench: Evaluating SWE Agents on Cross-OS Code Migration https://ax-news.com/?article=216085530 AX-NEWS en 2026-10-15T04:00:00+00:00 Taming the Online Software Engineering Tongue: Detecting and Reducing Offensive Language in Software Communities https://ax-news.com/?article=216085533 AX-NEWS en 2026-10-15T04:00:00+00:00 SWE-Nexus: Automated Composition of Software Engineering Tasks from Test Execution https://ax-news.com/?article=216085534 AX-NEWS en 2026-10-15T04:00:00+00:00 The Code of Theseus: Can Agents Rebuild Software from Recovered Design Documents? https://ax-news.com/?article=216085538 AX-NEWS en 2026-10-15T04:00:00+00:00 Mission (Im)Possible: Towards Autonomous Discovery of Autopilot Logic Flaws in Open-Source Drone Frameworks https://ax-news.com/?article=216085539 AX-NEWS en 2026-10-15T04:00:00+00:00 P2Patch: Exploit-Guided Vulnerability Repair https://ax-news.com/?article=216085541 AX-NEWS en 2026-10-15T04:00:00+00:00 Securing High-Concurrency Ticket Sales: A Framework Based on Microservice https://ax-news.com/?article=216085543 AX-NEWS en 2026-10-15T04:00:00+00:00 Terminal Agents Suffice for Enterprise Automation https://ax-news.com/?article=216085546 AX-NEWS en 2026-10-15T04:00:00+00:00 An Empirical Study of Gemini 3 for Detecting Natural Language Test Smells in Manual Test Cases https://ax-news.com/?article=216085550 AX-NEWS en 2026-10-15T04:00:00+00:00 MOCHA: Multi-Objective Chebyshev Annealing for Agent Skill Optimization https://ax-news.com/?article=216085551 AX-NEWS en 2026-10-15T04:00:00+00:00 BTS-AgentBench: A Deterministic, Replayable Pipeline from Read-Only Telemetry Logs to Agent Benchmarks https://ax-news.com/?article=216085553 AX-NEWS en 2026-10-15T04:00:00+00:00 SoftwareGym: Scaling Computer-Use Agent Training with Diverse Synthesized Software Environments https://ax-news.com/?article=216085562 AX-NEWS en 2026-10-15T04:00:00+00:00 TrackShield: An Efficient Runtime Defense Against Availability Attacks on High-Performance Real-Time Multi-Object Tracking https://ax-news.com/?article=216085565 AX-NEWS en 2026-10-15T04:00:00+00:00 Quantum-Resilient Secure Protocol for Decentralized Edge-IoT Peer-to-Peer Energy Trading Systems https://ax-news.com/?article=216085567 AX-NEWS en 2026-10-15T04:00:00+00:00 Mission (Im)Possible: Towards Autonomous Discovery of Autopilot Logic Flaws in Open-Source Drone Frameworks https://ax-news.com/?article=216085572 AX-NEWS en 2026-10-15T04:00:00+00:00 DarKnight: Retrieval-Guided Agentic Framework for Breaking Dark Web CAPTCHA Gates https://ax-news.com/?article=216085573 AX-NEWS en 2026-10-15T04:00:00+00:00 Lost in the Fallback: How Reliably Do Typed Decision Models Use Fallback Options? https://ax-news.com/?article=216085575 AX-NEWS en 2026-10-15T04:00:00+00:00 Quiet Triggers, Loud Footprints: A Tri-Space Measurement Study of Backdoor Stealthiness https://ax-news.com/?article=216085577 AX-NEWS en 2026-10-15T04:00:00+00:00 ESAU: Expeditious Swarm Remote Attestation for Pub-Sub IoT Networks with Untrusted Cloud-based Proxy Verifier https://ax-news.com/?article=216085578 AX-NEWS en 2026-10-15T04:00:00+00:00 CoRedSkill: Stealthy Skill Composition Attacks via AST-Guided Injection https://ax-news.com/?article=216085583 AX-NEWS en 2026-10-15T04:00:00+00:00 Building Sound Evaluation Practices for Rust-Based Security Frameworks https://ax-news.com/?article=216085584 AX-NEWS en 2026-10-15T04:00:00+00:00 Phantomware: a Data Augmentation Framework for the Detection of Emerging Malware Campaigns https://ax-news.com/?article=216085589 AX-NEWS en 2026-10-15T04:00:00+00:00 Differentially Private Learning of Markov Chains: Near-Optimal Sample Complexity for Item and User Level Privacy https://ax-news.com/?article=216085591 AX-NEWS en 2026-10-15T04:00:00+00:00 Global and Local Entropy Tests for STL Files Under IEEE-754 Validity Constraints https://ax-news.com/?article=216085595 AX-NEWS en 2026-10-15T04:00:00+00:00 Prioritizing Microservice Requests via Retries https://ax-news.com/?article=216085598 AX-NEWS en 2026-10-15T04:00:00+00:00 Penetration Testing for System Security: Methods and Practical Approaches https://ax-news.com/?article=216085599 AX-NEWS en 2026-10-15T04:00:00+00:00 Security Analysis of ChatGPT: Threats and Privacy Risks https://ax-news.com/?article=216085600 AX-NEWS en 2026-10-15T04:00:00+00:00 It's My Agent, Not Me: Personal Privacy Boundaries in AI-Delegated Information Sharing https://ax-news.com/?article=216085602 AX-NEWS en 2026-10-15T04:00:00+00:00 Towards Secure Agent Skills: Architecture, Threat Taxonomy, and Security Analysis https://ax-news.com/?article=216085608 AX-NEWS en 2026-10-15T04:00:00+00:00 A2ABreak: Systematic Security Analysis of the A2A Protocol https://ax-news.com/?article=216085613 AX-NEWS en 2026-10-15T04:00:00+00:00 Natural Code Transformation Confuses Agents in Vulnerability Analysis https://ax-news.com/?article=216085615 AX-NEWS en 2026-10-15T04:00:00+00:00 SkillMarker: A KGW-Based Watermarking Method for Agent Skill Ownership Verification https://ax-news.com/?article=216085618 AX-NEWS en 2026-10-15T04:00:00+00:00 SkillScreen: High-Recall Screening of Malicious Agent Skills with Decision Models https://ax-news.com/?article=216085620 AX-NEWS en 2026-10-15T04:00:00+00:00 X.js: A Live Benchmark for Node.js Taint-Style Vulnerabilities https://ax-news.com/?article=216085622 AX-NEWS en 2026-10-15T04:00:00+00:00 Majority Bit-Aware Watermarking For Large Language Models https://ax-news.com/?article=216085624 AX-NEWS en 2026-10-15T04:00:00+00:00 A quantum algorithm for one-shot signatures https://ax-news.com/?article=216085625 AX-NEWS en 2026-10-15T04:00:00+00:00 Same Request, Different Boundary: Evaluating Cybersecurity Assistance across Conversational Contexts https://ax-news.com/?article=216085628 AX-NEWS en 2026-10-15T04:00:00+00:00 AI-Driven, Timing-Aware Power Optimization https://ax-news.com/?article=216085629 AX-NEWS en 2026-10-15T04:00:00+00:00 From Prompts to Silicon: Scaling LLM-Assisted Chip Design with the AI Hardware Design League https://ax-news.com/?article=216085630 AX-NEWS en 2026-10-15T04:00:00+00:00 O-SCOPE: a Raspberry Pi Pico oscilloscope https://ax-news.com/?article=216085631 AX-NEWS en 2026-10-15T04:00:00+00:00 CacheSmith: Accurate RAG Serving under Latency SLOs with Adaptive KV Reuse https://ax-news.com/?article=216085633 AX-NEWS en 2026-10-15T04:00:00+00:00 TALU: A Reconfigurable Tiled-ALU Grid for RISC-V https://ax-news.com/?article=216085635 AX-NEWS en 2026-10-15T04:00:00+00:00 ESL-former: Event Sparse Linear Transformer for FPGA-Accelerated Malware Detection https://ax-news.com/?article=216085638 AX-NEWS en 2026-10-15T04:00:00+00:00 Action Jets: Learning the Local Shape of the Action-conditioned Data Manifold https://ax-news.com/?article=216085639 AX-NEWS en 2026-10-15T04:00:00+00:00 How Far Can Coding Agents Go in Visual Generation? https://ax-news.com/?article=216085640 AX-NEWS en 2026-10-15T04:00:00+00:00 Why Do VLMs Fail at Remote Physiological Measurement? Rethinking with Physiological Grounding and Numerical Alignment https://ax-news.com/?article=216085641 AX-NEWS en 2026-10-15T04:00:00+00:00 WorldMemBench: A Comprehensive Benchmark for Memory of Video World Models https://ax-news.com/?article=216085643 AX-NEWS en 2026-10-15T04:00:00+00:00 The Gap Is in the Geometry: A Convergent Meta-Analysis of Multi-Facet Aerial and Remote Sensing Video Understanding https://ax-news.com/?article=216085647 AX-NEWS en 2026-10-15T04:00:00+00:00 Decoupled Drift-Diffusion World Models for Consistent Future Frame Prediction https://ax-news.com/?article=216085648 AX-NEWS en 2026-10-15T04:00:00+00:00 A Gradient-Regularized Deep Learning Method for Restoring Image in Myopic Vision https://ax-news.com/?article=216085649 AX-NEWS en 2026-10-15T04:00:00+00:00 Long-horizon Video Generation with Slot Memory Addressed By Region Tokens https://ax-news.com/?article=216085651 AX-NEWS en 2026-10-15T04:00:00+00:00 Kandinsky S2V 1.0: Audio-Driven Avatar Video Generation https://ax-news.com/?article=216085653 AX-NEWS en 2026-10-15T04:00:00+00:00 SonoWorld: Towards Interactive Pose-Controllable Ultrasound World Models https://ax-news.com/?article=216085657 AX-NEWS en 2026-10-15T04:00:00+00:00 The Impact of Detector Architecture, Model Scale, and Scene Density on Multi-Pedestrian Tracking https://ax-news.com/?article=216085664 AX-NEWS en 2026-10-15T04:00:00+00:00 Holi-Spatial 360: Generative Reconstruction from Sparse Panoramas for Spatial Rendering and Intelligence https://ax-news.com/?article=216085666 AX-NEWS en 2026-10-15T04:00:00+00:00 HyrCap: Hybrid Rank-Calibration of Action Proposals for Temporal Event Understanding https://ax-news.com/?article=216085669 AX-NEWS en 2026-10-15T04:00:00+00:00 Cross-Scenario Industrial Defect Detection via Domain-Robust Training and Metric-Aligned Selection https://ax-news.com/?article=216085670 AX-NEWS en 2026-10-15T04:00:00+00:00 TextVerifier: Seeing Beyond Recognition to Verify Chinese Text Rendering https://ax-news.com/?article=216085678 AX-NEWS en 2026-10-15T04:00:00+00:00 Adaptive Observation Control for Active Visual Recognition https://ax-news.com/?article=216085681 AX-NEWS en 2026-10-15T04:00:00+00:00 SPECTRA-VLA: Base-Fine Hyperspectral Token Transfer at Frozen Vision-Language-Action Interfaces https://ax-news.com/?article=216085682 AX-NEWS en 2026-10-15T04:00:00+00:00 Remember, Revisit, Revise: Scaffold Memory for Long-Horizon 3D Geometry https://ax-news.com/?article=216085685 AX-NEWS en 2026-10-15T04:00:00+00:00 No Way To Steal My Face: Proactive Defense Against Identity-Preserving Personalized Generation https://ax-news.com/?article=216085687 AX-NEWS en 2026-10-15T04:00:00+00:00 Mitigating Video Hallucinations via Attention-Guided Representation Perturbation https://ax-news.com/?article=216085688 AX-NEWS en 2026-10-15T04:00:00+00:00 A Diagnostic Study of World-Space Human Recovery Under High Camera Dynamics https://ax-news.com/?article=216085691 AX-NEWS en 2026-10-15T04:00:00+00:00 Discriminative Score Function: Turning Pretrained Models into Functional Generative Priors https://ax-news.com/?article=216085692 AX-NEWS en 2026-10-15T04:00:00+00:00 Physics-Shaped, Not Physical: Auditing Physics-Guided Underwater Image Restoration https://ax-news.com/?article=216085693 AX-NEWS en 2026-10-15T04:00:00+00:00 Q-MAGIC: Quad-only Mesh Autoregressive Generation via Singularity-Aware Circular Relative Offset Tokenization https://ax-news.com/?article=216085696 AX-NEWS en 2026-10-15T04:00:00+00:00 StateCraft: Augmenting Video World Models with Abstract-State Reasoning https://ax-news.com/?article=216085700 AX-NEWS en 2026-10-15T04:00:00+00:00 DeltaStreamer: Towards Human-Like Agentic Streaming Video Understanding https://ax-news.com/?article=216085702 AX-NEWS en 2026-10-15T04:00:00+00:00 CoDy: Codec Dynamics as Complementary Priors for Unsupervised Temporal Action Localization https://ax-news.com/?article=216085703 AX-NEWS en 2026-10-15T04:00:00+00:00 BluePixel: Toward Native 4K Agentic Image Editing https://ax-news.com/?article=216085704 AX-NEWS en 2026-10-15T04:00:00+00:00 Multimodal Medical Image Parsing with Task-Specific Low-Rank Adapters https://ax-news.com/?article=216085706 AX-NEWS en 2026-10-15T04:00:00+00:00 SAM3RL: Memory Control via Reinforcement Learning for Visual Object Tracking https://ax-news.com/?article=216085708 AX-NEWS en 2026-10-15T04:00:00+00:00 Why 3D Reconstruction Breaks Down on Under-Ice AUV Video, and How to Predict It https://ax-news.com/?article=216085713 AX-NEWS en 2026-10-15T04:00:00+00:00 When Pairwise Preferences Cycle: A Reliability-Anchored Preference Walk for Video GRPO https://ax-news.com/?article=216085715 AX-NEWS en 2026-10-15T04:00:00+00:00 RepForcing: Representation-Space Initialization for Autoregressive Video Distillation https://ax-news.com/?article=216085716 AX-NEWS en 2026-10-15T04:00:00+00:00 DreamHMR: From Video Generation to Human Motion Modeling via Structural Focusing https://ax-news.com/?article=216085729 AX-NEWS en 2026-10-15T04:00:00+00:00 Read, Parse, Describe: Unified Document Parsing with Visual Element Description Generation https://ax-news.com/?article=216085731 AX-NEWS en 2026-10-15T04:00:00+00:00 ReferFlow: Beyond Final-Target Localization for Complex Referring Expressions https://ax-news.com/?article=216085735 AX-NEWS en 2026-10-15T04:00:00+00:00 Hybrid supervised instance segmentation by learning label noise suppression https://ax-news.com/?article=216085736 AX-NEWS en 2026-10-15T04:00:00+00:00 Infant Fingerprints: Quality Assessment ＆ Recognition https://ax-news.com/?article=216085739 AX-NEWS en 2026-10-15T04:00:00+00:00 VascuSR: Iterative Anatomy-Aware Diffusion for CT Super-Resolution https://ax-news.com/?article=216085740 AX-NEWS en 2026-10-15T04:00:00+00:00 Reliability-Aware Multimodal Sentiment Prediction Under Local Modality Missingness https://ax-news.com/?article=216085741 AX-NEWS en 2026-10-15T04:00:00+00:00 Speculative Sampling in Interactive Video Generation https://ax-news.com/?article=216085742 AX-NEWS en 2026-10-15T04:00:00+00:00 A$^3$PreCore: Robust Rigid Registration for Native FLAIR-Space Brain-Mask Transfer https://ax-news.com/?article=216085743 AX-NEWS en 2026-10-15T04:00:00+00:00 Any Time, Any Space: A World-State-Centric Framework for Agentic Video Generation https://ax-news.com/?article=216085744 AX-NEWS en 2026-10-15T04:00:00+00:00 Player-1: Learning to Play from Synthetic Experience https://ax-news.com/?article=216085746 AX-NEWS en 2026-10-15T04:00:00+00:00 GeoThinker-$F$: Endogenous Predictive World Representations for Fast Spatial Intelligence https://ax-news.com/?article=216085747 AX-NEWS en 2026-10-15T04:00:00+00:00 DynThinker: Unifying Static 3D and Dynamic 4D Spatial Reasoning https://ax-news.com/?article=216085748 AX-NEWS en 2026-10-15T04:00:00+00:00 CommerceGen-Studio: An End-to-End Framework for Commercial-Grade Main-Image Generation https://ax-news.com/?article=216085753 AX-NEWS en 2026-10-15T04:00:00+00:00 $\lambda_0$: Scaling Open-World Egocentric Human Data for Humanoid Loco-Manipulation https://ax-news.com/?article=216085759 AX-NEWS en 2026-10-15T04:00:00+00:00 Deep Learning for Atmospheric Turbulence Mitigation: A Comparison Between GANs and Transformers https://ax-news.com/?article=216085760 AX-NEWS en 2026-10-15T04:00:00+00:00 Integrated Novelty Detection Systems: From Sensor Networks to Multi-Novelty Computer Vision https://ax-news.com/?article=216085763 AX-NEWS en 2026-10-15T04:00:00+00:00 Vision-Language Models Integrate Conflicting Evidence Like Biased Bayesian Observers https://ax-news.com/?article=216085764 AX-NEWS en 2026-10-15T04:00:00+00:00 From Failures to Learnable Worlds: Policy-Conditioned Environment Generation for Navigation Agents https://ax-news.com/?article=216085774 AX-NEWS en 2026-10-15T04:00:00+00:00 Cortex: Consolidating Context into Parametric Memory https://ax-news.com/?article=216085777 AX-NEWS en 2026-10-15T04:00:00+00:00 Generative Representation Learning for Scalable Latent Tokenization https://ax-news.com/?article=216085781 AX-NEWS en 2026-10-15T04:00:00+00:00 A LoRA is Worth a Thousand Pictures https://ax-news.com/?article=216085783 AX-NEWS en 2026-10-15T04:00:00+00:00 Video Depth Anything: Consistent Depth Estimation for Super-Long Videos https://ax-news.com/?article=216085786 AX-NEWS en 2026-10-15T04:00:00+00:00 Enabling Validation for Robust Few-Shot Recognition https://ax-news.com/?article=216085789 AX-NEWS en 2026-10-15T04:00:00+00:00 Chain of Time: In-Context Physical Simulation with Image Generation Models https://ax-news.com/?article=216085793 AX-NEWS en 2026-10-15T04:00:00+00:00 CASHEW: Stabilizing Multimodal Reasoning via Iterative Trajectory Aggregation https://ax-news.com/?article=216085795 AX-NEWS en 2026-10-15T04:00:00+00:00 Flow Matching with Uncertainty Quantification and Guidance https://ax-news.com/?article=216085797 AX-NEWS en 2026-10-15T04:00:00+00:00 Global Cross-Modal Geo-Localization: A Million-Scale Dataset and a Physical Consistency Learning Framework https://ax-news.com/?article=216085798 AX-NEWS en 2026-10-15T04:00:00+00:00 Selective Prediction Forgetting for Adaptation of Weakly Supervised Localization of Histology Images https://ax-news.com/?article=216085799 AX-NEWS en 2026-10-15T04:00:00+00:00 GenState-AI: State-Aware Dataset for Text-to-Video Retrieval on AI-Generated Videos https://ax-news.com/?article=216085801 AX-NEWS en 2026-10-15T04:00:00+00:00 KiToke: Distribution-Aware Token Compression for Video Large Language Models https://ax-news.com/?article=216085803 AX-NEWS en 2026-10-15T04:00:00+00:00 Beyond Reconstruction: Reconstruction-to-Vector Diffusion for Hyperspectral Anomaly Detection https://ax-news.com/?article=216085804 AX-NEWS en 2026-10-15T04:00:00+00:00 Topology-Aware Representation Alignment for Semi-Supervised Vision-Language Learning https://ax-news.com/?article=216085805 AX-NEWS en 2026-10-15T04:00:00+00:00 Learning Dynamic Evidence Routes for Vision Transformer Probing https://ax-news.com/?article=216085807 AX-NEWS en 2026-10-15T04:00:00+00:00 Selection, Not Fusion: Radar-Modulated State Space Models for Radar-Camera Depth Estimation https://ax-news.com/?article=216085809 AX-NEWS en 2026-10-15T04:00:00+00:00 OmniSelect: Dynamic Modality-Aware Token Compression for Efficient Omni-modal Large Language Models https://ax-news.com/?article=216085812 AX-NEWS en 2026-10-15T04:00:00+00:00 Masked Diffusion Vision-Language Models for Temporal Action Localization https://ax-news.com/?article=216085814 AX-NEWS en 2026-10-15T04:00:00+00:00 STREAM: Stochastic Riemannian Flow Matching with Anisotropic Decoder for Digital Histopathology Image Generation https://ax-news.com/?article=216085819 AX-NEWS en 2026-10-15T04:00:00+00:00 CorrelationFlow: A Training-Free Geometric Approach for LiDAR Scene Flow Estimation https://ax-news.com/?article=216085820 AX-NEWS en 2026-10-15T04:00:00+00:00 Efficient Noise Context-Aware Representation for Low-Dose CT Denoising https://ax-news.com/?article=216085824 AX-NEWS en 2026-10-15T04:00:00+00:00 AdaVDR: Adaptive Tool Use and Reflection for Video Deep Research https://ax-news.com/?article=216085828 AX-NEWS en 2026-10-15T04:00:00+00:00 CLON: Cue-Calibrated Linguistic Object Onboarding for Zero-Shot 6D Pose Front-Ends https://ax-news.com/?article=216085830 AX-NEWS en 2026-10-15T04:00:00+00:00 GAE: Learning a Geometry-Native Latent Space for 3D-Consistent World Generation https://ax-news.com/?article=216085835 AX-NEWS en 2026-10-15T04:00:00+00:00 DMAD: Distribution Matching as Adversarial Distillation for Fast Visual Generation https://ax-news.com/?article=216085836 AX-NEWS en 2026-10-15T04:00:00+00:00 Imagine the Future, Internalize the Gist: Efficient VLA Reasoning via Internalized Spatiotemporal Imagination https://ax-news.com/?article=216085838 AX-NEWS en 2026-10-15T04:00:00+00:00 Identity-Duplication Auditing in National-Scale Neuroimaging Repositories https://ax-news.com/?article=216085840 AX-NEWS en 2026-10-15T04:00:00+00:00 Hide and Seek: HIDE Concepts to SEEK explanations for black box models https://ax-news.com/?article=216085841 AX-NEWS en 2026-10-15T04:00:00+00:00 SliderEdit++: Improved Slider Trajectories in Instruction-Based Image Editing https://ax-news.com/?article=216085842 AX-NEWS en 2026-10-15T04:00:00+00:00 MvFFN: Multi-view Floor plan Feed-forward Network for Unposed Wide-Baseline Panorama Layout Reconstruction https://ax-news.com/?article=216085843 AX-NEWS en 2026-10-15T04:00:00+00:00 RealityBench: Simulated Environments to Evaluate a Vision Language Model's Ability to Document Human Physical Work https://ax-news.com/?article=216085844 AX-NEWS en 2026-10-15T04:00:00+00:00 Use Of Convolutional Neural Networks In Detection Of Branch Dieback Disease In Pequi Trees https://ax-news.com/?article=216085845 AX-NEWS en 2026-10-15T04:00:00+00:00 ProtoPur: Prototype-Purity Pseudo-Labeling for Weakly Supervised Instance Learning in Pathology https://ax-news.com/?article=216085846 AX-NEWS en 2026-10-15T04:00:00+00:00 Reference-Efficient Multimodal Bitstream-Corrupted Video Recovery via Depth-Conditioned Adaptation https://ax-news.com/?article=216085851 AX-NEWS en 2026-10-15T04:00:00+00:00 Plan-Bench: Can Existing VLMs Go Well Beyond Perception to Reason and Plan in Embodied Worlds? https://ax-news.com/?article=216085852 AX-NEWS en 2026-10-15T04:00:00+00:00 MiniDog: Dog-Breed Text-to-image Flow Matching from Pretraining to Fine-Tuning on 4 Consumer GPUs https://ax-news.com/?article=216085853 AX-NEWS en 2026-10-15T04:00:00+00:00 Quantifying the Impact of Motion on 2D Gaze Estimation in Real-World Mobile Interactions https://ax-news.com/?article=216085854 AX-NEWS en 2026-10-15T04:00:00+00:00 VEDA: Generation of 3D Molecules via Variance-Exploding Diffusion with Annealing https://ax-news.com/?article=216085855 AX-NEWS en 2026-10-15T04:00:00+00:00 Schr\"odinger's Navigator: Imagining an Ensemble of Futures for Zero-Shot Object Navigation https://ax-news.com/?article=216085856 AX-NEWS en 2026-10-15T04:00:00+00:00 Imaging-anchored Multiomics in Cardiovascular Disease: Integrating Cardiac Imaging, Bulk, Single-cell, and Spatial Transcriptomics https://ax-news.com/?article=216085861 AX-NEWS en 2026-10-15T04:00:00+00:00 Reward Design for Physical Reasoning in Vision-Language Models https://ax-news.com/?article=216085864 AX-NEWS en 2026-10-15T04:00:00+00:00 LIME: Learning Intent-aware Camera Motion from Egocentric Video https://ax-news.com/?article=216085866 AX-NEWS en 2026-10-15T04:00:00+00:00 MeshSplatBench: A Unified Benchmark for Triangle- and Mesh-Based Neural Rendering https://ax-news.com/?article=216085867 AX-NEWS en 2026-10-15T04:00:00+00:00 VGM-VS: Rethinking Visual Geometry Model for High-Precision Visual Servoing https://ax-news.com/?article=216085868 AX-NEWS en 2026-10-15T04:00:00+00:00 MultiFly: A Real-World Multimodal Aerial Dataset with Annotation-Efficient Label Transfer and Cross-Modal Semantic Consistency https://ax-news.com/?article=216085870 AX-NEWS en 2026-10-15T04:00:00+00:00 Data-Free Continual Learning for World Action Model with Rectified Generative Replay https://ax-news.com/?article=216085873 AX-NEWS en 2026-10-15T04:00:00+00:00 Evaluating Large Language Models for Multilingual Abstractive Summarization: A Comprehensive Study of English and Bengali https://ax-news.com/?article=216085875 AX-NEWS en 2026-10-15T04:00:00+00:00 Joint Subspace Sparse Attention for Efficient Long-Context Decoding https://ax-news.com/?article=216085877 AX-NEWS en 2026-10-15T04:00:00+00:00 Pre-Trained Language Models as Zero-Shot Tools for Social Science Research https://ax-news.com/?article=216085880 AX-NEWS en 2026-10-15T04:00:00+00:00 DecisionRobust: Benchmarking Robustness for JEV Style Decision Models Across Text and Vision https://ax-news.com/?article=216085881 AX-NEWS en 2026-10-15T04:00:00+00:00 CAFE: Confining Feature Distillation to Language-Routed Adapters for Compact Multilingual Automatic Speech Recognition https://ax-news.com/?article=216085883 AX-NEWS en 2026-10-15T04:00:00+00:00 Fantastic Metrics and How to Find Them: Meta-Evaluating Metrics for Multi-lingual Style-Personalized Generation https://ax-news.com/?article=216085885 AX-NEWS en 2026-10-15T04:00:00+00:00 How to Evaluate When You Don't Know How to Evaluate? Choosing Reliable Setups for Base Language Model Benchmarking https://ax-news.com/?article=216085887 AX-NEWS en 2026-10-15T04:00:00+00:00 Weighted Ensemble Sampling for Rare-Event Estimation in Language Models https://ax-news.com/?article=216085888 AX-NEWS en 2026-10-15T04:00:00+00:00 DUALVIEW: Leveraging Broad and Output-Specific Evidence for LLM-based Multi-Output Text Regression https://ax-news.com/?article=216085890 AX-NEWS en 2026-10-15T04:00:00+00:00 Do Syntax Heads Influence Model Behavior? https://ax-news.com/?article=216085892 AX-NEWS en 2026-10-15T04:00:00+00:00 Whose Data, Whose Benchmark? A User-Centric Framework for Auditing Evaluation Resources https://ax-news.com/?article=216085893 AX-NEWS en 2026-10-15T04:00:00+00:00 Can LLM Agents Efficiently Identify Appliance Faults? Insights From Diagnosing a Simulated Appliance https://ax-news.com/?article=216085895 AX-NEWS en 2026-10-15T04:00:00+00:00 PersEvalBench: Can LLM Evaluators Judge Contextually Appropriate Use of Persona Information? https://ax-news.com/?article=216085896 AX-NEWS en 2026-10-15T04:00:00+00:00 TopicMerge: A Divide and Conquer Approach to Topic Modeling https://ax-news.com/?article=216085898 AX-NEWS en 2026-10-15T04:00:00+00:00 Target-Token Asymmetry Can Masquerade As Depth Specialization https://ax-news.com/?article=216085899 AX-NEWS en 2026-10-15T04:00:00+00:00 Tail Competition Explains Scaling in Best-of-N Sampling for Verifiable Problems https://ax-news.com/?article=216085908 AX-NEWS en 2026-10-15T04:00:00+00:00 How Do LLMs Understand Legal Philosophy? Diagnosing Legal-Philosophical Reasoning in LLMs https://ax-news.com/?article=216085914 AX-NEWS en 2026-10-15T04:00:00+00:00 Retrieve What Helps, Only When It Helps: Agentic Reinforcement Learning for Selective Retrieval-Augmented Machine Translation https://ax-news.com/?article=216085915 AX-NEWS en 2026-10-15T04:00:00+00:00 A Unified Response Framework for Questions and Tutoring Dialogues https://ax-news.com/?article=216085918 AX-NEWS en 2026-10-15T04:00:00+00:00 Evidence-Anchored Overdose Death Prediction from Death Investigation Reports https://ax-news.com/?article=216085926 AX-NEWS en 2026-10-15T04:00:00+00:00 Selective Reasoning for Typed Decision Models: When to Start, Read, and Stop https://ax-news.com/?article=216085927 AX-NEWS en 2026-10-15T04:00:00+00:00 HACHIMI-II: From Role-Play to Learner Behavior Modeling for Faithful Student Simulation https://ax-news.com/?article=216085932 AX-NEWS en 2026-10-15T04:00:00+00:00 RouteWeaver: Weaving Mode Selection and Execution into Unified LLM Routing https://ax-news.com/?article=216085933 AX-NEWS en 2026-10-15T04:00:00+00:00 Beyond State Capacity: Why Retrieval Breaks in Mamba https://ax-news.com/?article=216085935 AX-NEWS en 2026-10-15T04:00:00+00:00 MakSafe: A Spatiotemporal Semantic Framework for Formal Specification and Compliance Checking of Road Vehicle Safety Rules https://ax-news.com/?article=216085937 AX-NEWS en 2026-10-15T04:00:00+00:00 Beyond Reachability: A Relation-Semantic Reasoning Framework for Biomedical Multi-hop QA https://ax-news.com/?article=216085938 AX-NEWS en 2026-10-15T04:00:00+00:00 Qwen-MT-Lumen at WMT2026: Instruction-Specialized Translation via Quality-Aware Training and On-Policy Distillation https://ax-news.com/?article=216085939 AX-NEWS en 2026-10-15T04:00:00+00:00 PRISMATIC : Prescription Risk Inspection System for Multi-Agent Treatment Interaction in Clinical Decision-Making https://ax-news.com/?article=216085940 AX-NEWS en 2026-10-15T04:00:00+00:00 Likelihood Is Not Authorship: Can We Reliably Measure Human Contribution in AI-Assisted Writing? https://ax-news.com/?article=216085944 AX-NEWS en 2026-10-15T04:00:00+00:00 Delta Tokenizer: Reference-Identical Tokenization of Session Deltas and Segment-Parallelism for Long Prompts on Multicore CPUs https://ax-news.com/?article=216085949 AX-NEWS en 2026-10-15T04:00:00+00:00 RCCM: Diagnosing Gains and Harms in Reasoning-Prompt Transfer https://ax-news.com/?article=216085953 AX-NEWS en 2026-10-15T04:00:00+00:00 MemDuet: Learning Dual-Process Memory for Long-Context Reasoning https://ax-news.com/?article=216085955 AX-NEWS en 2026-10-15T04:00:00+00:00 Does Machine Translation Retain Media Bias? https://ax-news.com/?article=216085959 AX-NEWS en 2026-10-15T04:00:00+00:00 Gray-Box Hallucination Detection in LLMs with Token Identities https://ax-news.com/?article=216085960 AX-NEWS en 2026-10-15T04:00:00+00:00 A Strong Harness Narrows the Model Gap: A Comparative Evaluation for Legislative Document-to-XML Conversion https://ax-news.com/?article=216085962 AX-NEWS en 2026-10-15T04:00:00+00:00 What Is a Clarification? Estimating Model-Dependent Input Ambiguity https://ax-news.com/?article=216085966 AX-NEWS en 2026-10-15T04:00:00+00:00 Why Generate a Click? Plug-in Decision Heads for Web Agents https://ax-news.com/?article=216085967 AX-NEWS en 2026-10-15T04:00:00+00:00 Sparse Autoencoders for Mechanistic Interpretability in NLP: A Critical Survey of Recoverability, Interpretability, and Utility https://ax-news.com/?article=216085968 AX-NEWS en 2026-10-15T04:00:00+00:00 Gap Detection: Mitigating Homogenization through Demand and Defensibility https://ax-news.com/?article=216085971 AX-NEWS en 2026-10-15T04:00:00+00:00 When Occupation-derived Skills Don't Help: On the Limits of Skill-Augmented Career Path Prediction https://ax-news.com/?article=216085972 AX-NEWS en 2026-10-15T04:00:00+00:00 What Makes a Social Agent's Interactions Effective? Learning from Verifiable Outcomes in Paired Worlds https://ax-news.com/?article=216085975 AX-NEWS en 2026-10-15T04:00:00+00:00 Repairing Speech Access After Text Updates with Frozen Affine Fields https://ax-news.com/?article=216085976 AX-NEWS en 2026-10-15T04:00:00+00:00 Anuvani-LID: Robust and Calibrated Spoken Language Identification for Indian Languages https://ax-news.com/?article=216085977 AX-NEWS en 2026-10-15T04:00:00+00:00 CSWBench: Evaluating Context-Sensitive Code-Switching in Creative Writing https://ax-news.com/?article=216085979 AX-NEWS en 2026-10-15T04:00:00+00:00 Taking the PULSE of Medical Reasoning: Step-Level Retrieval Timing for Knowledge-Grounded Inference https://ax-news.com/?article=216085981 AX-NEWS en 2026-10-15T04:00:00+00:00 Anuvani-Diarization: Zero Shot Speaker Diarization and Annotation Conventions Across 22 Languages https://ax-news.com/?article=216085982 AX-NEWS en 2026-10-15T04:00:00+00:00 Do AI Agents Gossip? Evaluative Talk in Human and AI-Agent Online Communities https://ax-news.com/?article=216085985 AX-NEWS en 2026-10-15T04:00:00+00:00 From Triage to Impact: A Multi-Hop Reasoning Benchmark for Explainable Persian Hate Speech https://ax-news.com/?article=216085989 AX-NEWS en 2026-10-15T04:00:00+00:00 Analyzing performance of Retrieval Augmented Generation models for Question Answering Tasks https://ax-news.com/?article=216085990 AX-NEWS en 2026-10-15T04:00:00+00:00 The COUNT: Counting N-grams Unlocks Scaling on Host Memory and Training-Free Adaptation https://ax-news.com/?article=216085992 AX-NEWS en 2026-10-15T04:00:00+00:00 MolLean: A Process-Verifiable Language for Chemical Reasoning https://ax-news.com/?article=216085993 AX-NEWS en 2026-10-15T04:00:00+00:00 Equal CER, Unequal Damage: Severity-Weighted Character Error Rate for OCR https://ax-news.com/?article=216085994 AX-NEWS en 2026-10-15T04:00:00+00:00 ChronoCulture: Evaluating Cultural Awareness Across Time in Large Language Models https://ax-news.com/?article=216085995 AX-NEWS en 2026-10-15T04:00:00+00:00 AdaRSI: On-Demand Recursive Self-Improvement for Embodied Agents https://ax-news.com/?article=216085996 AX-NEWS en 2026-10-15T04:00:00+00:00 Lost in Translation: Why Lower Bias Scores Don't Mean Fairer Models https://ax-news.com/?article=216086000 AX-NEWS en 2026-10-15T04:00:00+00:00 PerSo: Investigating Facets of LLMs' Social Intelligence in Real-World Persuasion Scenarios https://ax-news.com/?article=216086002 AX-NEWS en 2026-10-15T04:00:00+00:00 Latent Compaction with Test-Time Training https://ax-news.com/?article=216086003 AX-NEWS en 2026-10-15T04:00:00+00:00 Knowledge Distillation from Large Reasoning Models to Compact Student Models: A Case Study on the John O Bryan Mathematics Competition https://ax-news.com/?article=216086010 AX-NEWS en 2026-10-15T04:00:00+00:00 Beyond Aggregate Accuracy: Item-Level Transitions in Prompt Optimization https://ax-news.com/?article=216086011 AX-NEWS en 2026-10-15T04:00:00+00:00 GroundGUI: GUI Grounding by High-Quality Data and Distillation-to-Reinforcement Learning https://ax-news.com/?article=216086013 AX-NEWS en 2026-10-15T04:00:00+00:00 Unlocking Structured Pruning for Reasoning Language Models via Attention-Preserving MLP Trimming https://ax-news.com/?article=216086015 AX-NEWS en 2026-10-15T04:00:00+00:00 MA-Bench: Measuring Operational Planning in Language Models https://ax-news.com/?article=216086018 AX-NEWS en 2026-10-15T04:00:00+00:00 ListQA: A Benchmark for Evaluating List-Formatted Factual Knowledge Retrieval in Large Language Models https://ax-news.com/?article=216086020 AX-NEWS en 2026-10-15T04:00:00+00:00 From Efficiency to Sufficiency: The Cost-Aware Measurement Design Framework for Automated Essay Scoring https://ax-news.com/?article=216086021 AX-NEWS en 2026-10-15T04:00:00+00:00 Truthful and Expected-Payment-Optimal Model Routing in Graph-Based Agentic Workflows https://ax-news.com/?article=216086022 AX-NEWS en 2026-10-15T04:00:00+00:00 Counterfactual Gate-Support Decomposition: Separating Selection from Redistribution in Training-Data Filtering https://ax-news.com/?article=216086024 AX-NEWS en 2026-10-15T04:00:00+00:00 Steering Vectors for Competing Ethical Frameworks Are Interchangeable: A Competing-Target Test for Activation Steering https://ax-news.com/?article=216086025 AX-NEWS en 2026-10-15T04:00:00+00:00 VLX-Go: Robust Embodied Tracking through Multi-Stage Learning and On-Policy Refinement https://ax-news.com/?article=216086026 AX-NEWS en 2026-10-15T04:00:00+00:00 Seeing, Maintaining, and Learning: The Evolution of Multimodal Agent Memory https://ax-news.com/?article=216086029 AX-NEWS en 2026-10-15T04:00:00+00:00 Diagnosing and Correcting Reward Hacking in Verifiable Instruction Following https://ax-news.com/?article=216086030 AX-NEWS en 2026-10-15T04:00:00+00:00 $\tau$-Emotion-Bench: Exposing the Interaction Fragility of LLM Agents through Real-World User Emotions https://ax-news.com/?article=216086031 AX-NEWS en 2026-10-15T04:00:00+00:00 Who's Behind the Text? Robust Model Authorship Attribution https://ax-news.com/?article=216086033 AX-NEWS en 2026-10-15T04:00:00+00:00 Twenty Days Later: A Pre-Registered Test of History-Based Forecasts of Brand Mentions in Gemini Answers https://ax-news.com/?article=216086036 AX-NEWS en 2026-10-15T04:00:00+00:00 Model What Matters: Decision-Guided Selective World Modeling for Language Agents https://ax-news.com/?article=216086040 AX-NEWS en 2026-10-15T04:00:00+00:00 Mitigating Video Hallucinations via Attention-Guided Representation Perturbation https://ax-news.com/?article=216086046 AX-NEWS en 2026-10-15T04:00:00+00:00 Designing Textual Interfaces To Enhance Llm Reasoning On Audio-Visual Question Answering https://ax-news.com/?article=216086047 AX-NEWS en 2026-10-15T04:00:00+00:00 LLM-Based Policy Compliance Verification of Loan Applications https://ax-news.com/?article=216086048 AX-NEWS en 2026-10-15T04:00:00+00:00 MultiPartyTurnBench: Benchmarking Floor Control in Multi-Party Spoken Dialogue https://ax-news.com/?article=216086051 AX-NEWS en 2026-10-15T04:00:00+00:00 SwarmRSI: Recursive Self-Improvement through Evolving Scientific Agent Swarm https://ax-news.com/?article=216086060 AX-NEWS en 2026-10-15T04:00:00+00:00 Anticipatory Evaluation of Language Models: Predicting LLM Benchmark Scores from Descriptions https://ax-news.com/?article=216086061 AX-NEWS en 2026-10-15T04:00:00+00:00 Eigen-Agent: Adaptive Multi-Agent Scientific Reasoning with Monitor-Based RAG https://ax-news.com/?article=216086062 AX-NEWS en 2026-10-15T04:00:00+00:00 EconCausal: A Context-Aware Economic Reasoning Benchmark for Large Language Models https://ax-news.com/?article=216086063 AX-NEWS en 2026-10-15T04:00:00+00:00 A large-scale pipeline for LLM-assisted corpus annotation: variation and change in the English consider construction https://ax-news.com/?article=216086066 AX-NEWS en 2026-10-15T04:00:00+00:00 QuantEval: A Benchmark for Financial Quantitative Tasks in Large Language Models https://ax-news.com/?article=216086068 AX-NEWS en 2026-10-15T04:00:00+00:00 MasalBench: A Benchmark for Contextual and Cross-Cultural Understanding of Persian Proverbs in LLMs https://ax-news.com/?article=216086070 AX-NEWS en 2026-10-15T04:00:00+00:00 Geometric Alignment without Functional Equivalence: A Layer-wise Analysis of the Speech-Text Modality Gap https://ax-news.com/?article=216086071 AX-NEWS en 2026-10-15T04:00:00+00:00 LoopRPT: Reinforcement Pre-Training for Looped Language Models https://ax-news.com/?article=216086072 AX-NEWS en 2026-10-15T04:00:00+00:00 PLACID: Privacy-preserving Large language models for Acronym Clinical Inference and Disambiguation https://ax-news.com/?article=216086073 AX-NEWS en 2026-10-15T04:00:00+00:00 AdaptFuse: Training-Free Sequential Preference Inference via Externalized Bayesian Computation https://ax-news.com/?article=216086074 AX-NEWS en 2026-10-15T04:00:00+00:00 Phantom Paradoxes: Language Models Treat Unresolved Circular Truth Dependence as Contradiction https://ax-news.com/?article=216086080 AX-NEWS en 2026-10-15T04:00:00+00:00 ConRAG: Consensus-Driven Evidence Flow for Multi-Hop Question Answering https://ax-news.com/?article=216086082 AX-NEWS en 2026-10-15T04:00:00+00:00 Ouvia: A User-centered Framework for Measuring Usability of Speech Translation in Real-World Communication Scenarios https://ax-news.com/?article=216086083 AX-NEWS en 2026-10-15T04:00:00+00:00 Explain Like I'm 5 or Whatever I Choose: Evaluating the Potential for Interactive Complexity in Language Model Responses https://ax-news.com/?article=216086084 AX-NEWS en 2026-10-15T04:00:00+00:00 When More Documents Hurt RAG: Measuring and Reducing Vector Search Dilution with Domain-Scoped Retrieval https://ax-news.com/?article=216086085 AX-NEWS en 2026-10-15T04:00:00+00:00 ProReviewer: Evidence-Driven Investigation for Scientific Peer Review https://ax-news.com/?article=216086086 AX-NEWS en 2026-10-15T04:00:00+00:00 HiMPO: Hindsight-Informed Memory Policy Optimization for Less-Entangled Credit in Long-Horizon Agents https://ax-news.com/?article=216086087 AX-NEWS en 2026-10-15T04:00:00+00:00 DEEPRUBRIC: Evidence-Tree Rubric Supervision for Efficient Reinforcement Learning of Deep Research Agents https://ax-news.com/?article=216086089 AX-NEWS en 2026-10-15T04:00:00+00:00 Every Time I Hire a Linguist, Inference Costs Go Down: On Linguistic Rules as Effective Prompt Compressors https://ax-news.com/?article=216086095 AX-NEWS en 2026-10-15T04:00:00+00:00 Hybrid Gated Attention https://ax-news.com/?article=216086096 AX-NEWS en 2026-10-15T04:00:00+00:00 LycheeMemory V2: Efficient Long-Term Memory for LLM Agents via Semantic Segment-Level Consolidation https://ax-news.com/?article=216086097 AX-NEWS en 2026-10-15T04:00:00+00:00 Refusing Intent, Not Form: Wrapper-Based Intent-Group Supervision for LLM Safety https://ax-news.com/?article=216086099 AX-NEWS en 2026-10-15T04:00:00+00:00 DCGC: Draft-Conditioned Global Correction for Complex Reasoning with Masked Diffusion Models https://ax-news.com/?article=216086100 AX-NEWS en 2026-10-15T04:00:00+00:00 TreeGraft: Adaptive Multi-Drafter Grafting for Tree-Based Speculative Decoding https://ax-news.com/?article=216086101 AX-NEWS en 2026-10-15T04:00:00+00:00 BTS-AgentBench: A Deterministic, Replayable Pipeline from Read-Only Telemetry Logs to Agent Benchmarks https://ax-news.com/?article=216086103 AX-NEWS en 2026-10-15T04:00:00+00:00 Lazy Grounding: Attacking Search Agents with Factual Evidence https://ax-news.com/?article=216086109 AX-NEWS en 2026-10-15T04:00:00+00:00 EduBehaviors: Assertion-based Schemas for Auditable Coding of Educational Dialogues https://ax-news.com/?article=216086110 AX-NEWS en 2026-10-15T04:00:00+00:00 Policy-Conditioned AI-Use Detection: An Evidentiary Framework for Academic Publishing https://ax-news.com/?article=216086112 AX-NEWS en 2026-10-15T04:00:00+00:00 Quality-Aware Self-Correcting Speech Translation on an Edge Device https://ax-news.com/?article=216086118 AX-NEWS en 2026-10-15T04:00:00+00:00 Evaluating LLMs as Agentic Workflow Executors in Real-World Customer Support Skills https://ax-news.com/?article=216086120 AX-NEWS en 2026-10-15T04:00:00+00:00 Do LLM Tutors Actually Teach? A Process-Centered Synthesis of the Tutoring Loop https://ax-news.com/?article=216086123 AX-NEWS en 2026-10-15T04:00:00+00:00 Back-Translation Still Matters: Leveraging Monolingual Data for Low-Resource Machine Translation with LLMs https://ax-news.com/?article=216086125 AX-NEWS en 2026-10-15T04:00:00+00:00 The Invisible Leash: Why RLVR May or May Not Escape Its Origin https://ax-news.com/?article=216086126 AX-NEWS en 2026-10-15T04:00:00+00:00 Ground-Truth Subgraphs for Better Training and Evaluation of Knowledge Graph Augmented LLMs https://ax-news.com/?article=216086127 AX-NEWS en 2026-10-15T04:00:00+00:00 The Instability of Safety: How Random Seeds and Temperature Expose Inconsistent LLM Refusal Behavior https://ax-news.com/?article=216086128 AX-NEWS en 2026-10-15T04:00:00+00:00 Dual-Evolving Reinforcement Learning for Automated Reward Design https://ax-news.com/?article=216086134 AX-NEWS en 2026-10-15T04:00:00+00:00 The Reasoning Trap -- Logical Reasoning as a Mechanistic Pathway to Situational Awareness https://ax-news.com/?article=216086139 AX-NEWS en 2026-10-15T04:00:00+00:00 Document-as-Image Representations Fall Short for Scientific Retrieval https://ax-news.com/?article=216086140 AX-NEWS en 2026-10-15T04:00:00+00:00 Ideological Bias in LLMs' Economic Causal Reasoning https://ax-news.com/?article=216086146 AX-NEWS en 2026-10-15T04:00:00+00:00 From Clicks to Intent: Cross-Platform Session Embeddings with LLM-Distilled Taxonomy for Financial Services Recommendations https://ax-news.com/?article=216086147 AX-NEWS en 2026-10-15T04:00:00+00:00 Algorithmic Unverifiability of Safety for Fixed and Recursively Self-Improving Systems https://ax-news.com/?article=216086151 AX-NEWS en 2026-10-15T04:00:00+00:00 Rubric Dropout: A Simple Way to Mitigate Reward Hacking in Rubric-as-Reward RL https://ax-news.com/?article=216086152 AX-NEWS en 2026-10-15T04:00:00+00:00 AVA-Encoder: Towards Agent-Native Video Representation Learning https://ax-news.com/?article=216086153 AX-NEWS en 2026-10-15T04:00:00+00:00 Mechanistic Circuit Identification for Controllable Data Generation https://ax-news.com/?article=216086156 AX-NEWS en 2026-10-15T04:00:00+00:00 SecJev: Bringing Security Expertise to System One Decision Models https://ax-news.com/?article=216086157 AX-NEWS en 2026-10-15T04:00:00+00:00 Lost in the bf16 Cast: Exporting Ternary Language Models Can Revert Most Low-Learning-Rate Code Changes https://ax-news.com/?article=216086159 AX-NEWS en 2026-10-15T04:00:00+00:00 Do LLMs Learn from Rewards in Context? : Rethinking the role of reward in In-Context RL https://ax-news.com/?article=216086160 AX-NEWS en 2026-10-15T04:00:00+00:00 RealityBench: Simulated Environments to Evaluate a Vision Language Model's Ability to Document Human Physical Work https://ax-news.com/?article=216086162 AX-NEWS en 2026-10-15T04:00:00+00:00 AlphaRLM: Aligning Language Models for Literature-Grounded Symbolic Factor Discovery https://ax-news.com/?article=216086163 AX-NEWS en 2026-10-15T04:00:00+00:00 Hidden in Plain Sight: Advancing Harmful Content Understanding via Perception-Aware Adversarial Self-Play https://ax-news.com/?article=216086169 AX-NEWS en 2026-10-15T04:00:00+00:00 Readout Scaling Shapes Sparse Feature Recovery https://ax-news.com/?article=216086173 AX-NEWS en 2026-10-15T04:00:00+00:00 Lotus: Learning to Understand Time-series by Learning to Forecast https://ax-news.com/?article=216086174 AX-NEWS en 2026-10-15T04:00:00+00:00 Inverse Reasoning Models for Efficient Post-Training and Verification from Answer-Only Data https://ax-news.com/?article=216086175 AX-NEWS en 2026-10-15T04:00:00+00:00 Do Vision CIL Methods Transfer to Protein? A Diagnostic Benchmark of Frozen Protein Encoders https://ax-news.com/?article=216086176 AX-NEWS en 2026-10-15T04:00:00+00:00 Do Perturbation Predictors Learn Gene Interactions? Diagnosing Extrapolation in Agentic Screening https://ax-news.com/?article=216086177 AX-NEWS en 2026-10-15T04:00:00+00:00 Token Utility for On-Policy Distillation via Local Trust-Region Optimization https://ax-news.com/?article=216086181 AX-NEWS en 2026-10-15T04:00:00+00:00 IR-PRM+ with Previous-Utility Prediction: Constant Regret and Best-Iterate Convergence https://ax-news.com/?article=216086183 AX-NEWS en 2026-10-15T04:00:00+00:00 Who Should We Listen to More? Welfare-Aware Preference Acquisition for Pluralistic Alignment https://ax-news.com/?article=216086186 AX-NEWS en 2026-10-15T04:00:00+00:00 Loss Curvature as a Sampling-Free Proxy for Memorization in Diffusion Models https://ax-news.com/?article=216086190 AX-NEWS en 2026-10-15T04:00:00+00:00 How Inner Optimizers Shape Replica Scaling https://ax-news.com/?article=216086191 AX-NEWS en 2026-10-15T04:00:00+00:00 Theoretical and Practical Advances in Hierarchical Bayesian Deep Learning Methodology https://ax-news.com/?article=216086192 AX-NEWS en 2026-10-15T04:00:00+00:00 Backpropagating Verifier Rewards Through Continuous Flow Language Models https://ax-news.com/?article=216086193 AX-NEWS en 2026-10-15T04:00:00+00:00 Beyond Aggregate Accuracy: Item-Level Transitions in Prompt Optimization https://ax-news.com/?article=216086194 AX-NEWS en 2026-10-15T04:00:00+00:00 Contextual Credit Policy Optimization https://ax-news.com/?article=216086197 AX-NEWS en 2026-10-15T04:00:00+00:00 PairIT: Autoregressive Transformers for Low-Data Molecule Optimization https://ax-news.com/?article=216086204 AX-NEWS en 2026-10-15T04:00:00+00:00 Adaptive Computation with Conformal Certification https://ax-news.com/?article=216086206 AX-NEWS en 2026-10-15T04:00:00+00:00 Narrowing the Collaboration Gap, Probably https://ax-news.com/?article=216086208 AX-NEWS en 2026-10-15T04:00:00+00:00 Spectral-MoE: Heterogeneous Per-Layer Expert Utilization in Dense-to-MoE Conversion https://ax-news.com/?article=216086209 AX-NEWS en 2026-10-15T04:00:00+00:00 LLMs program using Reusable and Composable Abstract Representations https://ax-news.com/?article=216086210 AX-NEWS en 2026-10-15T04:00:00+00:00 FinGREAT: Evaluating LLMs on Financial Graph-guided Retrieval And Typing https://ax-news.com/?article=216086212 AX-NEWS en 2026-10-15T04:00:00+00:00 Beyond Time Induction: Structured Conditional Neural Solvers for Parametric Stochastic-Volatility Pricing https://ax-news.com/?article=216086218 AX-NEWS en 2026-10-15T04:00:00+00:00 DTDD: Divergence-Triggered Dynamic Distillation for Reliable On-Policy Supervision https://ax-news.com/?article=216086219 AX-NEWS en 2026-10-15T04:00:00+00:00 Did the LLM Answer the Question? A Semantic Reconstruction Game for Jailbreak Evaluation https://ax-news.com/?article=216086220 AX-NEWS en 2026-10-15T04:00:00+00:00 Historical-Feature Residual Adaptation for Sequential Screening https://ax-news.com/?article=216086221 AX-NEWS en 2026-10-15T04:00:00+00:00 Why don't Graph Transformers attend to the same token? https://ax-news.com/?article=216086222 AX-NEWS en 2026-10-15T04:00:00+00:00 Counterfactual Gate-Support Decomposition: Separating Selection from Redistribution in Training-Data Filtering https://ax-news.com/?article=216086224 AX-NEWS en 2026-10-15T04:00:00+00:00 Where to Start, How to Move: Analyzing Curricula under GRPO for Long-Horizon LLM Agents https://ax-news.com/?article=216086226 AX-NEWS en 2026-10-15T04:00:00+00:00 Asymptotic Behavior of Transformers https://ax-news.com/?article=216086227 AX-NEWS en 2026-10-15T04:00:00+00:00 Dynamic Graph World Modelling: Learning Future Dynamics from Temporal Context https://ax-news.com/?article=216086229 AX-NEWS en 2026-10-15T04:00:00+00:00 One-Step Prediction Fidelity Is a Poor Proxy for Planning Performance in JEPA World Models https://ax-news.com/?article=216086231 AX-NEWS en 2026-10-15T04:00:00+00:00 RA$^2$: Retain-Anchored Attraction Preserves Forget-Adjacent Utility in LLM Unlearning https://ax-news.com/?article=216086235 AX-NEWS en 2026-10-15T04:00:00+00:00 W-JEPA: Wavelet Joint-Embedding Predictive Architecture for Wearable Activity Recognition https://ax-news.com/?article=216086237 AX-NEWS en 2026-10-15T04:00:00+00:00 Progress-Aware Distillation for Mitigating Stagnation in Small Language Model Agents https://ax-news.com/?article=216086238 AX-NEWS en 2026-10-15T04:00:00+00:00 MIPS: Mitigating Mode Collapse in Reinforcement Learning for Large Outcome Spaces https://ax-news.com/?article=216086242 AX-NEWS en 2026-10-15T04:00:00+00:00 Diagnosing and Correcting Reward Hacking in Verifiable Instruction Following https://ax-news.com/?article=216086243 AX-NEWS en 2026-10-15T04:00:00+00:00 Two-stage Residual Learning for Modelling Strength-Informed Optimisation of Thermal Systems https://ax-news.com/?article=216086250 AX-NEWS en 2026-10-15T04:00:00+00:00 Divergent Paths: Learning an Outcome-Predictive Representation of LLM Agent Trajectories https://ax-news.com/?article=216086251 AX-NEWS en 2026-10-15T04:00:00+00:00 Sparse Autoencoders Are a Shared Coordinate System for Symbolic Matching https://ax-news.com/?article=216086256 AX-NEWS en 2026-10-15T04:00:00+00:00 Function-Space Temporal Self-Distillation for Policy Optimization https://ax-news.com/?article=216086258 AX-NEWS en 2026-10-15T04:00:00+00:00 ReGRA: Residual-Gradient Adaptation for Complementary Low-Rank Fine-Tuning https://ax-news.com/?article=216087841 AX-NEWS en 2026-10-15T04:00:00+00:00 The Value of Spike Timing: A Leakage-Resistant Benchmark of SNN Design Choices for Network Intrusion Detection https://ax-news.com/?article=216086261 AX-NEWS en 2026-10-15T04:00:00+00:00 What Happens to the Goal? Distinct Failures of Policy Alignment in Goal Misgeneralization https://ax-news.com/?article=216086262 AX-NEWS en 2026-10-15T04:00:00+00:00 ProtModernBERT: Compute-Efficient Protein Language Modeling https://ax-news.com/?article=216086264 AX-NEWS en 2026-10-15T04:00:00+00:00 Learning to Compute Is Not Learning to Retain or Reuse in Looped Transformers https://ax-news.com/?article=216086265 AX-NEWS en 2026-10-15T04:00:00+00:00 From Global to Tail Convergence: Dynamics of $\alpha$-Stable Score-Based Generative Models https://ax-news.com/?article=216086266 AX-NEWS en 2026-10-15T04:00:00+00:00 Learning Who Benefits Most: Multi-Treatment Causal Ranking for Population Health Stratification https://ax-news.com/?article=216086269 AX-NEWS en 2026-10-15T04:00:00+00:00 Efficient contextual partial monitoring with general function approximation https://ax-news.com/?article=216086271 AX-NEWS en 2026-10-15T04:00:00+00:00 When Does Depth Help? Understanding Layerwise Inference in Tabular Foundation Models https://ax-news.com/?article=216086273 AX-NEWS en 2026-10-15T04:00:00+00:00 CTIA-ODE: Continuous-Time Inter-Variable Attention for Long-Term Time Series Forecasting https://ax-news.com/?article=216086274 AX-NEWS en 2026-10-15T04:00:00+00:00 Rent-Seeking Language Models: Reward Models Set the Prices, Frequent Audits Curb the Rent https://ax-news.com/?article=216086277 AX-NEWS en 2026-10-15T04:00:00+00:00 SPARS: A Stability-Plasticity-Aware Region Selection Framework for Continual Learning https://ax-news.com/?article=216086278 AX-NEWS en 2026-10-15T04:00:00+00:00 Neural Wasserstein Splines: Representation-Invariant Second-Order Priors for Trajectory Inference https://ax-news.com/?article=216086281 AX-NEWS en 2026-10-15T04:00:00+00:00 Universal Sample-Based Embeddings of Higher-Order Objects https://ax-news.com/?article=216086285 AX-NEWS en 2026-10-15T04:00:00+00:00 MolHop: Scaffold-Hopping Molecular Design with Agentic Reinforcement Learning https://ax-news.com/?article=216086286 AX-NEWS en 2026-10-15T04:00:00+00:00 MorphingNet: Symbolic Regression Where the Network Is the Formula https://ax-news.com/?article=216086287 AX-NEWS en 2026-10-15T04:00:00+00:00 Learning Graph Energies for Finite-Time Generation https://ax-news.com/?article=216086291 AX-NEWS en 2026-10-15T04:00:00+00:00 Provable Transformer Context Compression for In-Context Reinforcement Learning https://ax-news.com/?article=216086292 AX-NEWS en 2026-10-15T04:00:00+00:00 Outperforming 1000 Euclidean Layers With Hyperbolic Goal-Conditioned RL https://ax-news.com/?article=216086298 AX-NEWS en 2026-10-15T04:00:00+00:00 Rethinking Prediction Horizons: Decoupling Model Queries from State Updates in Few-Step MeanFlow https://ax-news.com/?article=216086309 AX-NEWS en 2026-10-15T04:00:00+00:00 Dimension-Optimal Dynamic Regret in Exp-Concave Online Learning https://ax-news.com/?article=216086310 AX-NEWS en 2026-10-15T04:00:00+00:00 HGRP: Heterogeneous Graph Neural Network for Routability Prediction https://ax-news.com/?article=216086311 AX-NEWS en 2026-10-15T04:00:00+00:00 MAEM: Mitigating Recency Bias via a Replay-Free, Capacity-Controlled Dynamic Mixture of Experts for Class-Incremental Graph Learning https://ax-news.com/?article=216086312 AX-NEWS en 2026-10-15T04:00:00+00:00 Retrieval Over Training: Similarity search-based Model Selection for Time Series Anomaly Detection https://ax-news.com/?article=216086320 AX-NEWS en 2026-10-15T04:00:00+00:00 Predicting Unseen Scientific Interactions: Conditional Flow Models Hallucinate Non-Additive Effects https://ax-news.com/?article=216086321 AX-NEWS en 2026-10-15T04:00:00+00:00 SpectrumQuant: Spectrum Alignment for LLM Quantization https://ax-news.com/?article=216086323 AX-NEWS en 2026-10-15T04:00:00+00:00 Are We Overthinking One-Step Generation? https://ax-news.com/?article=216086324 AX-NEWS en 2026-10-15T04:00:00+00:00 Training Dynamics of Transformers on Unbounded Inputs: Attention Learning Can Lag Output Layer Learning https://ax-news.com/?article=216086327 AX-NEWS en 2026-10-15T04:00:00+00:00 NeuroDETR: Multiscale Discrete Spatiotemporal Tokenization for Asynchronous EEG Event Detection https://ax-news.com/?article=216086329 AX-NEWS en 2026-10-15T04:00:00+00:00 Fractional is Better: Learnable Derivative Orders in Neural Operator Learning https://ax-news.com/?article=216086330 AX-NEWS en 2026-10-15T04:00:00+00:00 ReAl: Refine neural operators via aligning dynamical flow https://ax-news.com/?article=216086331 AX-NEWS en 2026-10-15T04:00:00+00:00 From Human Corrections to Learned Segmentations: A Critical Mathematical Review of Information, Learning, and Human Effort https://ax-news.com/?article=216086332 AX-NEWS en 2026-10-15T04:00:00+00:00 Training Language Models to Fail Gracefully https://ax-news.com/?article=216086333 AX-NEWS en 2026-10-15T04:00:00+00:00 Hyperspherical Contrastive Representations Unlock Planning and Exploration https://ax-news.com/?article=216086334 AX-NEWS en 2026-10-15T04:00:00+00:00 When Does Momentum Help in Reinforcement Learning with Verifiable Rewards? https://ax-news.com/?article=216086340 AX-NEWS en 2026-10-15T04:00:00+00:00 Learning by Examples: Power Grid Steady State Analysis with a Tabular Foundation Model https://ax-news.com/?article=216086341 AX-NEWS en 2026-10-15T04:00:00+00:00 Selective Growing Q-Networks (SGQN): An Analysis of Adaptive Action Grids in Decoupled Q-Learning https://ax-news.com/?article=216086347 AX-NEWS en 2026-10-15T04:00:00+00:00 Bayesian Learning to Select Fair Classifiers https://ax-news.com/?article=216086351 AX-NEWS en 2026-10-15T04:00:00+00:00 Detection of Potato Plant Leaf Diseases using Convolutional Neural Networks https://ax-news.com/?article=216086356 AX-NEWS en 2026-10-15T04:00:00+00:00 Your Transformer Is Secretly Elastic https://ax-news.com/?article=216086357 AX-NEWS en 2026-10-15T04:00:00+00:00 Edgewise Envelopes Between Balanced Forman and Ollivier-Ricci Curvature https://ax-news.com/?article=216086359 AX-NEWS en 2026-10-15T04:00:00+00:00 Physics-Guided Multi-Fidelity Surrogate Modeling for Natural Supercavity Geometry of an Axisymmetric Conical Cavitator https://ax-news.com/?article=216086361 AX-NEWS en 2026-10-15T04:00:00+00:00 AI-Driven, Timing-Aware Power Optimization https://ax-news.com/?article=216086364 AX-NEWS en 2026-10-15T04:00:00+00:00 TorchSpin: Differentiable Electron Paramagnetic Resonance Simulation in PyTorch https://ax-news.com/?article=216086365 AX-NEWS en 2026-10-15T04:00:00+00:00 The Agentic Scientist: Orchestrating Coding Agents for Automated Scientific (Co-)Discovery https://ax-news.com/?article=216086370 AX-NEWS en 2026-10-15T04:00:00+00:00 Semi-Amortized Bayesian Inference with Reusable Local Posteriors https://ax-news.com/?article=216086378 AX-NEWS en 2026-10-15T04:00:00+00:00 Smart Alone, Blind Together: Why Accuracy Fails to CertifyTheory of Mind in Multi-Agent Teams https://ax-news.com/?article=216086389 AX-NEWS en 2026-10-15T04:00:00+00:00 Embedding Geometry Shapes LLM Routing: Tracing Failure Modes and Improving Generalization https://ax-news.com/?article=216086392 AX-NEWS en 2026-10-15T04:00:00+00:00 Multi-Sensitive Distributional Fairness: Joint Wasserstein Audits and Shapley Allocation https://ax-news.com/?article=216086393 AX-NEWS en 2026-10-15T04:00:00+00:00 TopicMerge: A Divide and Conquer Approach to Topic Modeling https://ax-news.com/?article=216086394 AX-NEWS en 2026-10-15T04:00:00+00:00 Target-Token Asymmetry Can Masquerade As Depth Specialization https://ax-news.com/?article=216086395 AX-NEWS en 2026-10-15T04:00:00+00:00 Steering Vectors for Competing Ethical Frameworks Are Interchangeable: A Competing-Target Test for Activation Steering https://ax-news.com/?article=216086398 AX-NEWS en 2026-10-15T04:00:00+00:00 ActMOF: Mapping Reticular Synthesis through Active Learning https://ax-news.com/?article=216086402 AX-NEWS en 2026-10-15T04:00:00+00:00 State-Matched Sequence Conformal Prediction https://ax-news.com/?article=216086407 AX-NEWS en 2026-10-15T04:00:00+00:00 Typed Decision Models on Tabular Data https://ax-news.com/?article=216086409 AX-NEWS en 2026-10-15T04:00:00+00:00 Evidence-Anchored Overdose Death Prediction from Death Investigation Reports https://ax-news.com/?article=216086415 AX-NEWS en 2026-10-15T04:00:00+00:00 Projected Wasserstein-Fisher-Rao Flows for Hawkes Background-Intensity Estimation https://ax-news.com/?article=216086416 AX-NEWS en 2026-10-15T04:00:00+00:00 L3M: A Verifiable Harness and Runtime for Self-Extending and Self-Improving Agents https://ax-news.com/?article=216086420 AX-NEWS en 2026-10-15T04:00:00+00:00 Risk-Controlled DFT Selection for Machine-Learned Interatomic Potentials https://ax-news.com/?article=216086421 AX-NEWS en 2026-10-15T04:00:00+00:00 Model What Matters: Decision-Guided Selective World Modeling for Language Agents https://ax-news.com/?article=216086422 AX-NEWS en 2026-10-15T04:00:00+00:00 HACHIMI-II: From Role-Play to Learner Behavior Modeling for Faithful Student Simulation https://ax-news.com/?article=216086424 AX-NEWS en 2026-10-15T04:00:00+00:00 Learning Individual Scientific Taste with Privileged Hindsight Distillation https://ax-news.com/?article=216086430 AX-NEWS en 2026-10-15T04:00:00+00:00 More Methods, Better Agents? A Reality Check on Self-Distillation in Agentic Reinforcement Learning https://ax-news.com/?article=216086431 AX-NEWS en 2026-10-15T04:00:00+00:00 StateCraft: Augmenting Video World Models with Abstract-State Reasoning https://ax-news.com/?article=216086432 AX-NEWS en 2026-10-15T04:00:00+00:00 ReproBAIT: Can coding agents build their own biological AI tools? https://ax-news.com/?article=216086435 AX-NEWS en 2026-10-15T04:00:00+00:00 Text-Informed Training Data Filtering for Enhanced Virtual Flow Meter Performance https://ax-news.com/?article=216086438 AX-NEWS en 2026-10-15T04:00:00+00:00 Few-Shot Adaptation for Anomalous Sound Detection at Low False-Positive Rate https://ax-news.com/?article=216086439 AX-NEWS en 2026-10-15T04:00:00+00:00 Multimodal Medical Image Parsing with Task-Specific Low-Rank Adapters https://ax-news.com/?article=216086443 AX-NEWS en 2026-10-15T04:00:00+00:00 Choosing the Number of Attention Heads from Intrinsic Dimension: A Small-Scale Study https://ax-news.com/?article=216086446 AX-NEWS en 2026-10-15T04:00:00+00:00 Gap Detection: Mitigating Homogenization through Demand and Defensibility https://ax-news.com/?article=216086449 AX-NEWS en 2026-10-15T04:00:00+00:00 Continual pretraining Prostate MRI ViT Encoder for task alignment https://ax-news.com/?article=216086455 AX-NEWS en 2026-10-15T04:00:00+00:00 CASI: Credit Assignment via Set Intervention for Agentic Retrieval https://ax-news.com/?article=216086458 AX-NEWS en 2026-10-15T04:00:00+00:00 Efficient Test-Time Adaptation For Robot Policies https://ax-news.com/?article=216086466 AX-NEWS en 2026-10-15T04:00:00+00:00 The COUNT: Counting N-grams Unlocks Scaling on Host Memory and Training-Free Adaptation https://ax-news.com/?article=216086467 AX-NEWS en 2026-10-15T04:00:00+00:00 SafeAdapt-Poker: Counterfactual Risk Calibration for Budgeted Adaptation under Opponent Shift https://ax-news.com/?article=216086468 AX-NEWS en 2026-10-15T04:00:00+00:00 Lost in Translation: Why Lower Bias Scores Don't Mean Fairer Models https://ax-news.com/?article=216086470 AX-NEWS en 2026-10-15T04:00:00+00:00 VASPO: Self-Distillation with Privileged Value Estimation https://ax-news.com/?article=216086473 AX-NEWS en 2026-10-15T04:00:00+00:00 Latent Compaction with Test-Time Training https://ax-news.com/?article=216086474 AX-NEWS en 2026-10-15T04:00:00+00:00 Price of Anarchy of First-Price Auctions in Agentic Markets https://ax-news.com/?article=216086476 AX-NEWS en 2026-10-15T04:00:00+00:00 Modeling and Understanding Neural Weights of Humanoid Policies with Diffusion https://ax-news.com/?article=216086484 AX-NEWS en 2026-10-15T04:00:00+00:00 Rule-based and reinforcement-learning policies for resource allocation in a pediatric echo lab: a simulation study https://ax-news.com/?article=216086485 AX-NEWS en 2026-10-15T04:00:00+00:00 The Invisible Leash: Why RLVR May or May Not Escape Its Origin https://ax-news.com/?article=216086491 AX-NEWS en 2026-10-15T04:00:00+00:00 The Instability of Safety: How Random Seeds and Temperature Expose Inconsistent LLM Refusal Behavior https://ax-news.com/?article=216086492 AX-NEWS en 2026-10-15T04:00:00+00:00 Long-Range Distillation: Distilling 10,000 Years of Simulated Climate into Long Timestep AI Weather Models https://ax-news.com/?article=216086494 AX-NEWS en 2026-10-15T04:00:00+00:00 Interpolation of GEDI Biomass Estimates with Calibrated Uncertainty Quantification https://ax-news.com/?article=216086496 AX-NEWS en 2026-10-15T04:00:00+00:00 Deep Time-series Forecasting Needs Kernelized Moment Balancing https://ax-news.com/?article=216086501 AX-NEWS en 2026-10-15T04:00:00+00:00 Parameter-Efficient Temporal Domain Generalization https://ax-news.com/?article=216086502 AX-NEWS en 2026-10-15T04:00:00+00:00 Task-Driven Subspace Decomposition for Knowledge Sharing and Isolation in LoRA-based Continual Learning https://ax-news.com/?article=216086503 AX-NEWS en 2026-10-15T04:00:00+00:00 MARS: Harmonizing Multimodal Convergence via Adaptive Rank Search https://ax-news.com/?article=216086504 AX-NEWS en 2026-10-15T04:00:00+00:00 NePPO: Near-Potential Policy Optimization for General-Sum Multi-Agent Reinforcement Learning https://ax-news.com/?article=216086507 AX-NEWS en 2026-10-15T04:00:00+00:00 Structural Pass Analysis in Football: Learning Pass Archetypes and Tactical Impact from Spatio-Temporal Tracking Data https://ax-news.com/?article=216086509 AX-NEWS en 2026-10-15T04:00:00+00:00 Medical Imaging Classification with Cold-Atom Reservoir Computing using Auto-Encoders and Surrogate-Driven Training https://ax-news.com/?article=216086510 AX-NEWS en 2026-10-15T04:00:00+00:00 From Causal Graphs to Markovian States: Multi-Order State Exposure for Deep RL https://ax-news.com/?article=216086511 AX-NEWS en 2026-10-15T04:00:00+00:00 Generative Actor-Critic with Soft Bridge Policies https://ax-news.com/?article=216086512 AX-NEWS en 2026-10-15T04:00:00+00:00 TabFORGE: A Tabular Foundation Model for Generative Modelling https://ax-news.com/?article=216086513 AX-NEWS en 2026-10-15T04:00:00+00:00 TIDES: Implicit Time-Awareness in Selective State Space Models https://ax-news.com/?article=216086520 AX-NEWS en 2026-10-15T04:00:00+00:00 BrainDyn: A Sheaf Neural ODE for Forecasting and Generating Brain Dynamics https://ax-news.com/?article=216086527 AX-NEWS en 2026-10-15T04:00:00+00:00 AgentWorld: A Data Factory for Training LLM Agents from Multi-Turn Interactions https://ax-news.com/?article=216086529 AX-NEWS en 2026-10-15T04:00:00+00:00 Geological text descriptions in ill-posed inverse problems: insights from learned hydraulic-conductivity inversion https://ax-news.com/?article=216086530 AX-NEWS en 2026-10-15T04:00:00+00:00 Blackknife: Query-Free Black-Box Rewiring Attacks on Heterogeneous Graph Neural Networks https://ax-news.com/?article=216086531 AX-NEWS en 2026-10-15T04:00:00+00:00 Platonic Projection Structures: Operator-Induced Observability in Representation Learning https://ax-news.com/?article=216086532 AX-NEWS en 2026-10-15T04:00:00+00:00 What Does a Discrete Diffusion Model Learn? One Reverse Process in Three Coordinates https://ax-news.com/?article=216086534 AX-NEWS en 2026-10-15T04:00:00+00:00 Correlation-Aware Contextual Bandits with Surrogate Rewards for LLM Routing https://ax-news.com/?article=216086544 AX-NEWS en 2026-10-15T04:00:00+00:00 Wrong Operator or Blind Design? A Post-Training Diagnostic for Physics-Informed Coefficient Learning https://ax-news.com/?article=216086546 AX-NEWS en 2026-10-15T04:00:00+00:00 Mechanistic Circuit Identification for Controllable Data Generation https://ax-news.com/?article=216086548 AX-NEWS en 2026-10-15T04:00:00+00:00 When Genomic Masking Priors Fail to Transfer: Strong Variant Prediction, Weak Functional Generation https://ax-news.com/?article=216086550 AX-NEWS en 2026-10-15T04:00:00+00:00 Structured Multi-Level-Set Inversion for 3-D Electromagnetic Inverse Scattering https://ax-news.com/?article=216086551 AX-NEWS en 2026-10-15T04:00:00+00:00 Relatively Smart II: Tractable or Semi-Supervised Instance-Optimal Learning https://ax-news.com/?article=216086554 AX-NEWS en 2026-10-15T04:00:00+00:00 hyperbolix: Hyperbolic Deep Learning in JAX https://ax-news.com/?article=216086556 AX-NEWS en 2026-10-15T04:00:00+00:00 A Computational Framework for Modelling Organisation-Level Semantic Identity from Longitudinal Textual Data https://ax-news.com/?article=216086557 AX-NEWS en 2026-10-15T04:00:00+00:00 Learning Provable Neural Network Observer for Uncertain Dynamical Systems https://ax-news.com/?article=216086558 AX-NEWS en 2026-10-15T04:00:00+00:00 DiffPTS: Rethinking Diffusion ELBO for Probabilistic Time Series Forecasting https://ax-news.com/?article=216086559 AX-NEWS en 2026-10-15T04:00:00+00:00 TimeES: Probabilistic and Deterministic Time Series Forecasting via Evolutionary Spectra https://ax-news.com/?article=216086560 AX-NEWS en 2026-10-15T04:00:00+00:00 Deep kernel hedging https://ax-news.com/?article=216086561 AX-NEWS en 2026-10-15T04:00:00+00:00 NeuronDiscover: Agent-in-Twin for Mechanistic Discovery in Neuronal Microenvironments with World Action Models https://ax-news.com/?article=216086562 AX-NEWS en 2026-10-15T04:00:00+00:00 NeuronSifter: An Agent-in-Twin for Prioritizing Central Nervous System Interventions with World Action Models https://ax-news.com/?article=216086563 AX-NEWS en 2026-10-15T04:00:00+00:00 The Teacher Is a Direction, Not a Destination: Extrapolating RL-Induced Representation Residuals in On-Policy Distillation https://ax-news.com/?article=216086564 AX-NEWS en 2026-10-15T04:00:00+00:00 Efficient Memory Crystallization for Graph Learning under Non-Stationary Distribution Shifts https://ax-news.com/?article=216086565 AX-NEWS en 2026-10-15T04:00:00+00:00 The Neuro-Physical Inverter: A Modular Framework for Magnetotelluric Inversion Coupling Ensemble Conditioning with Residual Learning https://ax-news.com/?article=216086568 AX-NEWS en 2026-10-15T04:00:00+00:00 Lost in the bf16 Cast: Exporting Ternary Language Models Can Revert Most Low-Learning-Rate Code Changes https://ax-news.com/?article=216086569 AX-NEWS en 2026-10-15T04:00:00+00:00 Do LLMs Learn from Rewards in Context? : Rethinking the role of reward in In-Context RL https://ax-news.com/?article=216086574 AX-NEWS en 2026-10-15T04:00:00+00:00 Who Sets the Pace of Judge Hacking? Judge Capability versus the Policy-Judge Gap https://ax-news.com/?article=216086575 AX-NEWS en 2026-10-15T04:00:00+00:00 Towards Modality-Agnostic Seizure Classification: A Unified Deep Learning Framework for Heterogeneous EEG and Intracranial EEG Signals https://ax-news.com/?article=216086582 AX-NEWS en 2026-10-15T04:00:00+00:00 Interaction-as-a-Judge https://ax-news.com/?article=216086590 AX-NEWS en 2026-10-15T04:00:00+00:00 Score-Based Training for Energy-Based TTS Models https://ax-news.com/?article=216086593 AX-NEWS en 2026-10-15T04:00:00+00:00 Anticipatory Evaluation of Language Models: Predicting LLM Benchmark Scores from Descriptions https://ax-news.com/?article=216086877 AX-NEWS en 2026-10-15T04:00:00+00:00 Observe, Share, or Predict? Disentangling Partner Information in Embodied Multi-Agent Collaboration https://ax-news.com/?article=216086594 AX-NEWS en 2026-10-15T04:00:00+00:00 Don't Run with Scissors: Pruning Breaks VLA Models but They Can Be Recovered https://ax-news.com/?article=216086597 AX-NEWS en 2026-10-15T04:00:00+00:00 Tracking large chemical reaction networks and rare events by neural networks https://ax-news.com/?article=216086598 AX-NEWS en 2026-10-15T04:00:00+00:00 Imaging-anchored Multiomics in Cardiovascular Disease: Integrating Cardiac Imaging, Bulk, Single-cell, and Spatial Transcriptomics https://ax-news.com/?article=216086605 AX-NEWS en 2026-10-15T04:00:00+00:00 StaRPO: Stability-Augmented Reinforcement Policy Optimization https://ax-news.com/?article=216086607 AX-NEWS en 2026-10-15T04:00:00+00:00 Ideological Bias in LLMs' Economic Causal Reasoning https://ax-news.com/?article=216086608 AX-NEWS en 2026-10-15T04:00:00+00:00 Dictionary learning for Kernel EDMD https://ax-news.com/?article=216086609 AX-NEWS en 2026-10-15T04:00:00+00:00 Topology-Aware Representation Alignment for Semi-Supervised Vision-Language Learning https://ax-news.com/?article=216086882 AX-NEWS en 2026-10-15T04:00:00+00:00 MADDIE: Multi-Agent Drug Discovery Engine https://ax-news.com/?article=216086612 AX-NEWS en 2026-10-15T04:00:00+00:00 Symmetry-Compatible Principle for Optimizer Design: Embeddings, LM Heads, SwiGLU MLPs, and MoE Routers https://ax-news.com/?article=216086614 AX-NEWS en 2026-10-15T04:00:00+00:00 MOCHA: Multi-Objective Chebyshev Annealing for Agent Skill Optimization https://ax-news.com/?article=216086616 AX-NEWS en 2026-10-15T04:00:00+00:00 Memory by Design: Bayesian Layers for Sequence Modeling https://ax-news.com/?article=216086617 AX-NEWS en 2026-10-15T04:00:00+00:00 STREAM: Stochastic Riemannian Flow Matching with Anisotropic Decoder for Digital Histopathology Image Generation https://ax-news.com/?article=216086624 AX-NEWS en 2026-10-15T04:00:00+00:00 LIME: Learning Intent-aware Camera Motion from Egocentric Video https://ax-news.com/?article=216086626 AX-NEWS en 2026-10-15T04:00:00+00:00 Adapting Generalist Vehicle Models for High-Speed MPC Across Terrains https://ax-news.com/?article=216086627 AX-NEWS en 2026-10-15T04:00:00+00:00 Hopformer: Homogeneity-Pursuit Transformer for Time Series Forecasting https://ax-news.com/?article=216086629 AX-NEWS en 2026-10-15T04:00:00+00:00 QASP: Query-Adaptive Robust Vector Search Policy https://ax-news.com/?article=216086633 AX-NEWS en 2026-10-15T04:00:00+00:00 LLMs Can Design Near-Optimal OR Algorithms https://ax-news.com/?article=216086635 AX-NEWS en 2026-10-15T04:00:00+00:00 PrismQuant: Optimal Null-Space Rotations for Grouped Quantizers https://ax-news.com/?article=216086645 AX-NEWS en 2026-10-15T04:00:00+00:00 Sharp Asymptotic Theory of Maximum Likelihood Estimation for Gaussian Processes with an RBF Kernel https://ax-news.com/?article=216086649 AX-NEWS en 2026-10-15T04:00:00+00:00 MvFFN: Multi-view Floor plan Feed-forward Network for Unposed Wide-Baseline Panorama Layout Reconstruction https://ax-news.com/?article=216086651 AX-NEWS en 2026-10-15T04:00:00+00:00 Strong Gaussian Approximation of Constant Learning Rate SGD: Bias and Trajectory Inference https://ax-news.com/?article=216086652 AX-NEWS en 2026-10-15T04:00:00+00:00 AlphaRLM: Aligning Language Models for Literature-Grounded Symbolic Factor Discovery https://ax-news.com/?article=216086654 AX-NEWS en 2026-10-15T04:00:00+00:00 ProtoPur: Prototype-Purity Pseudo-Labeling for Weakly Supervised Instance Learning in Pathology https://ax-news.com/?article=216086655 AX-NEWS en 2026-10-15T04:00:00+00:00 Privacy-Preserving GNN Inference on Financial Transaction Graphs via Homomorphic Encryption https://ax-news.com/?article=216086657 AX-NEWS en 2026-10-15T04:00:00+00:00 Principled Design of Expected Improvement for Continuous Simulation Optimization https://ax-news.com/?article=216086659 AX-NEWS en 2026-10-15T04:00:00+00:00 Artificiality's First Exam: An LLM-Referenced C-test for Supraintelligence https://ax-news.com/?article=216086663 AX-NEWS en 2026-10-15T04:00:00+00:00 Long-Horizon-Terminal-Bench 2.0: Automating Diverse Task Construction and Measuring Sustained Agent Progress https://ax-news.com/?article=216086665 AX-NEWS en 2026-10-15T04:00:00+00:00 Unconstrained CTI-REALM with Open-Weights https://ax-news.com/?article=216086667 AX-NEWS en 2026-10-15T04:00:00+00:00 Cross-Modal Latent Influence: Patch-Level Training Sample Attribution for Vision-Language Models https://ax-news.com/?article=216086669 AX-NEWS en 2026-10-15T04:00:00+00:00 Harness^2: Recursive Agent Harnessing for an Open World https://ax-news.com/?article=216086670 AX-NEWS en 2026-10-15T04:00:00+00:00 Echo: Error-Compensated 4-Bit Tensor-Parallel Communication for LLM Training and Inference https://ax-news.com/?article=216086672 AX-NEWS en 2026-10-15T04:00:00+00:00 ConicFlow: constrained Inference-time optimal control for flow matching models https://ax-news.com/?article=216086675 AX-NEWS en 2026-10-15T04:00:00+00:00 When Pleasing the User Compromises Care: AI Sycophancy in Caregiver-Mediated Healthcare https://ax-news.com/?article=216086677 AX-NEWS en 2026-10-15T04:00:00+00:00 ANASSA: From High-Level Framework to Low-Level Architecture for Spatial Agentic AI https://ax-news.com/?article=216086679 AX-NEWS en 2026-10-15T04:00:00+00:00 SAT-RL: Training Language Models for Logical Reasoning with Symbolic Solvers https://ax-news.com/?article=216086688 AX-NEWS en 2026-10-15T04:00:00+00:00 Are Multimodal Benchmarks Really Useful? Item-Level Multimodal Benchmark Diagnosis via Structure-Response Co-Calibration https://ax-news.com/?article=216086695 AX-NEWS en 2026-10-15T04:00:00+00:00 PEARL: Process-Experience Aware Reinforcement Learning for Multi-Turn Agents https://ax-news.com/?article=216086696 AX-NEWS en 2026-10-15T04:00:00+00:00 AegisVox: Factorized Privacy and Clinical Preservation for Long-Form Speech https://ax-news.com/?article=216086697 AX-NEWS en 2026-10-15T04:00:00+00:00 Shaping Latent Mixture-of-Experts: From Expert Geometry to Layerwise Capacity Allocation https://ax-news.com/?article=216086698 AX-NEWS en 2026-10-15T04:00:00+00:00 RASSG: Repair-Aware Semantic Survival Gating for Streaming Tool Execution https://ax-news.com/?article=216086707 AX-NEWS en 2026-10-15T04:00:00+00:00 SAGE: Pushing 2-Bit Vector-Quantized LLMs toward Real-World Usability https://ax-news.com/?article=216086709 AX-NEWS en 2026-10-15T04:00:00+00:00 GateSight: Recurrent Memory Anticipates Attention Memory for Query-Agnostic KV Eviction in Hybrid LLMs https://ax-news.com/?article=216086712 AX-NEWS en 2026-10-15T04:00:00+00:00 ProgAgent: Learning Tool Orchestration through Programmatic Training https://ax-news.com/?article=216086715 AX-NEWS en 2026-10-15T04:00:00+00:00 GREAT-ESDD: Graph Edge Attention Network for Effectively Steered Delivery Decisions https://ax-news.com/?article=216086716 AX-NEWS en 2026-10-15T04:00:00+00:00 CESNET-TimeSeries26: A Multi-Year Network Traffic Time Series Dataset for Annual Seasonality, Concept Drift, and Long-Term Anomaly Detection https://ax-news.com/?article=216086717 AX-NEWS en 2026-10-15T04:00:00+00:00 ASIWorld: Benchmarking Autonomous Agents in a Persistent Survival Sandbox https://ax-news.com/?article=216086722 AX-NEWS en 2026-10-15T04:00:00+00:00 WeatherBridge: Forecast-Aware Multi-Source Input Adaptation for Pretrained Weather Forecasting Models https://ax-news.com/?article=216086725 AX-NEWS en 2026-10-15T04:00:00+00:00 Probable but Not Valid: A Psychometric Audit of Decision Models as Synthetic Survey Respondents https://ax-news.com/?article=216086726 AX-NEWS en 2026-10-15T04:00:00+00:00 Bridging Risk Approximation Gaps in Model Predictive Task Sampling via In-Context Modeling https://ax-news.com/?article=216086727 AX-NEWS en 2026-10-15T04:00:00+00:00 WorkBorne: Discovering Agentic Tasks from Real-World Artifact Transitions https://ax-news.com/?article=216086728 AX-NEWS en 2026-10-15T04:00:00+00:00 SkillForgeBench: Evaluating Agent Reliability Grounded in Agent Skill Specifications https://ax-news.com/?article=216086730 AX-NEWS en 2026-10-15T04:00:00+00:00 VC-OPD: Visual Counterfactual On-Policy Distillation for Grounded Vision-Language Reasoning https://ax-news.com/?article=216086734 AX-NEWS en 2026-10-15T04:00:00+00:00 SkillHorizon: Constructing Long-Horizon Agent Tasks through Skill Composition https://ax-news.com/?article=216086736 AX-NEWS en 2026-10-15T04:00:00+00:00 Single-Sample Decoding of a Two-Layer Sound-Word Canvas Model for Thai Klon Pad https://ax-news.com/?article=216086738 AX-NEWS en 2026-10-15T04:00:00+00:00 Can You Trust Your Preference Models? Stackelberg Games for Alignment https://ax-news.com/?article=216086740 AX-NEWS en 2026-10-15T04:00:00+00:00 Belief Embedding Tree Search https://ax-news.com/?article=216086741 AX-NEWS en 2026-10-15T04:00:00+00:00 Trace Evolution Bench: Measuring Whether Agents Improve from Their Own Environment Traces https://ax-news.com/?article=216086744 AX-NEWS en 2026-10-15T04:00:00+00:00 Self-Evolving Visual Agent via Margin Reward https://ax-news.com/?article=216086746 AX-NEWS en 2026-10-15T04:00:00+00:00 GesBench: When and Where Do Multimodal Language Models Perceive Social Meaning? https://ax-news.com/?article=216086750 AX-NEWS en 2026-10-15T04:00:00+00:00 Can agents whose sole duty is to keep humans alive be hijacked to kill? Delayed multi-turn derived-action trap attacks in simulated high-stakes environments https://ax-news.com/?article=216086753 AX-NEWS en 2026-10-15T04:00:00+00:00 Running Fewer Loops Removes Refusal Behaviour in Recurrent-Depth Language Models https://ax-news.com/?article=216086754 AX-NEWS en 2026-10-15T04:00:00+00:00 HarnessNet: Feedback-driven Hierarchical Joint Harness Evolution for Multi-agent Systems https://ax-news.com/?article=216086756 AX-NEWS en 2026-10-15T04:00:00+00:00 Words to World: Benchmarking LLMs in Interactive Physical Environments https://ax-news.com/?article=216086757 AX-NEWS en 2026-10-15T04:00:00+00:00 Using Evidence-Centered Design to Guide Prompt Engineering in Measurement: An Illustration with Automated Essay Scoring https://ax-news.com/?article=216086758 AX-NEWS en 2026-10-15T04:00:00+00:00 MoMaTune: Model, Match, Then Tune Language Models for Numerical Records https://ax-news.com/?article=216086760 AX-NEWS en 2026-10-15T04:00:00+00:00 RECAP: Calibrating Low-Bit Reasoning Models on the History They Read https://ax-news.com/?article=216086761 AX-NEWS en 2026-10-15T04:00:00+00:00 OntoAR-HAR: Ontology-Guided Agentic RAG with Personalized Memory for Human Activity Recognition https://ax-news.com/?article=216086764 AX-NEWS en 2026-10-15T04:00:00+00:00 MultiFlow: Vision-Driven Multimodal fMRI Encoding via Stimulus-Informed Source Flow Matching https://ax-news.com/?article=216086769 AX-NEWS en 2026-10-15T04:00:00+00:00 State Representation Shapes Long-Horizon Agent Learning and Transfer: An Empirical Study https://ax-news.com/?article=216086772 AX-NEWS en 2026-10-15T04:00:00+00:00 Hidden in Plain Sight: Advancing Harmful Content Understanding via Perception-Aware Adversarial Self-Play https://ax-news.com/?article=216086775 AX-NEWS en 2026-10-15T04:00:00+00:00 SkillFusion: Towards Reliable Multi-Skill Composition for LLM Agents https://ax-news.com/?article=216086781 AX-NEWS en 2026-10-15T04:00:00+00:00 Inverse Garment Design with Visual Agents https://ax-news.com/?article=216086785 AX-NEWS en 2026-10-15T04:00:00+00:00 Recall What Is Missing: Composing Evidence from Long-Term Agent Memory https://ax-news.com/?article=216086788 AX-NEWS en 2026-10-15T04:00:00+00:00 FARL: A Fully Automated Pipeline of RL Interface and Solver Design https://ax-news.com/?article=216086790 AX-NEWS en 2026-10-15T04:00:00+00:00 Suggested Is Not Superseded: A Pre-Registered Evaluation of a System-One Model as a Memory-Retirement Gate https://ax-news.com/?article=216086792 AX-NEWS en 2026-10-15T04:00:00+00:00 History Replays Itself: Unleashing Long-Context Capability in Linear Attention https://ax-news.com/?article=216086793 AX-NEWS en 2026-10-15T04:00:00+00:00 Visible but Not Avoided: State-Dependent Re-Proposal of Rejected Candidates in Catalog-Based LLM Optimization Loops https://ax-news.com/?article=216086794 AX-NEWS en 2026-10-15T04:00:00+00:00 Google Earth AI Geospatial Reasoning Agent: Capabilities and a Systematic Evaluation https://ax-news.com/?article=216086795 AX-NEWS en 2026-10-15T04:00:00+00:00 Agent Sociodrama: Social-Dynamics-Guided Persona Recasting for LLM Agent Teams https://ax-news.com/?article=216086796 AX-NEWS en 2026-10-15T04:00:00+00:00 Passing Tests, Missing Semantics: Evidence of Interpretive Lock-In in Plan-Based DataFrame Code Generation https://ax-news.com/?article=216086797 AX-NEWS en 2026-10-15T04:00:00+00:00 Attention Sinks in VLMs Are Borrowed, Not Seen https://ax-news.com/?article=216086798 AX-NEWS en 2026-10-15T04:00:00+00:00 Engram Injection: A Study of Temporal Validity in Parametric Language-Model Memory https://ax-news.com/?article=216086803 AX-NEWS en 2026-10-15T04:00:00+00:00 The Anatomy of a Blind Spot: What an LLM Judge Must Be Shown, and How Much https://ax-news.com/?article=216086804 AX-NEWS en 2026-10-15T04:00:00+00:00 Vision: "What Don't I Know About User's Preferences?" How Uncertainty Estimation Improves Proactive Assistant Alignment https://ax-news.com/?article=216086805 AX-NEWS en 2026-10-15T04:00:00+00:00 ADAPT: Audio-Depth Action Planning with Transition-Aware Rewards for Lights-Out Industrial Navigation https://ax-news.com/?article=216086806 AX-NEWS en 2026-10-15T04:00:00+00:00 Small but Mighty: Test Suites as Improvement Signals for Self-Evolving Agents https://ax-news.com/?article=216086807 AX-NEWS en 2026-10-15T04:00:00+00:00 PopGen: Generating Semantically Diverse Populations for Zero-Shot Coordination https://ax-news.com/?article=216086809 AX-NEWS en 2026-10-15T04:00:00+00:00 Handoff Curves: Initial Selection, Later Handoff, and Supervision Targets in Multi-turn LLM Routing https://ax-news.com/?article=216086810 AX-NEWS en 2026-10-15T04:00:00+00:00 Large language model-generated patterns for epidemiological modeling: a multi-benchmark evaluation framework https://ax-news.com/?article=216086813 AX-NEWS en 2026-10-15T04:00:00+00:00 Understanding and Reducing Misalignment in Persuasion Optimization https://ax-news.com/?article=216086814 AX-NEWS en 2026-10-15T04:00:00+00:00 Beyond Single-Pathogen Forecasts: Predicting Shared Respiratory Hospital Burden from Influenza, COVID-19, and RSV https://ax-news.com/?article=216086815 AX-NEWS en 2026-10-15T04:00:00+00:00 Heterogeneous Agentic Coevolution https://ax-news.com/?article=216086816 AX-NEWS en 2026-10-15T04:00:00+00:00 The Sharp Directions Are Against You: Curvature Analysis of Activation Steering https://ax-news.com/?article=216086828 AX-NEWS en 2026-10-15T04:00:00+00:00 Correct Choices, Failed Sequences: Choice2Seq Benchmarks Correctness Retention Across Output Interfaces https://ax-news.com/?article=216086834 AX-NEWS en 2026-10-15T04:00:00+00:00 REVEAL: Reverse Engineering Agentic Latents from Frontier-Model Traces https://ax-news.com/?article=216086835 AX-NEWS en 2026-10-15T04:00:00+00:00 Memory-Efficient Integer-Only Training of Deep Neural Networks https://ax-news.com/?article=216086837 AX-NEWS en 2026-10-15T04:00:00+00:00 Narrative Paradoxes in LLM Inference: Shaping Reasoning Trajectories toward Misalignment https://ax-news.com/?article=216086838 AX-NEWS en 2026-10-15T04:00:00+00:00 ReTAC: Residual Test-Time Agentic Computation for Video Spatial Reasoning https://ax-news.com/?article=216086839 AX-NEWS en 2026-10-15T04:00:00+00:00 HyWe: Unifying Search and Operation for Real-World Hybrid Web Tasks https://ax-news.com/?article=216086841 AX-NEWS en 2026-10-15T04:00:00+00:00 TRAP: Tool-result Replay Attack for Probing Misbinding in LLM Agents https://ax-news.com/?article=216086844 AX-NEWS en 2026-10-15T04:00:00+00:00 World Models Need a Physical Registry: Learning Internal Predictive States for Physically Plausible World Models https://ax-news.com/?article=216086848 AX-NEWS en 2026-10-15T04:00:00+00:00 SLS-Bench: A Benchmark for Incident Log Summarization with Synthetic Observability Data https://ax-news.com/?article=216086850 AX-NEWS en 2026-10-15T04:00:00+00:00 AuthGateBench: Benchmarking LLMs as Authorization Gate https://ax-news.com/?article=216086851 AX-NEWS en 2026-10-15T04:00:00+00:00 RAP-WAM: Learning World-Action Models through Predictive Rehearsal and Action Perturbations https://ax-news.com/?article=216086855 AX-NEWS en 2026-10-15T04:00:00+00:00 EAU: Environment-Agent-User Co-evolution for Training User-Centric Agents https://ax-news.com/?article=216086857 AX-NEWS en 2026-10-15T04:00:00+00:00 Overtaught, Underlearned: Learner-Centered Distillation from Multi-Agent Discussion https://ax-news.com/?article=216086196 AX-NEWS en 2026-10-15T04:00:00+00:00 Unlocking Structured Pruning for Reasoning Language Models via Attention-Preserving MLP Trimming https://ax-news.com/?article=216086862 AX-NEWS en 2026-10-15T04:00:00+00:00 When 1+1 Backfires: Rethinking Relevance-Diversity Balancing for Sample-Aware Visual Token Reduction https://ax-news.com/?article=216086864 AX-NEWS en 2026-10-15T04:00:00+00:00 LATCH: LLM-Assisted Timing Closure Harness for Post-Route FPGA Optimisation https://ax-news.com/?article=216086865 AX-NEWS en 2026-10-15T04:00:00+00:00 Does a Hosted Decision Model Respect Irrelevant Alternatives? A Pre-Registered Test of Option-Set Dependence in Jev https://ax-news.com/?article=216086866 AX-NEWS en 2026-10-15T04:00:00+00:00 Structural Baselines Matter for Agent Failure Detection and Attribution https://ax-news.com/?article=216086867 AX-NEWS en 2026-10-15T04:00:00+00:00 Trace-to-Architecture: Capability Bottleneck Diagnosis for Harness Revision https://ax-news.com/?article=216086868 AX-NEWS en 2026-10-15T04:00:00+00:00 Queue-Aware Token Communications: Bridging AI Representation and Wireless Service https://ax-news.com/?article=216086869 AX-NEWS en 2026-10-15T04:00:00+00:00 Separating Prompt Harmfulness from Interaction Safety via Partial Generation https://ax-news.com/?article=216086871 AX-NEWS en 2026-10-15T04:00:00+00:00 Game-Creation-Agents: Autonomous Game Production https://ax-news.com/?article=216086873 AX-NEWS en 2026-10-15T04:00:00+00:00 Same Operation, Different Permission: Evaluating Whether Guardrails Honor Authorization https://ax-news.com/?article=216086875 AX-NEWS en 2026-10-15T04:00:00+00:00 Acceptable Misalignment https://ax-news.com/?article=216086878 AX-NEWS en 2026-10-15T04:00:00+00:00 Neural Bayesian Networks for Modular and Scalable Decision-Making Under Uncertainty https://ax-news.com/?article=216086879 AX-NEWS en 2026-10-15T04:00:00+00:00 Audit tools of the trade: Automated Auditor Elicitation Can Be Sensitive to the Context the Auditor Is Given https://ax-news.com/?article=216086880 AX-NEWS en 2026-10-15T04:00:00+00:00 Transparent Information Flow Modeling for Role-Aware AI Act Assessment https://ax-news.com/?article=216086881 AX-NEWS en 2026-10-15T04:00:00+00:00 WeFair: Fidelity-Aware Alignment from Human Feedback for Personalized Query Rewriting in Short-Video Search https://ax-news.com/?article=216086883 AX-NEWS en 2026-10-15T04:00:00+00:00 PRAISE: A Reproducible Workflow for Non-Programmer Scientists to Implement Published AI Models https://ax-news.com/?article=216086886 AX-NEWS en 2026-10-15T04:00:00+00:00 Benchmarking Quantum Kernel SVMs for Credit Card Fraud Detection: Performance Realities Under NISQ Constraints https://ax-news.com/?article=216086893 AX-NEWS en 2026-10-15T04:00:00+00:00 The Format is the Filter: Scoring Format Fixes What an LLM Judge Can Express https://ax-news.com/?article=216086898 AX-NEWS en 2026-10-15T04:00:00+00:00 AutoMARS: Automatic and Scalable Multi-Agent Large Language Model Framework for Supply Chain Risk Assessment https://ax-news.com/?article=216086904 AX-NEWS en 2026-10-15T04:00:00+00:00 Towards Resilience: Slice-Driven Orchestration of Mobile IoMT in 6G-Edge-Continuum https://ax-news.com/?article=216086905 AX-NEWS en 2026-10-15T04:00:00+00:00 The Agent Knew: Internal States Forecast Unauthorized Actions and Stop Them, and the Lies That Follow https://ax-news.com/?article=216086906 AX-NEWS en 2026-10-15T04:00:00+00:00 Reliable Text-to-SQL in Resource-Constrained Settings with Small LLMs via Iterative Retry Workflows https://ax-news.com/?article=216086907 AX-NEWS en 2026-10-15T04:00:00+00:00 Beyond Successful Play: Diagnosing Opponent Modeling in Large Language Models https://ax-news.com/?article=216086908 AX-NEWS en 2026-10-15T04:00:00+00:00 Do Theorem Provers Need Theorem-Proving Agents? mini-Lean-agent: A Coding-Agent Baseline for Lean https://ax-news.com/?article=216086910 AX-NEWS en 2026-10-15T04:00:00+00:00 When Goals Leak Across Relationships: How Cached Goal Representations Shape Cross-Client Decisions https://ax-news.com/?article=216086912 AX-NEWS en 2026-10-15T04:00:00+00:00 Get In, Decide, Prove: A Merchant-Side Readiness Benchmark for Agentic Commerce https://ax-news.com/?article=216086913 AX-NEWS en 2026-10-15T04:00:00+00:00 EPOCH: Coverage-Aware Evolution with Experiential Preference Optimization for LLM-based Automated Heuristic Design https://ax-news.com/?article=216086914 AX-NEWS en 2026-10-15T04:00:00+00:00 Learning to Play: Reinforcement Learning and Games https://ax-news.com/?article=216086915 AX-NEWS en 2026-10-15T04:00:00+00:00 Generalizable field of view extension for diffusion MRI via conditional flow matching https://ax-news.com/?article=216086916 AX-NEWS en 2026-10-15T04:00:00+00:00 Agency as a New Organizing Abstraction for Computer Science https://ax-news.com/?article=216086917 AX-NEWS en 2026-10-15T04:00:00+00:00 SchemaWeaver: Accelerating On-Device Mobile Agentic AI via Schema-Guided Parallel LLM Decoding https://ax-news.com/?article=216086919 AX-NEWS en 2026-10-15T04:00:00+00:00 An FPGA-Based Spiking Neural Network for Spatiotemporal Pattern Learning and Classification https://ax-news.com/?article=216086920 AX-NEWS en 2026-10-15T04:00:00+00:00 REA: From Correct LLM Judgments to Safe Decision Delivery https://ax-news.com/?article=216086921 AX-NEWS en 2026-10-15T04:00:00+00:00 TacitVLA: Reasoning Vision-Language-Action Models Without Reasoning Latency https://ax-news.com/?article=216086923 AX-NEWS en 2026-10-15T04:00:00+00:00 RAN-JEPA: An Action-Conditioned World Model for Energy-efficient Mobile Network Control https://ax-news.com/?article=216086927 AX-NEWS en 2026-10-15T04:00:00+00:00 Executable Prefix Values for Locating Agent Failures https://ax-news.com/?article=216086930 AX-NEWS en 2026-10-15T04:00:00+00:00 Can Agents Truly Forget? Explore Machine Unlearning for LLM Agents https://ax-news.com/?article=216086931 AX-NEWS en 2026-10-15T04:00:00+00:00 RoTA-Bench: Evaluating 3D Spatial Reasoning through Interactive Projection Alignment https://ax-news.com/?article=216086934 AX-NEWS en 2026-10-15T04:00:00+00:00 Stable Token-level Scheduling for Serverless LLM Inference https://ax-news.com/?article=216086935 AX-NEWS en 2026-10-15T04:00:00+00:00 MedEvo: Medical Reasoning Evolution through Knowledge Navigation https://ax-news.com/?article=216086939 AX-NEWS en 2026-10-15T04:00:00+00:00 ECG-RSI: Recursive Self-Improvement through Targeted Electrocardiogram Waveform Evolution https://ax-news.com/?article=216086940 AX-NEWS en 2026-10-15T04:00:00+00:00 Keep Your Receipts: Trustworthy Cleanup of Agent-Built Knowledge Graphs https://ax-news.com/?article=216086941 AX-NEWS en 2026-10-15T04:00:00+00:00 Upstream Influence, Downstream Re-Anchoring in LLM Agent Chains https://ax-news.com/?article=216086942 AX-NEWS en 2026-10-15T04:00:00+00:00 Evidence-First Agentic Verification https://ax-news.com/?article=216086948 AX-NEWS en 2026-10-15T04:00:00+00:00 Memory Echo in Single-Agent Long-Term Memory: Lifecycle Evaluation and Provenance-Guided Mitigation https://ax-news.com/?article=216086949 AX-NEWS en 2026-10-15T04:00:00+00:00 Agentic4PDM: Host-Governed Evidence Admissibility for Industrial Fault Diagnosis https://ax-news.com/?article=216086950 AX-NEWS en 2026-10-15T04:00:00+00:00 Empowering Edge Agents: A Systematic Analysis of Edge-Cloud Collaboration in LLM Agent Execution https://ax-news.com/?article=216086951 AX-NEWS en 2026-10-15T04:00:00+00:00 Benchmarking and Training Reward Models for Cross-Source Evidence Grounding in Search Agents https://ax-news.com/?article=216086952 AX-NEWS en 2026-10-15T04:00:00+00:00 Learning Adaptive Deliberation Control for Reliable Recognition with Multi-Agent Language Models https://ax-news.com/?article=216086953 AX-NEWS en 2026-10-15T04:00:00+00:00 Socratic Skill Learning: Interleaving Teaching and Practice for Transferable Agent Skills https://ax-news.com/?article=216086954 AX-NEWS en 2026-10-15T04:00:00+00:00 ECMR: Evidence-Aware Deliberation Control for Multi-Agent LLM Reasoning https://ax-news.com/?article=216086956 AX-NEWS en 2026-10-15T04:00:00+00:00 PaceReasoner: Label-Free Learning to Answer Briefly from Long Reasoning https://ax-news.com/?article=216086958 AX-NEWS en 2026-10-15T04:00:00+00:00 Seeing Depth but Choosing Cues in Vision-Language Models https://ax-news.com/?article=216086965 AX-NEWS en 2026-10-15T04:00:00+00:00 One-Sided Verification Under Limited Expert Review https://ax-news.com/?article=216086968 AX-NEWS en 2026-10-15T04:00:00+00:00 CompanionSafe: From Multi-turn Safety Evaluation to Guardrails for AI Companions https://ax-news.com/?article=216086970 AX-NEWS en 2026-10-15T04:00:00+00:00 Fresh at Decision, Stale at Action: Routing New Information to LLM Decisions Already Made https://ax-news.com/?article=216086971 AX-NEWS en 2026-10-15T04:00:00+00:00 Monitoring latent reasoning in looped language models https://ax-news.com/?article=216086973 AX-NEWS en 2026-10-15T04:00:00+00:00 RadixFlow: Filling Execution Bubbles in Prefix-Cached Hybrid LLM Serving https://ax-news.com/?article=216086977 AX-NEWS en 2026-10-15T04:00:00+00:00 QORH: Learning Query-Specific Ordered Rule Hypergraphs for Inductive Knowledge Graph Link Prediction https://ax-news.com/?article=216086978 AX-NEWS en 2026-10-15T04:00:00+00:00 Consider, Then Choose: Order-Invariant Decisions in System One Models https://ax-news.com/?article=216086985 AX-NEWS en 2026-10-15T04:00:00+00:00 Choosing LLMs for Strategic Agent Interactions https://ax-news.com/?article=216086986 AX-NEWS en 2026-10-15T04:00:00+00:00 ABot-ER: Unified Embodied Reasoning through Agentic Data-Model Co-Evolution https://ax-news.com/?article=216086987 AX-NEWS en 2026-10-15T04:00:00+00:00 Delegating Earth science model calibration to knowledge-guided LLM agents https://ax-news.com/?article=216086988 AX-NEWS en 2026-10-15T04:00:00+00:00 The Singularity Has a Distribution: Exact Timing Laws and Detection Limits for a Stochastic Intelligence Explosion https://ax-news.com/?article=216086989 AX-NEWS en 2026-10-15T04:00:00+00:00 Thinker-WM: A Unified World Model with Shared Multimodal Representations for Embodied Intelligence https://ax-news.com/?article=216086990 AX-NEWS en 2026-10-15T04:00:00+00:00 Autonomous Science Bench: Evaluating AI Agents for Autonomous Scientific Discovery https://ax-news.com/?article=216086993 AX-NEWS en 2026-10-15T04:00:00+00:00 The Smart Buildings Challenge: Learning Foundation Models for Real-World Optimization at Scale https://ax-news.com/?article=216086995 AX-NEWS en 2026-10-15T04:00:00+00:00 Input-Conditioned Search for Efficient Test-Time Scaling of Recursive Reasoners https://ax-news.com/?article=216086997 AX-NEWS en 2026-10-15T04:00:00+00:00 Configuring RAG Systems: What Breaks, Where Originates, and How to Fix https://ax-news.com/?article=216086998 AX-NEWS en 2026-10-15T04:00:00+00:00 Order-Consistent Latent Geometry for Reliable Short-Horizon Planning in World Models https://ax-news.com/?article=216087002 AX-NEWS en 2026-10-15T04:00:00+00:00 Auditing Future-Memory Use in Point-in-Time Language Agents https://ax-news.com/?article=216087003 AX-NEWS en 2026-10-15T04:00:00+00:00 AgentStripes: An Evidence-Graded Maturity Model for AI Agents https://ax-news.com/?article=216087004 AX-NEWS en 2026-10-15T04:00:00+00:00 Beyond Answer Voting: Fine-Grained Correction of LLM Reasoning through Graph Alignment across Sampled Traces https://ax-news.com/?article=216087009 AX-NEWS en 2026-10-15T04:00:00+00:00 Unlocking Token Rewards via Training-Free Reward Attribution https://ax-news.com/?article=216087010 AX-NEWS en 2026-10-15T04:00:00+00:00 Beyond the Verdict: Agentic Code Judging with Verifiable Feedback https://ax-news.com/?article=216087011 AX-NEWS en 2026-10-15T04:00:00+00:00 Jeva: System One Models from First Principles https://ax-news.com/?article=216087012 AX-NEWS en 2026-10-15T04:00:00+00:00 BLADE: Auditing Information Use for Failure Attribution in LLM Multi-Agent Systems https://ax-news.com/?article=216087014 AX-NEWS en 2026-10-15T04:00:00+00:00 Self-Evolving Agent Harness https://ax-news.com/?article=216087016 AX-NEWS en 2026-10-15T04:00:00+00:00 Who Improves the Robot? Toward Physical Recursive Self-Improvement https://ax-news.com/?article=216087017 AX-NEWS en 2026-10-15T04:00:00+00:00 MFG: Multi-turn Feedback Guided Molecular Optimization https://ax-news.com/?article=216087018 AX-NEWS en 2026-10-15T04:00:00+00:00 AesCode: Aesthetic Code Generation with Decoupled Cross-Modal Rewards https://ax-news.com/?article=216087019 AX-NEWS en 2026-10-15T04:00:00+00:00 Subgraph-Aware Training of Language Models for Knowledge Graph Completion Using Structure-Aware Contrastive Learning https://ax-news.com/?article=216087021 AX-NEWS en 2026-10-15T04:00:00+00:00 Latent Algorithmic Structure Precedes Grokking: A Mechanistic Study of ReLU MLPs on Modular Arithmetic https://ax-news.com/?article=216087022 AX-NEWS en 2026-10-15T04:00:00+00:00 Selective Knowledge Control for Continual GUI Agent Learning over Application Streams https://ax-news.com/?article=216086211 AX-NEWS en 2026-10-15T04:00:00+00:00 Refined Topology-Pass Scheduling: Damped Trust-Region Compensation for Dynamic k-NN Graphs in SE(3)-Equivariant Structure Prediction https://ax-news.com/?article=216087024 AX-NEWS en 2026-10-15T04:00:00+00:00 MRFlow: Mechanism-Structured Residual Flow Matching for Virtual Cell Perturbation Prediction https://ax-news.com/?article=216087025 AX-NEWS en 2026-10-15T04:00:00+00:00 Predict Before You Modify: Learning Improvement Dynamics for Self-Evolving Agents https://ax-news.com/?article=216087027 AX-NEWS en 2026-10-15T04:00:00+00:00 GameSmith: Scaling Zero-Sum Self-Play with Synthesised Games https://ax-news.com/?article=216087028 AX-NEWS en 2026-10-15T04:00:00+00:00 Splicing Hints into Reasoning Traces: Learning from Demonstrator Failures https://ax-news.com/?article=216086217 AX-NEWS en 2026-10-15T04:00:00+00:00 Verifier-Grounded Agentic RL for Provably Correct Code https://ax-news.com/?article=216087031 AX-NEWS en 2026-10-15T04:00:00+00:00 SemTree: Judge-Aware Semantic Decision Trees for Inspectable and Repairable Rule Decisions https://ax-news.com/?article=216087033 AX-NEWS en 2026-10-15T04:00:00+00:00 PreSO: Privileged Representation Isolation for On-Policy Self-Distillation https://ax-news.com/?article=216087037 AX-NEWS en 2026-10-15T04:00:00+00:00 When Log Parsing Removes What Matters: Detecting Failures in Distributed GPU Workloads https://ax-news.com/?article=216087039 AX-NEWS en 2026-10-15T04:00:00+00:00 Bias Robustness of Genetic Multi-Criteria Sorting versus Learned Rankers under Proxy Skew and Label Contamination https://ax-news.com/?article=216087040 AX-NEWS en 2026-10-15T04:00:00+00:00 Barycentric Anchored Weight Search for Robust Model Merging https://ax-news.com/?article=216087043 AX-NEWS en 2026-10-15T04:00:00+00:00 CoEvoke: Evoking Multi-Agent Collaboration for Trajectory Collection https://ax-news.com/?article=216087044 AX-NEWS en 2026-10-15T04:00:00+00:00 OPMD: On-Policy Mechanism Distillation Beyond Output Supervision https://ax-news.com/?article=216087052 AX-NEWS en 2026-10-15T04:00:00+00:00 The Future of AI-assisted Physics: Discovering, Verifying and Organizing Results via Formalization https://ax-news.com/?article=216087056 AX-NEWS en 2026-10-15T04:00:00+00:00 One Model, Multiple Compute Budgets: Multi-Ratio ConceptMoE for Flexible Compute Across Turns https://ax-news.com/?article=216087057 AX-NEWS en 2026-10-15T04:00:00+00:00 Two-Stage Multi-modal Learning for Dynamic Audio-Visual Navigation: From Physical Alignment to Scene Aggregation https://ax-news.com/?article=216087058 AX-NEWS en 2026-10-15T04:00:00+00:00 SAGE: Efficient Protected Vision-Language Inference on Smart Glasses https://ax-news.com/?article=216087064 AX-NEWS en 2026-10-15T04:00:00+00:00 Cortex: Measurement-Gated Evolution and Pruning of Coding-Agent Skills and Rules https://ax-news.com/?article=216087065 AX-NEWS en 2026-10-15T04:00:00+00:00 Learnable Low-Rank Polynomial Sketch for Effective Linear Attention https://ax-news.com/?article=216087066 AX-NEWS en 2026-10-15T04:00:00+00:00 CAPTOR: a vision-language foundation model for Chest-Abdomen-Pelvis Oncologic CT https://ax-news.com/?article=216087067 AX-NEWS en 2026-10-15T04:00:00+00:00 Latent World Action Model for GUI Agents https://ax-news.com/?article=216087068 AX-NEWS en 2026-10-15T04:00:00+00:00 Agentic Data Engineering for LLMs: System Design and a Controlled Empirical Study https://ax-news.com/?article=216087069 AX-NEWS en 2026-10-15T04:00:00+00:00 Akule: Fast and Scalable Multi-Robot Motion Planning via Sparse Interaction Diffusion https://ax-news.com/?article=216087075 AX-NEWS en 2026-10-15T04:00:00+00:00 TraceSampler: Making Sampling Errors Predictable and Correctable for Accelerated Generative Sampling https://ax-news.com/?article=216087077 AX-NEWS en 2026-10-15T04:00:00+00:00 DexFLEX: Contact-Aware Foundation Controller for Command-Guided Dexterity https://ax-news.com/?article=216087078 AX-NEWS en 2026-10-15T04:00:00+00:00 Deep learning from a control vantage point https://ax-news.com/?article=216087079 AX-NEWS en 2026-10-15T04:00:00+00:00 RealityBench: Simulated Environments to Evaluate a Vision Language Model's Ability to Document Human Physical Work https://ax-news.com/?article=216087081 AX-NEWS en 2026-10-15T04:00:00+00:00 Coarse-Graining Recursive Expert Computation: Continuation-Relative Interfaces and Failure Modes https://ax-news.com/?article=216087084 AX-NEWS en 2026-10-15T04:00:00+00:00 Specification-Based Testing of Large Language Models https://ax-news.com/?article=216087087 AX-NEWS en 2026-10-15T04:00:00+00:00 Co-adaptive Rule Routing and Constraining for Structured Knowledge Retrieval https://ax-news.com/?article=216087088 AX-NEWS en 2026-10-15T04:00:00+00:00 Diffusion-Based Auctions for Multi-Winner Banner Ads https://ax-news.com/?article=216087089 AX-NEWS en 2026-10-15T04:00:00+00:00 RES-MR: Risk-Aware Reasoning for Explainable and Safe Medication Recommendation https://ax-news.com/?article=216087094 AX-NEWS en 2026-10-15T04:00:00+00:00 Compositional Concepts Erasing: Disentangling Object-Style via Domain Manifold Unlearning https://ax-news.com/?article=216087099 AX-NEWS en 2026-10-15T04:00:00+00:00 LLM-based User-Product Relevance Evaluation for Dynamic Product Advertising https://ax-news.com/?article=216087102 AX-NEWS en 2026-10-15T04:00:00+00:00 EarthAlign: Learning Language-Aligned Representations of Earth System Data https://ax-news.com/?article=216087103 AX-NEWS en 2026-10-15T04:00:00+00:00 Prospective Forcing: Learning to Look Ahead for Autoregressive Long Video Diffusion https://ax-news.com/?article=216087104 AX-NEWS en 2026-10-15T04:00:00+00:00 DexCast: Learning Real-World Dexterous Control from Human Videos https://ax-news.com/?article=216087105 AX-NEWS en 2026-10-15T04:00:00+00:00 AlignAudio: A Unified Dual-Alignment Framework for Noise-Robust Speech-Conditioned Generation https://ax-news.com/?article=216087107 AX-NEWS en 2026-10-15T04:00:00+00:00 Lingdan-V2: Large language models for clinically grounded reasoning in traditional Chinese medicine https://ax-news.com/?article=216087115 AX-NEWS en 2026-10-15T04:00:00+00:00 YOUDrive: Driving Style as a Composable Direction for End-to-End Autonomous Driving https://ax-news.com/?article=216087119 AX-NEWS en 2026-10-15T04:00:00+00:00 Cross-Lingual TTS for Indian Languages: A Benchmark and Inference-Time Duration Estimation Strategies https://ax-news.com/?article=216087120 AX-NEWS en 2026-10-15T04:00:00+00:00 Getting Space Right: Agentic Rewards for Image Generation https://ax-news.com/?article=216087121 AX-NEWS en 2026-10-15T04:00:00+00:00 Probabilistic Multi-Source Data Selection via Learnable Categorical Priors: Variance Reduction and Guaranteed Derandomization https://ax-news.com/?article=216087125 AX-NEWS en 2026-10-15T04:00:00+00:00 Too Late to Prune: Generative AI, the Screen, and Team Creative Decisions https://ax-news.com/?article=216087128 AX-NEWS en 2026-10-15T04:00:00+00:00 UltraBERT: Beyond the Limit of BERT Pre-Training https://ax-news.com/?article=216087136 AX-NEWS en 2026-10-15T04:00:00+00:00 TurnCost: Turns, Not Observations: Cache-Aware Loop Engineering for Coding Agents https://ax-news.com/?article=216087137 AX-NEWS en 2026-10-15T04:00:00+00:00 scHFBiMamba: a bidirectional Mamba autoencoder for cardiac disease-state classification from single-nucleus RNA-seq data https://ax-news.com/?article=216087139 AX-NEWS en 2026-10-15T04:00:00+00:00 RIECNN: Real-Time Image Enhanced CNN for Traffic Sign Recognition https://ax-news.com/?article=216087140 AX-NEWS en 2026-10-15T04:00:00+00:00 To Defer or Not to Defer? Online Learning with LLMs and Congested Experts https://ax-news.com/?article=216087142 AX-NEWS en 2026-10-15T04:00:00+00:00 Exploring Jailbreak Vulnerability Across Depth-Based Dynamic Inference in Large Language Models https://ax-news.com/?article=216087143 AX-NEWS en 2026-10-15T04:00:00+00:00 PANINI-DR: Controlled Deep Research through Generative Semantic Workspaces https://ax-news.com/?article=216087144 AX-NEWS en 2026-10-15T04:00:00+00:00 Framework for an AI-Ready ARPES Community Database https://ax-news.com/?article=216087151 AX-NEWS en 2026-10-15T04:00:00+00:00 Co-DSL: Human-LLM Co-design of Reusable Spatial Concepts for Layout Generation https://ax-news.com/?article=216087154 AX-NEWS en 2026-10-15T04:00:00+00:00 Accuracy and Uncertainty in Machine Deception Detection (Research White Paper) https://ax-news.com/?article=216087155 AX-NEWS en 2026-10-15T04:00:00+00:00 Anchor-and-Harvest Curriculum: A Fully Unmasked Non-LLM Curriculum for Craftax https://ax-news.com/?article=216087156 AX-NEWS en 2026-10-15T04:00:00+00:00 ZOIF: Zeroth-Order Influence Function Estimation for LLM Data Selection Using Only Forward Passes https://ax-news.com/?article=216087161 AX-NEWS en 2026-10-15T04:00:00+00:00 Siam-ALS: An Explainable Siamese Deep Learning Framework for Early ALS Detection Using EEG and Eye-Tracking Signals https://ax-news.com/?article=216087165 AX-NEWS en 2026-10-15T04:00:00+00:00 E8 Lattice Key Quantization for Low-Bit KV-Cache Compression https://ax-news.com/?article=216087166 AX-NEWS en 2026-10-15T04:00:00+00:00 Sensitivity or Criterion? Measuring and Moving When Language Models Act https://ax-news.com/?article=216087167 AX-NEWS en 2026-10-15T04:00:00+00:00 Pessimistic Latent Task-aware Optimization for Robust Offline Meta-Reinforcement Learning https://ax-news.com/?article=216087170 AX-NEWS en 2026-10-15T04:00:00+00:00 When Messages Go Wrong: Understanding Communication Faults in LLM-Based Multi-Agent Systems https://ax-news.com/?article=216087171 AX-NEWS en 2026-10-15T04:00:00+00:00 Security in LLM-Assisted Coding: A Systematic Literature Review https://ax-news.com/?article=216086239 AX-NEWS en 2026-10-15T04:00:00+00:00 SKG: A Law-Induced Engine from Inference to Induction https://ax-news.com/?article=216087173 AX-NEWS en 2026-10-15T04:00:00+00:00 CacheLink: Functional KV Transport for Zero-Prefill Cross-Model Context Handoff https://ax-news.com/?article=216087175 AX-NEWS en 2026-10-15T04:00:00+00:00 SARATHI: Decoupled Data-Free Probing and Adaptive Reconstruction for Structured LLM Pruning https://ax-news.com/?article=216087181 AX-NEWS en 2026-10-15T04:00:00+00:00 TabMosaic: Unified In-Context Diffusion for Tabular Generative Tasks https://ax-news.com/?article=216087185 AX-NEWS en 2026-10-15T04:00:00+00:00 Uncovering the Generative Landscape of Diffusion Models: A Spectral-Guided Quality-Diversity Diffusion Framework https://ax-news.com/?article=216087187 AX-NEWS en 2026-10-15T04:00:00+00:00 Hyperbolic Time Series Forecasting with Learnable Decomposition and Manifold Dynamics https://ax-news.com/?article=216087191 AX-NEWS en 2026-10-15T04:00:00+00:00 Adaptive Look, Flexible Thought: Learning How and How Long to Think in Multimodal Reasoning https://ax-news.com/?article=216087193 AX-NEWS en 2026-10-15T04:00:00+00:00 Personalized LLM Recommendation with Semantic IDs: Autoregressive Beam Search vs. Multi-Token Prediction https://ax-news.com/?article=216087198 AX-NEWS en 2026-10-15T04:00:00+00:00 Review Rarely Beats the Stronger Model: Separating Verification from Capability Transfer in LLM Pipelines https://ax-news.com/?article=216087199 AX-NEWS en 2026-10-15T04:00:00+00:00 Gen Through the Lens: Camera-Controllable Video Generation via Cross-Coordinate Conditioning Fusion https://ax-news.com/?article=216087204 AX-NEWS en 2026-10-15T04:00:00+00:00 Unfair and Unsafe: Everyday Bias Triggers Emergent Misalignment https://ax-news.com/?article=216087205 AX-NEWS en 2026-10-15T04:00:00+00:00 Embedding Information in Policy Randomness: Distribution-Preserving Implicit Communication in MDPs https://ax-news.com/?article=216087207 AX-NEWS en 2026-10-15T04:00:00+00:00 When Does Compensating Inherited Quantization Error Help? Mean-Square Guarantees for Layer-Wise Quantization and Their Limits https://ax-news.com/?article=216087209 AX-NEWS en 2026-10-15T04:00:00+00:00 OT-FlowRec: Optimal Transport-Guided Multi-Bridge Flow for Multimodal Sequential Recommendation https://ax-news.com/?article=216087212 AX-NEWS en 2026-10-15T04:00:00+00:00 AI Representations of Mental Health Stigma: Quantifying the Gap Between AI Estimations and Human Perceptions Across Gender Groups Using GPT-Based LLMs https://ax-news.com/?article=216087213 AX-NEWS en 2026-10-15T04:00:00+00:00 Adaptive Compression and Targeted Perturbation: A Unified Framework for Generalized Audio Deepfake Detection https://ax-news.com/?article=216087218 AX-NEWS en 2026-10-15T04:00:00+00:00 PID-Gated Continual Prompt Adaptation Under Noisy Feedback https://ax-news.com/?article=216087219 AX-NEWS en 2026-10-15T04:00:00+00:00 Query Your Way Out: Benchmarking Multi-Turn Knowledge Reasoning through Generalized Puzzle Solving https://ax-news.com/?article=216087223 AX-NEWS en 2026-10-15T04:00:00+00:00 Fisher information and the geometry of memorization in neural networks https://ax-news.com/?article=216087224 AX-NEWS en 2026-10-15T04:00:00+00:00 EventLens: Event-Structure Reinforcement Learning for Video Understanding https://ax-news.com/?article=216087230 AX-NEWS en 2026-10-15T04:00:00+00:00 Avoiding What Your Teacher Already Knows: Entity Familiarity for Deep-Search Distillation https://ax-news.com/?article=216087231 AX-NEWS en 2026-10-15T04:00:00+00:00 A Survey of Flow Matching in Reinforcement Learning https://ax-news.com/?article=216087232 AX-NEWS en 2026-10-15T04:00:00+00:00 SLDBench v2: Active Scaling Law Discovery https://ax-news.com/?article=216087234 AX-NEWS en 2026-10-15T04:00:00+00:00 Explicitly Aligned Multi-View Breast Cancer Risk Prediction from Variable-Length Screening Histories https://ax-news.com/?article=216087235 AX-NEWS en 2026-10-15T04:00:00+00:00 BAT3R: Robust Online 3D Reconstruction with Bayesian Adaptive State Updates https://ax-news.com/?article=216087236 AX-NEWS en 2026-10-15T04:00:00+00:00 WorldRoPE: Probabilistic World-Centric Rotary Embedding for Multi-View Attention https://ax-news.com/?article=216087240 AX-NEWS en 2026-10-15T04:00:00+00:00 Estimating the Causal Impact of Social Navigation Signals in Corridor Scenarios https://ax-news.com/?article=216087241 AX-NEWS en 2026-10-15T04:00:00+00:00 ARMED: Adaptive Retrieval-Augmented Medication Recommendation https://ax-news.com/?article=216087243 AX-NEWS en 2026-10-15T04:00:00+00:00 CryptoFlowBench: Benchmarking Multi-Hop Reasoning on Blockchains for Cryptocurrency Fund Tracing https://ax-news.com/?article=216087246 AX-NEWS en 2026-10-15T04:00:00+00:00 SLEM: Spectrum-Aware Latent Expert Merging https://ax-news.com/?article=216087249 AX-NEWS en 2026-10-15T04:00:00+00:00 From Caricature to Collective Artifact: How Persona Construction Drives Polarization in Generative Social Simulations https://ax-news.com/?article=216087250 AX-NEWS en 2026-10-15T04:00:00+00:00 pi-Net: Empirical Latent Representations for Differentiable Physics Heads in Data-Scarce Systems https://ax-news.com/?article=216087252 AX-NEWS en 2026-10-15T04:00:00+00:00 Heuristics are Not Enough: Calibrated and Corrected Caching for Video Diffusion Acceleration https://ax-news.com/?article=216087257 AX-NEWS en 2026-10-15T04:00:00+00:00 Integrating Feature Understandability into Feature Selection for Human-Centred Tabular Explanations https://ax-news.com/?article=216087258 AX-NEWS en 2026-10-15T04:00:00+00:00 AeroChem: Closed-loop Physics-Informed State Space Modeling for Long-term Chemically-Reactive Air Quality Forecasting--Extended Version https://ax-news.com/?article=216087259 AX-NEWS en 2026-10-15T04:00:00+00:00 REEL: Learning to Retrieve, Evaluate, and Evolve Visual Memory for Any Long-Horizon Multi-Shot Video Generation https://ax-news.com/?article=216087268 AX-NEWS en 2026-10-15T04:00:00+00:00 InfoVis: Unified Slide Image Generation and Editing https://ax-news.com/?article=216087269 AX-NEWS en 2026-10-15T04:00:00+00:00 Logit Leakage through Floating-Point Bias Addition