https://ax-news.com/?article=183790174 AX-NEWS en 2026-09-30T05:54:18+00:00 "Astra Advanced Intelligence at a price of a quarter"...OpenAI, 'GPT-6.1 Sol' released https://ax-news.com/?article=184525176 AX-NEWS en 2026-09-30T05:54:16+00:00 Palauans fear getting caught in potential conflict between the US and China https://ax-news.com/?article=184525177 AX-NEWS en 2026-09-30T05:54:16+00:00 Oil retreat fails to halt bond yield rise in Japan, US https://ax-news.com/?article=184525178 AX-NEWS en 2026-09-30T05:54:16+00:00 Malaysia's former PM Mahathir, 101, hospitalized after wife's death https://ax-news.com/?article=184525179 AX-NEWS en 2026-09-30T05:51:57+00:00 On October 1st, on duty China will be the rotating director. Long https://ax-news.com/?article=184525180 AX-NEWS en 2026-09-30T05:51:37+00:00 R Stars through GTA 6 more games: Players can hook up, brush SNS, exercise... https://ax-news.com/?article=184525181 AX-NEWS en 2026-09-30T05:37:36+00:00 Polar krypton: There are no plans to develop a new tram-type, focus superfast charge and mix https://ax-news.com/?article=184525182 AX-NEWS en 2026-09-30T05:35:32+00:00 South Korea marks major shift to sodium-ion batteries to regain market https://ax-news.com/?article=184525184 AX-NEWS en 2026-09-30T05:30:53+00:00 The 6 Best Laptop Docking Stations to Unlock the Full Desktop Experience (2026) https://ax-news.com/?article=184525185 AX-NEWS en 2026-09-30T05:23:04+00:00 TrinaTracker launches solar panel installation and cleaning robots https://ax-news.com/?article=184525186 AX-NEWS en 2026-09-30T05:21:58+00:00 U.S. homeowners are now slightly less mistrustful of solar companies https://ax-news.com/?article=184525187 AX-NEWS en 2026-09-30T05:17:54+00:00 Dyson, AI, electric toothbrush CamaraJet, once, officially admitted that there was a leak in the early batch. https://ax-news.com/?article=184525188 AX-NEWS en 2026-09-30T05:16:33+00:00 The vibration terminated the acquisition of the connection advantage and the payment plate had previously been suspended and renewed. https://ax-news.com/?article=184525189 AX-NEWS en 2026-09-30T05:15:02+00:00 Apple Pay is now available in India https://ax-news.com/?article=184525190 AX-NEWS en 2026-09-30T05:08:53+00:00 Linux Laboratories raises $70M from ChrysCapital and Tata Capital Healthcare Fund https://ax-news.com/?article=184525191 AX-NEWS en 2026-09-30T05:05:56+00:00 Dirty Optimization Secrets (C for Playdate) https://ax-news.com/?article=184525192 AX-NEWS en 2026-09-30T05:00:50+00:00 Apple Pay landed on the Indian market, initially supporting only one bank. https://ax-news.com/?article=184525193 AX-NEWS en 2026-09-30T05:00:00+00:00 Fanatics Promo Code: 10% Off https://ax-news.com/?article=184435176 AX-NEWS en 2026-09-30T04:52:58+00:00 Taiwan taps US tech for sea drones to fend off China's vast maritime fleet https://ax-news.com/?article=184435175 AX-NEWS en 2026-09-30T04:52:58+00:00 Bangladesh's US buying spree fails to bring export benefit https://ax-news.com/?article=184510174 AX-NEWS en 2026-09-30T04:52:07+00:00 OpenAI says ‘soz, my bad’ to Australia over Medicare debacle https://ax-news.com/?article=184510175 AX-NEWS en 2026-09-30T04:49:38+00:00 The Australian government looks to harden defences from AI on its ‘legacy’ tech https://ax-news.com/?article=184435177 AX-NEWS en 2026-09-30T04:49:02+00:00 Trump signed an executive order to change the name of AI to SI and launch the U.S. government dialogue question and answer website. https://ax-news.com/?article=184525194 AX-NEWS en 2026-09-30T04:48:46+00:00 Apple Pay arrives in India with Axis Bank, PayU as launch partners https://ax-news.com/?article=184435178 AX-NEWS en 2026-09-30T04:46:40+00:00 There’s been buzz around Carney for a prize long coveted by Trump https://ax-news.com/?article=184525195 AX-NEWS en 2026-09-30T04:38:34+00:00 Commentary: What risks does China's DRAM capacity face amid tightening market? https://ax-news.com/?article=184525196 AX-NEWS en 2026-09-30T04:38:32+00:00 DeepSeek brings software tools to Huawei's Ascend 950 to take on Nvidia https://ax-news.com/?article=184435179 AX-NEWS en 2026-09-30T04:35:54+00:00 Meta Muse Fire, Silver Warning AI Smart or Impact Apple Service Business Income https://ax-news.com/?article=184435180 AX-NEWS en 2026-09-30T04:31:02+00:00 vivo V80 price in India leaks along with full specs https://ax-news.com/?article=184525197 AX-NEWS en 2026-09-30T04:26:32+00:00 Geely-NIO deal signals consolidation in China's fragmented EV battery-swapping market https://ax-news.com/?article=184435181 AX-NEWS en 2026-09-30T04:20:07+00:00 US-China trade truce extension draws orders back to China, threatening Taiwanese booking volumes https://ax-news.com/?article=184435182 AX-NEWS en 2026-09-30T04:18:05+00:00 VSMC bets on value over cost as Singapore fab builds next-generation R＆amp;D and IP capabilities https://ax-news.com/?article=184435183 AX-NEWS en 2026-09-30T04:14:16+00:00 No OpenAI IPO Until the AI Stops Going Rogue, CEO Sam Altman Says https://ax-news.com/?article=184435184 AX-NEWS en 2026-09-30T04:13:25+00:00 CXMT's US$5.2 billion buildout deepens China's push for domestic DRAM equipment https://ax-news.com/?article=184435185 AX-NEWS en 2026-09-30T04:09:44+00:00 Foxconn links motors, humanoids, smart factories into a vertically integrated robotics strategy https://ax-news.com/?article=184435186 AX-NEWS en 2026-09-30T04:06:17+00:00 Magnesium prices fall below aluminum as EV makers look to cut weight https://ax-news.com/?article=184435187 AX-NEWS en 2026-09-30T04:05:15+00:00 Fake Express Packages on npm Spread a Linux Worm https://ax-news.com/?article=184435188 AX-NEWS en 2026-09-30T04:05:03+00:00 Robinwood has launched the AI smart body tool to automatically track transactions for users. https://ax-news.com/?article=184525198 AX-NEWS en 2026-09-30T04:05:00+00:00 APOD: 2026 September 30 – Arp 78: Peculiar Galaxy in Aries https://ax-news.com/?article=184435189 AX-NEWS en 2026-09-30T04:04:53+00:00 Biadi: Follow-up to the brands abroad. https://ax-news.com/?article=184435190 AX-NEWS en 2026-09-30T04:04:49+00:00 Thunder Snake further expands the Trillion's joint product line, with pudding and Coolomey. Machine https://ax-news.com/?article=184525199 AX-NEWS en 2026-09-30T04:01:00+00:00 Powerful Storms Continue to Prowl the Pacific https://ax-news.com/?article=184378164 AX-NEWS en 2026-09-30T04:00:00+00:00 AdaFlash: Adaptive Speculative Decoding via On-Policy Distilled Diffusion Drafters https://ax-news.com/?article=184376591 AX-NEWS en 2026-09-30T04:00:00+00:00 Understanding and Exploiting Anisotropy in Post-Training https://ax-news.com/?article=184377999 AX-NEWS en 2026-09-30T04:00:00+00:00 Quantifying the Effect of Test Set Contamination on Generative Evaluations https://ax-news.com/?article=184378253 AX-NEWS en 2026-09-30T04:00:00+00:00 Improving Calibration of Black-Box Radiology AI Using Test-Time Augmentation https://ax-news.com/?article=184378456 AX-NEWS en 2026-09-30T04:00:00+00:00 OpenAI-HuggingFace: A Reproduction ＆ Lessons for Alignment Testing https://ax-news.com/?article=184378461 AX-NEWS en 2026-09-30T04:00:00+00:00 Risk-Averse Online POMDP Planning via CVaR of the Immediate Cost with Performance Guarantees https://ax-news.com/?article=184378714 AX-NEWS en 2026-09-30T04:00:00+00:00 Neural networks for spectral optimization https://ax-news.com/?article=184375903 AX-NEWS en 2026-09-30T04:00:00+00:00 BEACON: A Versatile Accelerator for Computational Pathology Applications https://ax-news.com/?article=184375237 AX-NEWS en 2026-09-30T04:00:00+00:00 Gate Synthesis in Dephasing-Limited Nitrogen-Vacancy Ensembles https://ax-news.com/?article=184375238 AX-NEWS en 2026-09-30T04:00:00+00:00 Quantum error mitigation from information dynamics https://ax-news.com/?article=184375965 AX-NEWS en 2026-09-30T04:00:00+00:00 Dual-Mode Low-Rank Learner with Bridge-Prototype Ensemble for Vision-Language Class-Incremental Learning https://ax-news.com/?article=184377012 AX-NEWS en 2026-09-30T04:00:00+00:00 Arithmetic Simplicity in Stochastic Gradient Methods https://ax-news.com/?article=184377034 AX-NEWS en 2026-09-30T04:00:00+00:00 When the Merge Coefficient Stops Mattering: Proximity Regularized Merging for Continual LoRA Adaptation https://ax-news.com/?article=184377994 AX-NEWS en 2026-09-30T04:00:00+00:00 Soft Geometric Inductive Bias for Object Centric Dynamics https://ax-news.com/?article=184378817 AX-NEWS en 2026-09-30T04:00:00+00:00 On-Policy Visual Evidence Distillation https://ax-news.com/?article=184379067 AX-NEWS en 2026-09-30T04:00:00+00:00 Screening Is Enough https://ax-news.com/?article=184376202 AX-NEWS en 2026-09-30T04:00:00+00:00 Hybrid Approach for Enhancing Lesion Segmentation in Fundus Images https://ax-news.com/?article=184378153 AX-NEWS en 2026-09-30T04:00:00+00:00 Jet-Long: Efficient Long-Context Extension with Dynamic Bifocal RoPE https://ax-news.com/?article=184377959 AX-NEWS en 2026-09-30T04:00:00+00:00 Understanding and Mitigating Under-Confidence in GNNs from the Final Layer https://ax-news.com/?article=184378792 AX-NEWS en 2026-09-30T04:00:00+00:00 CounterSteer: Suppressing Indirect Prompt Injection with Activation Steering https://ax-news.com/?article=184375303 AX-NEWS en 2026-09-30T04:00:00+00:00 Efficient Simulation of Hybrid Continuous- and Discrete-Variable Quantum Circuits via Gaussian Decompositions https://ax-news.com/?article=184375933 AX-NEWS en 2026-09-30T04:00:00+00:00 Towards Scalable Context-Aware Single-Cell Spatial Transcriptomics Prediction from Histology Images https://ax-news.com/?article=184376092 AX-NEWS en 2026-09-30T04:00:00+00:00 A Benchmark ＆ Dataset for Detecting AI-Manipulated Visual Evidence in the Court System https://ax-news.com/?article=184376146 AX-NEWS en 2026-09-30T04:00:00+00:00 Making Cross-Continental Federated Learning Repeatable with FLIP: a Multi-Application Study https://ax-news.com/?article=184376292 AX-NEWS en 2026-09-30T04:00:00+00:00 Learning to Recorrupt: Noise Distribution Agnostic Self-Supervised Image Denoising https://ax-news.com/?article=184376719 AX-NEWS en 2026-09-30T04:00:00+00:00 Mitigating Hallucination in Large Language Models: A Capability-Oriented Survey on RAG, Reasoning, and Agentic Systems https://ax-news.com/?article=184377214 AX-NEWS en 2026-09-30T04:00:00+00:00 MoGround: Measuring and Mitigating Modality Distraction in Vision-Language Models https://ax-news.com/?article=184377694 AX-NEWS en 2026-09-30T04:00:00+00:00 Gradient-Guided Decoupled Adaptation for Geospatial Vision-Language Models https://ax-news.com/?article=184377697 AX-NEWS en 2026-09-30T04:00:00+00:00 Action Shaping: Policies Absorb What They Can Express https://ax-news.com/?article=184377808 AX-NEWS en 2026-09-30T04:00:00+00:00 DCEmbed: Scalable Optimization over Neural Surrogates https://ax-news.com/?article=184378175 AX-NEWS en 2026-09-30T04:00:00+00:00 Efficient LLM Adversarial Training via Low-Rank Defense and Circuit-Guided Surrogates https://ax-news.com/?article=184378179 AX-NEWS en 2026-09-30T04:00:00+00:00 Not Every Divergence Should Be Suppressed: Counterfactual Recoverability in On-Policy Distillation https://ax-news.com/?article=184378221 AX-NEWS en 2026-09-30T04:00:00+00:00 PlayTrain: An Efficient Reinforcement Learning Framework for LLM-Generated Adaptable JavaScript Games https://ax-news.com/?article=184378341 AX-NEWS en 2026-09-30T04:00:00+00:00 Why Fine-Tuning Encourages Hallucinations and How to Fix It https://ax-news.com/?article=184378467 AX-NEWS en 2026-09-30T04:00:00+00:00 SAGE: A Statistical Acceptance Gate for Self-Evolving Agents https://ax-news.com/?article=184378588 AX-NEWS en 2026-09-30T04:00:00+00:00 OptiCom : A Unified Framework for State-Conditioned Composition in LLM-Driven Optimization https://ax-news.com/?article=184378726 AX-NEWS en 2026-09-30T04:00:00+00:00 LoopICL: Looping a single transformer block to solve tabular tasks https://ax-news.com/?article=184375175 AX-NEWS en 2026-09-30T04:00:00+00:00 ParaAnya: Accelerating Parallel Diffusion Sampling with Plug-and-Play Output Caching https://ax-news.com/?article=184375176 AX-NEWS en 2026-09-30T04:00:00+00:00 Reshaping Rollout Workloads for Asynchronous RL Post-Training on Heterogeneous Accelerators https://ax-news.com/?article=184375182 AX-NEWS en 2026-09-30T04:00:00+00:00 ARGOS: Reinforcement Learning-Driven Multidimensional Elasticity for Service Orchestration in the Computing Continuum https://ax-news.com/?article=184375183 AX-NEWS en 2026-09-30T04:00:00+00:00 DScale: Scaling Block-Diffusion Speculative Decoding with Adaptive Verification https://ax-news.com/?article=184375190 AX-NEWS en 2026-09-30T04:00:00+00:00 Making Cross-Continental Federated Learning Repeatable with FLIP: a Multi-Application Study https://ax-news.com/?article=184375193 AX-NEWS en 2026-09-30T04:00:00+00:00 Replay the Curvature: Accurate and Scalable NVFP4 Quantization for Large Language Model Inference https://ax-news.com/?article=184375194 AX-NEWS en 2026-09-30T04:00:00+00:00 Federated Clustering with Unknown Local and Global Cluster Cardinalities https://ax-news.com/?article=184375195 AX-NEWS en 2026-09-30T04:00:00+00:00 CF-LoRA: Decoupled Factor Aggregation and Adaptation-Aware Client Clustering for Federated LoRA Fine-Tuning https://ax-news.com/?article=184375196 AX-NEWS en 2026-09-30T04:00:00+00:00 Encoding and Node Choices in Transversal Fault-Tolerant Distributed Quantum Computations: An Initial Study https://ax-news.com/?article=184375198 AX-NEWS en 2026-09-30T04:00:00+00:00 Recolorable Graph Exploration by an Oblivious Agent with Fewer Colors https://ax-news.com/?article=184375205 AX-NEWS en 2026-09-30T04:00:00+00:00 Heddle: Learning Structural Templates for Parallelism Planning on Heterogeneous GPU Clusters https://ax-news.com/?article=184375210 AX-NEWS en 2026-09-30T04:00:00+00:00 Massively Parallel Reinforcement Learning with a Chaotic Reconfigurable Clockless Chip https://ax-news.com/?article=184375223 AX-NEWS en 2026-09-30T04:00:00+00:00 Homo-RAG: Homology-Guided Retrieval-Augmented Generation for Cross-Species Gene Function Prediction https://ax-news.com/?article=184375224 AX-NEWS en 2026-09-30T04:00:00+00:00 Exponential Convergence of Deep Operator Networks for Elliptic Partial Differential Equations https://ax-news.com/?article=184375236 AX-NEWS en 2026-09-30T04:00:00+00:00 Quantum Encoding Agents: A Natural Language Interface for Data Embedding Strategy Selection in Quantum Machine Learning https://ax-news.com/?article=184375239 AX-NEWS en 2026-09-30T04:00:00+00:00 Learning Trotter Orderings for Heisenberg Hamiltonians with a Ranking Transformer https://ax-news.com/?article=184375240 AX-NEWS en 2026-09-30T04:00:00+00:00 Robust Entanglement Witnessing via Dense Network Coding with Graph States https://ax-news.com/?article=184375252 AX-NEWS en 2026-09-30T04:00:00+00:00 Beyond NISQ Assumptions: One-time Memory in the Classically Accessible Random-Oracle Model https://ax-news.com/?article=184375261 AX-NEWS en 2026-09-30T04:00:00+00:00 Quantum Monte Carlo Tree Search with Fixed Confidence https://ax-news.com/?article=184375277 AX-NEWS en 2026-09-30T04:00:00+00:00 Autonomous phase discovery https://ax-news.com/?article=184375306 AX-NEWS en 2026-09-30T04:00:00+00:00 Directional pumping of a two-level system by a fluctuation-regulated quantum source https://ax-news.com/?article=184375310 AX-NEWS en 2026-09-30T04:00:00+00:00 Cyclotomic Cosets: Hidden Subgroup and Quantum Sieving Algorithm for Prime-Power Moduli https://ax-news.com/?article=184375334 AX-NEWS en 2026-09-30T04:00:00+00:00 Improving the Stability of the Hierarchical Equations of Motion for Open Quantum Systems with Strong Coupling to Structured Bosonic Baths https://ax-news.com/?article=184375335 AX-NEWS en 2026-09-30T04:00:00+00:00 Temporal trade-offs in high-dimensional entanglement: a comprehensive noise model for optimal time-bin QKD protocols https://ax-news.com/?article=184375357 AX-NEWS en 2026-09-30T04:00:00+00:00 Spread Complexity for Local Operator Quenches with Conserved Momentum https://ax-news.com/?article=184375358 AX-NEWS en 2026-09-30T04:00:00+00:00 Connecting finite-size scaling and renormalization-group flows in Anderson localization on random graphs https://ax-news.com/?article=184375364 AX-NEWS en 2026-09-30T04:00:00+00:00 AG-CoT: Verified Algorithmic Traces for LLM Program Synthesis on Clifford Circuits https://ax-news.com/?article=184375375 AX-NEWS en 2026-09-30T04:00:00+00:00 Exact probability distributions of complex spacing ratios in non-Hermitian random matrices https://ax-news.com/?article=184375403 AX-NEWS en 2026-09-30T04:00:00+00:00 Spatial superposition for a two-dimensional matter-wave interferometer in an inverted harmonic potential with gyroscopic rotational stability https://ax-news.com/?article=184375404 AX-NEWS en 2026-09-30T04:00:00+00:00 Instance-optimal high-precision shadow tomography with few-copy measurements: A metrological approach https://ax-news.com/?article=184375409 AX-NEWS en 2026-09-30T04:00:00+00:00 Experimental Realization of the Markov Chain Monte Carlo Algorithm on a Quantum Computer https://ax-news.com/?article=184375424 AX-NEWS en 2026-09-30T04:00:00+00:00 Optically detected nuclear magnetic resonance of carbon-13 in bulk diamond https://ax-news.com/?article=184375429 AX-NEWS en 2026-09-30T04:00:00+00:00 Universal Spin Squeezing Dynamical Phase Transitions across Lattice Geometries, Dimensions, and Microscopic Couplings https://ax-news.com/?article=184375430 AX-NEWS en 2026-09-30T04:00:00+00:00 IRIS: A Compiler for Distributed Quantum Systems https://ax-news.com/?article=184375433 AX-NEWS en 2026-09-30T04:00:00+00:00 The bulk spectral gap is certifiable from above but uncomputable from below https://ax-news.com/?article=184375441 AX-NEWS en 2026-09-30T04:00:00+00:00 Sample-based quantum diagonalization approach for open-shell transition-metal complexes in gas and implicit-solvent https://ax-news.com/?article=184375465 AX-NEWS en 2026-09-30T04:00:00+00:00 Deterministic synthesis and processing of frequency-bin qubits in a macroscopically coherent quantum memory https://ax-news.com/?article=184375482 AX-NEWS en 2026-09-30T04:00:00+00:00 Anyon Quasilocalization in a Quasicrystalline Toric Code https://ax-news.com/?article=184375487 AX-NEWS en 2026-09-30T04:00:00+00:00 Groenewold-Moyal twists, integrable spin-chains and AdS/CFT https://ax-news.com/?article=184375489 AX-NEWS en 2026-09-30T04:00:00+00:00 Universal Quantum Transformer https://ax-news.com/?article=184375492 AX-NEWS en 2026-09-30T04:00:00+00:00 On pseudogap phase as precursor to a superconducting dome in high-Tc cuprates: Non-analytic T* as a function of doping https://ax-news.com/?article=184375496 AX-NEWS en 2026-09-30T04:00:00+00:00 Wigner symmetries single out symmetric Wasserstein distances in all finite dimensions https://ax-news.com/?article=184375497 AX-NEWS en 2026-09-30T04:00:00+00:00 Krylov Complexity from Loschmidt Amplitude https://ax-news.com/?article=184375504 AX-NEWS en 2026-09-30T04:00:00+00:00 BRST quantization for the restoration of broken symmetries: a pedagogical example https://ax-news.com/?article=184375508 AX-NEWS en 2026-09-30T04:00:00+00:00 Passive-Dynamic-Walking-Inspired Dynamics Guidance for Energy-Efficient Humanoid Locomotion https://ax-news.com/?article=184375509 AX-NEWS en 2026-09-30T04:00:00+00:00 In-Context Learning for Robots: Methods and Applications https://ax-news.com/?article=184375511 AX-NEWS en 2026-09-30T04:00:00+00:00 MagNav: A Dual-Core Magnetic Track Guidance Framework for Lighting-Invariant Navigation in Two-Wheeled Robots https://ax-news.com/?article=184375512 AX-NEWS en 2026-09-30T04:00:00+00:00 Scouting the Dynamics Gap: Test-Time Policy Adaptation via Action-Outcome Feedback https://ax-news.com/?article=184375513 AX-NEWS en 2026-09-30T04:00:00+00:00 KPI: A Promptable Kernel for Physical Interaction on Humanoids https://ax-news.com/?article=184375514 AX-NEWS en 2026-09-30T04:00:00+00:00 SkillWeaver: Agentic Exploration over Neural Interaction Skills for Scalable Robot Data Generation https://ax-news.com/?article=184375519 AX-NEWS en 2026-09-30T04:00:00+00:00 DORA: Divergence-Oriented Data-Relay Algorithm for Partially Connected Robot Teams https://ax-news.com/?article=184375526 AX-NEWS en 2026-09-30T04:00:00+00:00 Closed-Form Cartesian Forward Kinetostatics for Spatial Multi-Segment Tendon-Driven Continuum Robots https://ax-news.com/?article=184375530 AX-NEWS en 2026-09-30T04:00:00+00:00 Asymmetric Scout-Worker Reconnaissance for Route Validation in Unknown Environments https://ax-news.com/?article=184375539 AX-NEWS en 2026-09-30T04:00:00+00:00 Simple Agentic Memory for Generalist Robot Policies https://ax-news.com/?article=184375541 AX-NEWS en 2026-09-30T04:00:00+00:00 Executor-aware Candidate Selection via a Feasibility Certificate https://ax-news.com/?article=184375543 AX-NEWS en 2026-09-30T04:00:00+00:00 RoboChrono: A Real Robot Benchmark for Streaming Task Understanding https://ax-news.com/?article=184375545 AX-NEWS en 2026-09-30T04:00:00+00:00 Where Predictive Supervision Goes Shapes What VLA Policies Learn https://ax-news.com/?article=184375547 AX-NEWS en 2026-09-30T04:00:00+00:00 T$^2$Mem: Learning Test-Time Memory for Robotics https://ax-news.com/?article=184375553 AX-NEWS en 2026-09-30T04:00:00+00:00 Spotter: Let the Embodied Model Lead, and the VLM Reflect for It https://ax-news.com/?article=184375554 AX-NEWS en 2026-09-30T04:00:00+00:00 VidAct: Learning Manipulation from In-the-Wild Videos with Object-Centric 3D Awareness https://ax-news.com/?article=184375555 AX-NEWS en 2026-09-30T04:00:00+00:00 PreferenceFlow: Test-Time Guidance of Flow-Matching Robot Policies from Human Interventions https://ax-news.com/?article=184375557 AX-NEWS en 2026-09-30T04:00:00+00:00 All Roads Lead to Rome: Flow-driven Multi-Anchor Exploration for Open-Environment Active 3D Mapping https://ax-news.com/?article=184375558 AX-NEWS en 2026-09-30T04:00:00+00:00 AeroManip-VLA: Scalable Vision-Language-Action Learning for Aerial Manipulation with RL-Generated Demonstrations https://ax-news.com/?article=184375568 AX-NEWS en 2026-09-30T04:00:00+00:00 V2X-WAM: A Cooperative World Action Model for End-to-End Autonomous Driving https://ax-news.com/?article=184375570 AX-NEWS en 2026-09-30T04:00:00+00:00 ReF-HIL: Shaping the Critic around Human Action Neighborhoods for Efficient Human-in-the-Loop Reinforcement Learning https://ax-news.com/?article=184375577 AX-NEWS en 2026-09-30T04:00:00+00:00 Taming VLAs under Robot Execution Errors: Self-Compensation and Stress Testing https://ax-news.com/?article=184375578 AX-NEWS en 2026-09-30T04:00:00+00:00 DROM: A Language-Guided Diffusion Framework for Multi-Skill Robotic Manipulation https://ax-news.com/?article=184375590 AX-NEWS en 2026-09-30T04:00:00+00:00 Risk-Aware Semantic Grounding for Trustworthy LLM-Based Robot Planning https://ax-news.com/?article=184375598 AX-NEWS en 2026-09-30T04:00:00+00:00 Learning Expressive and Compositional Motion Representation via Spectral Skills https://ax-news.com/?article=184375605 AX-NEWS en 2026-09-30T04:00:00+00:00 MVG-WAM: Multiple View Geometry-Aware World-Action Modeling for Robotic Manipulation https://ax-news.com/?article=184375607 AX-NEWS en 2026-09-30T04:00:00+00:00 ExceptionDrive: A Planning-Oriented Counterfactual Corner-Case Benchmark for Autonomous Driving https://ax-news.com/?article=184375608 AX-NEWS en 2026-09-30T04:00:00+00:00 WayFinder: Hierarchical Visual-Language-Action for Zero-Shot Waypoint Generation and Low-Level Kinematic Control https://ax-news.com/?article=184375609 AX-NEWS en 2026-09-30T04:00:00+00:00 PhysWAM: Physically Consistent World Action Model for Autonomous Driving https://ax-news.com/?article=184375610 AX-NEWS en 2026-09-30T04:00:00+00:00 Comparing Utility of Inertial, Occupancy, Semantic, and Intent Information in Human Motion Prediction During Daily Tasks https://ax-news.com/?article=184375611 AX-NEWS en 2026-09-30T04:00:00+00:00 doPlan: A Variable-Horizon Dataset for Multi-Stage Language-Conditioned Planning in Autonomous Driving https://ax-news.com/?article=184375615 AX-NEWS en 2026-09-30T04:00:00+00:00 WorldLine: Action-Driven Visual Simulation for Robotic Manipulation https://ax-news.com/?article=184375616 AX-NEWS en 2026-09-30T04:00:00+00:00 MotorMind: Scaffolding General Vision Language Models for Zero-Shot Robot Manipulation https://ax-news.com/?article=184375617 AX-NEWS en 2026-09-30T04:00:00+00:00 CrossBFM: Distilling a Shared Latent Behavior Space Across Humanoid Embodiments https://ax-news.com/?article=184375618 AX-NEWS en 2026-09-30T04:00:00+00:00 FORM: Robot Manipulation through Direct Material Law Identification https://ax-news.com/?article=184375620 AX-NEWS en 2026-09-30T04:00:00+00:00 Counterfactual Video Generation Enables Scalable Humanoid Loco-Manipulation https://ax-news.com/?article=184375621 AX-NEWS en 2026-09-30T04:00:00+00:00 In-context Robot Learning Made Simple: A Democratized Recipe for Manipulation Tasks https://ax-news.com/?article=184375622 AX-NEWS en 2026-09-30T04:00:00+00:00 Skill-Space Shooting for Autonomous Robot Policy Improvement https://ax-news.com/?article=184375623 AX-NEWS en 2026-09-30T04:00:00+00:00 Systematic Multi-Agent Vision-and-Language Navigation: Formulation, Benchmark, and Method https://ax-news.com/?article=184375625 AX-NEWS en 2026-09-30T04:00:00+00:00 GeoWind2Plan: Mission-Time 3D Urban Wind Prediction for Energy-Efficient UAV Planning https://ax-news.com/?article=184375628 AX-NEWS en 2026-09-30T04:00:00+00:00 Action Chunking Proximal Policy Optimization with Feedback Correction https://ax-news.com/?article=184375632 AX-NEWS en 2026-09-30T04:00:00+00:00 InsightMap: Structured Spatial Modeling for Embodied Multimodal Reasoning https://ax-news.com/?article=184375635 AX-NEWS en 2026-09-30T04:00:00+00:00 Direct Experience World-Model Optimization: Learning the World Beyond Action Imitation https://ax-news.com/?article=184375642 AX-NEWS en 2026-09-30T04:00:00+00:00 iTeach: In the Wild Interactive Teaching for Failure-Driven Adaptation of Robot Perception https://ax-news.com/?article=184375644 AX-NEWS en 2026-09-30T04:00:00+00:00 Hyper Yoshimura: How a slight tweak on a classical folding pattern unleashes meta-stability for deployable robots https://ax-news.com/?article=184375649 AX-NEWS en 2026-09-30T04:00:00+00:00 AlignDrive: Aligned Lateral-Longitudinal Planning for End-to-End Autonomous Driving https://ax-news.com/?article=184375654 AX-NEWS en 2026-09-30T04:00:00+00:00 EvoScene-VLA: Evolving Scene Beliefs Inside the Action Decoder for Chunked Robot Control https://ax-news.com/?article=184375655 AX-NEWS en 2026-09-30T04:00:00+00:00 Manifold-Constrained MPPI: Real-Time Sampling-Based Control for Nonlinear Equality-Constrained Robotic Systems https://ax-news.com/?article=184375669 AX-NEWS en 2026-09-30T04:00:00+00:00 PAC-MAN: Perception-Aware CBF-RL for Whole-Body Safety in Humanoid Dodgeball https://ax-news.com/?article=184375673 AX-NEWS en 2026-09-30T04:00:00+00:00 Hydra: A Navigation World Action Model with Discrete Latent Planning and Continuous Flow-Matching Execution https://ax-news.com/?article=184375681 AX-NEWS en 2026-09-30T04:00:00+00:00 ME-Brain-1.0: Memory, Cognition and Action for Evolving Embodied Intelligence https://ax-news.com/?article=184375683 AX-NEWS en 2026-09-30T04:00:00+00:00 Control Barrier Functions for Safe Free-Flying Robotic Spacecraft Operations in Tumbling Target Capture https://ax-news.com/?article=184375696 AX-NEWS en 2026-09-30T04:00:00+00:00 RLE-Bench: A Qualifying Exam for Coding Agents as Robot Learning Engineers https://ax-news.com/?article=184375706 AX-NEWS en 2026-09-30T04:00:00+00:00 What Makes World Action Models Generalize? An Empirical Study of Test-Time Future Modeling https://ax-news.com/?article=184375715 AX-NEWS en 2026-09-30T04:00:00+00:00 Agent-Callable Feature Coverage: Measuring Software Readiness for AI Agents https://ax-news.com/?article=184375717 AX-NEWS en 2026-09-30T04:00:00+00:00 Beyond Rule-Based Mutation Testing: Test-Aware Mutant Generation Using Large Language Models https://ax-news.com/?article=184375718 AX-NEWS en 2026-09-30T04:00:00+00:00 PoliVEM: a Python-driven virtual element framework for computational solid mechanics https://ax-news.com/?article=184375720 AX-NEWS en 2026-09-30T04:00:00+00:00 UNBIND: UNlearning By INference-time Directional Steering for Code LLMs https://ax-news.com/?article=184375722 AX-NEWS en 2026-09-30T04:00:00+00:00 The Uneven Decline of Collective Knowledge Production: Evidence from Stack Overflow After Generative AI https://ax-news.com/?article=184375725 AX-NEWS en 2026-09-30T04:00:00+00:00 The Invisible Throttle: Running on Borrowed Time in Scratch https://ax-news.com/?article=184375728 AX-NEWS en 2026-09-30T04:00:00+00:00 How Much Prompt Is Enough? A Blackbox Minimization of Few-Shots in LLMs https://ax-news.com/?article=184375729 AX-NEWS en 2026-09-30T04:00:00+00:00 Strategies for Deploying AI Agents in Production at Scientific User Facilities https://ax-news.com/?article=184375730 AX-NEWS en 2026-09-30T04:00:00+00:00 LatentSift: Policy-State Filtering for Token-Efficient Verification of Software Engineering Agents https://ax-news.com/?article=184375731 AX-NEWS en 2026-09-30T04:00:00+00:00 WitnessGym: Benchmarking Coding Agents on the Construction of Bug Witnesses https://ax-news.com/?article=184375732 AX-NEWS en 2026-09-30T04:00:00+00:00 CTE-Bench: Counterfactual Trace Evaluation for Stateful Software Simulators https://ax-news.com/?article=184375734 AX-NEWS en 2026-09-30T04:00:00+00:00 XRepoSkill: Learning Transferable Skills for Software Engineering Agents https://ax-news.com/?article=184375735 AX-NEWS en 2026-09-30T04:00:00+00:00 Cross-Organizational SysML Model Integration: A Survey of Challenges and AI-Supported Tasks https://ax-news.com/?article=184375739 AX-NEWS en 2026-09-30T04:00:00+00:00 SafeLLM4SE: Statistical Evaluation and Reporting for LLM-based Software Engineering Systems https://ax-news.com/?article=184375751 AX-NEWS en 2026-09-30T04:00:00+00:00 Automated Evaluation of Multi-Turn Dialogues in In-Car Conversational Assistants https://ax-news.com/?article=184375753 AX-NEWS en 2026-09-30T04:00:00+00:00 Irene: Equivalence Checking of Hybrid Quantum Programs via Structure-Preserving Symbolic Reduction https://ax-news.com/?article=184375776 AX-NEWS en 2026-09-30T04:00:00+00:00 CIRCLE: A Framework for Evaluating AI from a Real-World Lens https://ax-news.com/?article=184375787 AX-NEWS en 2026-09-30T04:00:00+00:00 After the Fix: Transfer of Corrected Agent Experience https://ax-news.com/?article=184375795 AX-NEWS en 2026-09-30T04:00:00+00:00 Dual-Fit Imperative in Security Leadership: A Grounded Theory Investigation of CISO Role Enactment in Modern Organisations https://ax-news.com/?article=184375798 AX-NEWS en 2026-09-30T04:00:00+00:00 Raising the Bar for Chinese Adolescent LLM Safety: A Culturally-Grounded, Fine-Grained Benchmark https://ax-news.com/?article=184375801 AX-NEWS en 2026-09-30T04:00:00+00:00 MMSkillRisk: Can Agents Stay Safe When Multimodal Skills Become Traps? https://ax-news.com/?article=184375802 AX-NEWS en 2026-09-30T04:00:00+00:00 TEE Anchor: Cross-TEE Organizational Endorsement for Mitigating TEE Physical Attacks https://ax-news.com/?article=184375804 AX-NEWS en 2026-09-30T04:00:00+00:00 PrivacySkills: How Privacy Guidance Shapes Source Selection in LLM Agents https://ax-news.com/?article=184375806 AX-NEWS en 2026-09-30T04:00:00+00:00 Multi-Class, Multi-Tier Network Intrusion Detection: A Comprehensive and Reproducible Benchmark https://ax-news.com/?article=184375818 AX-NEWS en 2026-09-30T04:00:00+00:00 Self-Evolving Defense: Continual Security Policy Learning for LLM Agents https://ax-news.com/?article=184375821 AX-NEWS en 2026-09-30T04:00:00+00:00 pikit: A Composable Toolkit for Indirect Prompt Injection Research and Evaluation https://ax-news.com/?article=184375824 AX-NEWS en 2026-09-30T04:00:00+00:00 SKILLLITE: Evidence-Guided Malicious Skill Auditing with Compact LLMs https://ax-news.com/?article=184375825 AX-NEWS en 2026-09-30T04:00:00+00:00 Practical Secrets Extraction against Black-box LLMs https://ax-news.com/?article=184375829 AX-NEWS en 2026-09-30T04:00:00+00:00 ToolFence: Fine-Grained Authorization for Secure Tool-Using LLM Agents https://ax-news.com/?article=184375836 AX-NEWS en 2026-09-30T04:00:00+00:00 Smooth Sailing through Spherical Shells: Provable Random-Lattice Sieving in Time $2^{0.292n}$ https://ax-news.com/?article=184375839 AX-NEWS en 2026-09-30T04:00:00+00:00 Harvest Season for SLUB: From io_uring vulnerability to Novel Sheaf-Based Exploitation Techniques https://ax-news.com/?article=184375840 AX-NEWS en 2026-09-30T04:00:00+00:00 She Spoofed Sea Ships by the Sea Shore: Measuring Large-Scale GPS Spoofing in Global Maritime Traffic https://ax-news.com/?article=184375841 AX-NEWS en 2026-09-30T04:00:00+00:00 Where Do LLMs Decide to Break the Rules? Mechanistic Localization of Prompt Injection Compliance https://ax-news.com/?article=184375843 AX-NEWS en 2026-09-30T04:00:00+00:00 Selective Channel Restoration for Backdoored Vision-Language Models https://ax-news.com/?article=184375847 AX-NEWS en 2026-09-30T04:00:00+00:00 OpenAI-HuggingFace: A Reproduction ＆ Lessons for Alignment Testing https://ax-news.com/?article=184375869 AX-NEWS en 2026-09-30T04:00:00+00:00 TRACE: Task-Aware Adaptive Self-Evolving Agentic Jailbreaking https://ax-news.com/?article=184375871 AX-NEWS en 2026-09-30T04:00:00+00:00 CORE-BREW: LLR-Based Soft Decoding for Robust Multi-Bit LLM Watermarking https://ax-news.com/?article=184375874 AX-NEWS en 2026-09-30T04:00:00+00:00 Hamming Ideals and Grobner Bases for ISD-like Syndrome Decoding https://ax-news.com/?article=184375876 AX-NEWS en 2026-09-30T04:00:00+00:00 Toward provably private learning from federated data https://ax-news.com/?article=184375885 AX-NEWS en 2026-09-30T04:00:00+00:00 JUMP: Efficient Membership Inference on Fine-Tuned Diffusion Language Models https://ax-news.com/?article=184375887 AX-NEWS en 2026-09-30T04:00:00+00:00 SIREN (Luring LLMs onto the Rocks): PAIR-Driven Preference Manipulation in Web-RAG Recommenders https://ax-news.com/?article=184375895 AX-NEWS en 2026-09-30T04:00:00+00:00 GEM-KMeans: Memory-Efficient and Accurate Clustering on Massive Scale with GPU Optimization https://ax-news.com/?article=184375898 AX-NEWS en 2026-09-30T04:00:00+00:00 Efficient Linkage-Based Compartmentalization on CHERI https://ax-news.com/?article=184375902 AX-NEWS en 2026-09-30T04:00:00+00:00 PoisonCap: Efficient Hierarchical Temporal Safety for CHERI https://ax-news.com/?article=184375905 AX-NEWS en 2026-09-30T04:00:00+00:00 PipeDRAM: A Data-Transposition-Free Processing-Using-DRAM Architecture with Hardware/Software Pipelining https://ax-news.com/?article=184375906 AX-NEWS en 2026-09-30T04:00:00+00:00 Low-power analogue neural networks with trainable nonlinear connections for continuous control https://ax-news.com/?article=184375909 AX-NEWS en 2026-09-30T04:00:00+00:00 HEIR: Learning Human-Entity Interactions with Functional Roles https://ax-news.com/?article=184375910 AX-NEWS en 2026-09-30T04:00:00+00:00 Systematic Multi-Agent Vision-and-Language Navigation: Formulation, Benchmark, and Method https://ax-news.com/?article=184375930 AX-NEWS en 2026-09-30T04:00:00+00:00 LEGO-Anything: Coding Agents for 3D Scene Reconstruction https://ax-news.com/?article=184375931 AX-NEWS en 2026-09-30T04:00:00+00:00 Stealth Is a Relation, Not a Property: How Event Representations Create Blind Spots for Timing Attacks in Event-Based Perception https://ax-news.com/?article=184375938 AX-NEWS en 2026-09-30T04:00:00+00:00 Online Versatile Incremental Learning: Towards Class and Domain-Agnostic Adaptation at Any Time https://ax-news.com/?article=184375951 AX-NEWS en 2026-09-30T04:00:00+00:00 CrossTimeEdit: A Decade-Spanning Cross-View Dataset and Reward-Guided Editing for Historical Street-View Generation https://ax-news.com/?article=184375953 AX-NEWS en 2026-09-30T04:00:00+00:00 OCA: ODE-Driven Cross-Attention for Image-to-Point-Cloud Registration https://ax-news.com/?article=184375958 AX-NEWS en 2026-09-30T04:00:00+00:00 ReWorld-Track: A Recursive Event World Model for Language-Guided Multi-Camera Tracking https://ax-news.com/?article=184375961 AX-NEWS en 2026-09-30T04:00:00+00:00 AESplat: Advancing Pose-Free Feed-Forward 3D Gaussian Splatting via Decoupled Appearance Modeling https://ax-news.com/?article=184375976 AX-NEWS en 2026-09-30T04:00:00+00:00 Motion Concept Unlearning in Video Diffusion Models https://ax-news.com/?article=184375981 AX-NEWS en 2026-09-30T04:00:00+00:00 RoXDrive: Closed-Loop Reinforcement Learning for End-to-End Autonomous Driving via Action-Faithful Rollouts https://ax-news.com/?article=184375985 AX-NEWS en 2026-09-30T04:00:00+00:00 Less Supervision, Better Generalization: Weakly Supervised Fake Region Localization in Diffusion-Edited Images https://ax-news.com/?article=184376012 AX-NEWS en 2026-09-30T04:00:00+00:00 OmniRoute: Mapping Temporal Semantic Evidence to Audio-Visual Token Budgets for Efficient Omnimodal Large Language Models https://ax-news.com/?article=184376013 AX-NEWS en 2026-09-30T04:00:00+00:00 Spatial-OPSD: Self-Improving Spatial Reasoning via Label-Free Self-Distillation https://ax-news.com/?article=184376014 AX-NEWS en 2026-09-30T04:00:00+00:00 Context without Commitment: Robust Dense Correspondence under Non-Rigid Deformation https://ax-news.com/?article=184376017 AX-NEWS en 2026-09-30T04:00:00+00:00 Task-Oriented Visual Feature Compression via Residual Vector Quantization for Device-Edge Multimodal Inference https://ax-news.com/?article=184376020 AX-NEWS en 2026-09-30T04:00:00+00:00 NRF-GS: Neural Residual Fields for Expressive and Compact Gaussian Splatting https://ax-news.com/?article=184376038 AX-NEWS en 2026-09-30T04:00:00+00:00 Beyond Attention Imbalance: Mitigating Hallucinations via Spectral Surgery https://ax-news.com/?article=184376044 AX-NEWS en 2026-09-30T04:00:00+00:00 FLASH: A "Generate Once, Synthesize Many" Framework for Synthetic Anomaly Generation in Industrial Anomaly Detection https://ax-news.com/?article=184376047 AX-NEWS en 2026-09-30T04:00:00+00:00 OFBD: Object-Focused Background Debiasing for Long-Tailed Learning https://ax-news.com/?article=184376050 AX-NEWS en 2026-09-30T04:00:00+00:00 When to Retrieve, When to Stay: Uncertainty-Aware Temporal Evidence Allocation for Streaming Video-LLMs https://ax-news.com/?article=184376060 AX-NEWS en 2026-09-30T04:00:00+00:00 Complementary Retrieval-Augmented Prompting for Consistent Long-Form Video Generation https://ax-news.com/?article=184376062 AX-NEWS en 2026-09-30T04:00:00+00:00 Event-Only Wingbeat Counting under Camera Motion: A Controlled MuJoCo Benchmark https://ax-news.com/?article=184376063 AX-NEWS en 2026-09-30T04:00:00+00:00 Label Less, Learn More: Resource-Efficient Active Semi-Supervised Learning for Onboard Satellite Image Annotation https://ax-news.com/?article=184376073 AX-NEWS en 2026-09-30T04:00:00+00:00 Decompose Radicals, Then Reward: Fine-Grained Inspection for Accurate Chinese Text Rendering https://ax-news.com/?article=184376076 AX-NEWS en 2026-09-30T04:00:00+00:00 FedSocket: Recipient-Executable Knowledge Exchange for Heterogeneous Multimodal Federated Learning https://ax-news.com/?article=184376078 AX-NEWS en 2026-09-30T04:00:00+00:00 Targeted Visual Counterfactual Explanations for Contrastive Vision-Language Model https://ax-news.com/?article=184376081 AX-NEWS en 2026-09-30T04:00:00+00:00 Exemplar2VQA: A Scalable Exemplar-Driven Visual Question Answering Generation Framework via Multi-Agent Coding https://ax-news.com/?article=184376082 AX-NEWS en 2026-09-30T04:00:00+00:00 Tracing the Evidence: Faithful Token Attribution Through Vision-Language Reasoning https://ax-news.com/?article=184376083 AX-NEWS en 2026-09-30T04:00:00+00:00 Are In-Context Images Worth 10 Dimensions? https://ax-news.com/?article=184376084 AX-NEWS en 2026-09-30T04:00:00+00:00 Med-RADIO: Reducing All Medical Domains Into One via Multi-Teacher Distillation https://ax-news.com/?article=184376091 AX-NEWS en 2026-09-30T04:00:00+00:00 HiRAE: Hierarchical Representation Autoencoding with Residual Budgets https://ax-news.com/?article=184376093 AX-NEWS en 2026-09-30T04:00:00+00:00 Planetary Feature Fields are Scalable Earth Representations https://ax-news.com/?article=184376094 AX-NEWS en 2026-09-30T04:00:00+00:00 CHOQOLATE: Organizing Concept Bottleneck Latent Spaces with Choquet Integrals https://ax-news.com/?article=184376100 AX-NEWS en 2026-09-30T04:00:00+00:00 Evaluation Choices Shape Biomedical ML Claims: A Pediatric Pneumonia Benchmark Case Study https://ax-news.com/?article=184376106 AX-NEWS en 2026-09-30T04:00:00+00:00 Visual Branch is What You Need for CLIP-based Class-Incremental Learning https://ax-news.com/?article=184376108 AX-NEWS en 2026-09-30T04:00:00+00:00 SYNCR: Diagnosing and Learning Cross-Video Reasoning from Simulation https://ax-news.com/?article=184376115 AX-NEWS en 2026-09-30T04:00:00+00:00 HybridCUA: Learning to Orchestrate GUI and CLI for Computer-Use Agents https://ax-news.com/?article=184376123 AX-NEWS en 2026-09-30T04:00:00+00:00 Self-Aligned Forcing: Streaming Video Diffusion with Differentiable Noisy History https://ax-news.com/?article=184376133 AX-NEWS en 2026-09-30T04:00:00+00:00 Beyond the Timeline: Augmenting Long-Video Memory with Grounded Entity Biographies https://ax-news.com/?article=184376134 AX-NEWS en 2026-09-30T04:00:00+00:00 DMA$^2$: Pixel-space Distribution Matching with Adversarial and Anchor Losses https://ax-news.com/?article=184376137 AX-NEWS en 2026-09-30T04:00:00+00:00 Adversarial Training for Pixel Diffusion https://ax-news.com/?article=184376138 AX-NEWS en 2026-09-30T04:00:00+00:00 Imagine3D-LLM: Teaching MLLMs to Imagine 3D Scenes Before Answering https://ax-news.com/?article=184376141 AX-NEWS en 2026-09-30T04:00:00+00:00 Toward a Culturally Adapted Chinese Language Agent: A Wizard-of-Oz Study of Nonverbal Behavior in Chinese-German Intercultural Interaction https://ax-news.com/?article=184376148 AX-NEWS en 2026-09-30T04:00:00+00:00 One-Step Next-Latent Prediction Is Not a World Model https://ax-news.com/?article=184376154 AX-NEWS en 2026-09-30T04:00:00+00:00 Fisher-IRG: Fisher-Induced Local Invariant Representation Geometry across Language and Vision Models https://ax-news.com/?article=184376155 AX-NEWS en 2026-09-30T04:00:00+00:00 Staircase Policy: Streaming Inference for World-Action Models with Large Action Chunks https://ax-news.com/?article=184376156 AX-NEWS en 2026-09-30T04:00:00+00:00 Similar Choices, Different Attention: Cross-Modal Associations in Humans and Vision-Language Models https://ax-news.com/?article=184376157 AX-NEWS en 2026-09-30T04:00:00+00:00 Distilling Privileged Control Barrier Functions into RGB-Only Safety Filters for Dynamic Visual Navigation https://ax-news.com/?article=184376160 AX-NEWS en 2026-09-30T04:00:00+00:00 Emergent Specialization in Populations of Self-Supervised Collaborative Vision Experts Without a Shared Gate or Cross-Agent Gradients https://ax-news.com/?article=184376173 AX-NEWS en 2026-09-30T04:00:00+00:00 Hierarchical Compression of Vision-Language Model Benchmarks https://ax-news.com/?article=184376177 AX-NEWS en 2026-09-30T04:00:00+00:00 MeanFlowAdvantage: Stable Reward Fine-Tuning for Few-Step Average-Velocity Generators https://ax-news.com/?article=184376180 AX-NEWS en 2026-09-30T04:00:00+00:00 It's Not What the Image Shows: Irrelevant Context Destabilises VLM Judges Without Informing Them https://ax-news.com/?article=184376181 AX-NEWS en 2026-09-30T04:00:00+00:00 Pixels to Keys: Exploring Spatial and Motion Cues in Gameplay Inverse Dynamics https://ax-news.com/?article=184376182 AX-NEWS en 2026-09-30T04:00:00+00:00 Video-RSI: Recursive Self-Improvement of Video Understanding Agents via Harness Evolution https://ax-news.com/?article=184376198 AX-NEWS en 2026-09-30T04:00:00+00:00 Matrix-game 2.0: An open-source, real-time, and streaming interactive world model https://ax-news.com/?article=184376200 AX-NEWS en 2026-09-30T04:00:00+00:00 Achieving detailed medial temporal lobe segmentation with upsampled isotropic training from implicit neural representation https://ax-news.com/?article=184376205 AX-NEWS en 2026-09-30T04:00:00+00:00 Think, Then Look: Active Spatial Reasoning for House-Scale 3D Scene Understanding https://ax-news.com/?article=184376207 AX-NEWS en 2026-09-30T04:00:00+00:00 Training-Free Global Geometric Association for 4D LiDAR Panoptic Segmentation https://ax-news.com/?article=184376214 AX-NEWS en 2026-09-30T04:00:00+00:00 HARMONI: Aligning Human and Scene Priors for Multi-View 4D Reconstruction https://ax-news.com/?article=184376216 AX-NEWS en 2026-09-30T04:00:00+00:00 FusionBERT: Multi-View Image--3D Retrieval via Cross-Attention Visual Fusion and Normal-Aware 3D Encoder https://ax-news.com/?article=184376217 AX-NEWS en 2026-09-30T04:00:00+00:00 Suppression Is Not Forgetting: Residual Recoverability in Visual Concept Unlearning for VLMs https://ax-news.com/?article=184376219 AX-NEWS en 2026-09-30T04:00:00+00:00 ArtifactWorld: Scaling 3D Gaussian Splatting Artifact Restoration via Video Generation Models https://ax-news.com/?article=184376224 AX-NEWS en 2026-09-30T04:00:00+00:00 Rethinking the State Update Gate for Long-Sequence Recurrent 3D Reconstruction https://ax-news.com/?article=184376231 AX-NEWS en 2026-09-30T04:00:00+00:00 Fisher-Guided Progressive Parameter Selection for Adaptive Fine-Tuning https://ax-news.com/?article=184376234 AX-NEWS en 2026-09-30T04:00:00+00:00 Do Gaussian Scenes Contain Enough Structure for Intrinsic Segmentation? https://ax-news.com/?article=184376241 AX-NEWS en 2026-09-30T04:00:00+00:00 Beacon: Knowing When and How to Perform Agentic Visual Reasoning https://ax-news.com/?article=184376242 AX-NEWS en 2026-09-30T04:00:00+00:00 SimWAM: A Simple World Action Model for End-to-End Autonomous Driving https://ax-news.com/?article=184376243 AX-NEWS en 2026-09-30T04:00:00+00:00 Gated Spatial Redundancy Projection for Pathology Transformer Attentions https://ax-news.com/?article=184376245 AX-NEWS en 2026-09-30T04:00:00+00:00 Linguistic Trajectory Encoding for Efficient Long-Horizon Spatial Memory in Embodied Agents https://ax-news.com/?article=184376247 AX-NEWS en 2026-09-30T04:00:00+00:00 CST-WM: A Causally Structured World Model for Embodied Visual Tracking https://ax-news.com/?article=184376254 AX-NEWS en 2026-09-30T04:00:00+00:00 4DGS-Fixer: Generative Sparse-View 4D Gaussian Splatting with Iterative Refinement Guided by Video Diffusion Priors https://ax-news.com/?article=184376255 AX-NEWS en 2026-09-30T04:00:00+00:00 Rethinking Vision Architectures with Gated Linear Attention and KAN https://ax-news.com/?article=184376263 AX-NEWS en 2026-09-30T04:00:00+00:00 TriO: Tri-Modal Unsupervised Occupancy World Model for Anything Perception https://ax-news.com/?article=184376264 AX-NEWS en 2026-09-30T04:00:00+00:00 EyeVQA: Benchmarking Ophthalmic Vision-Language Models from Recognition to Spatial Grounding https://ax-news.com/?article=184376265 AX-NEWS en 2026-09-30T04:00:00+00:00 Harnessing Coupled Stream Completion For Human-Object Interaction Modeling https://ax-news.com/?article=184376270 AX-NEWS en 2026-09-30T04:00:00+00:00 TT-VidT: Decoupling the Temporal Axis for Efficient Motion-Centric Video Pretraining https://ax-news.com/?article=184376272 AX-NEWS en 2026-09-30T04:00:00+00:00 PGL-3D: Towards Progressive Geometric Learning for 3D Visual Query Localization https://ax-news.com/?article=184376273 AX-NEWS en 2026-09-30T04:00:00+00:00 Natural Image Autoencoder-Based fMRI Representations for Trait and State Prediction https://ax-news.com/?article=184376280 AX-NEWS en 2026-09-30T04:00:00+00:00 LVMT: Video Mask Transformer for Long-term Video Segmentation https://ax-news.com/?article=184376284 AX-NEWS en 2026-09-30T04:00:00+00:00 GeoVerse: World-Consistent Novel View Synthesis in Geometric Latent Space https://ax-news.com/?article=184376288 AX-NEWS en 2026-09-30T04:00:00+00:00 AlignDrive: Aligned Lateral-Longitudinal Planning for End-to-End Autonomous Driving https://ax-news.com/?article=184376294 AX-NEWS en 2026-09-30T04:00:00+00:00 NoiseRater: Meta-Learned Noise Valuation for Diffusion Model Training https://ax-news.com/?article=184376295 AX-NEWS en 2026-09-30T04:00:00+00:00 SCAMP: Sparse-anchor Control is One Small Projection https://ax-news.com/?article=184376299 AX-NEWS en 2026-09-30T04:00:00+00:00 NURBS Splatting: A Unified Differentiable Rendering Framework for Vector Graphics https://ax-news.com/?article=184376304 AX-NEWS en 2026-09-30T04:00:00+00:00 Hydra: A Navigation World Action Model with Discrete Latent Planning and Continuous Flow-Matching Execution https://ax-news.com/?article=184376306 AX-NEWS en 2026-09-30T04:00:00+00:00 MeshSplatBench: A Unified Benchmark for Triangle- and Mesh-Based Neural Rendering https://ax-news.com/?article=184376311 AX-NEWS en 2026-09-30T04:00:00+00:00 Don't Throw Away the Tail: Action Upcycling for Policy Acceleration https://ax-news.com/?article=184376313 AX-NEWS en 2026-09-30T04:00:00+00:00 ChestPheNoT: Deployable, Auditable Label-Status-Evidence Extraction from Radiology Reports https://ax-news.com/?article=184376314 AX-NEWS en 2026-09-30T04:00:00+00:00 A literature-guided descriptor-based framework for filtering composition search spaces https://ax-news.com/?article=184376315 AX-NEWS en 2026-09-30T04:00:00+00:00 Distributional sentiment modeling and anomaly detection for consumer complaint assessment https://ax-news.com/?article=184376327 AX-NEWS en 2026-09-30T04:00:00+00:00 Transformer MLP Gate Thresholds Are Couplings to a Carried Reference Direction https://ax-news.com/?article=184376328 AX-NEWS en 2026-09-30T04:00:00+00:00 IndicFDB: Benchmarking Full-Duplex Voice Agents across Indian Languages https://ax-news.com/?article=184376335 AX-NEWS en 2026-09-30T04:00:00+00:00 Using LMs to Model the Effects of Context and Coreference during Sentence Comprehension https://ax-news.com/?article=184376340 AX-NEWS en 2026-09-30T04:00:00+00:00 A model of rational interlocutors: Unification of comprehension and production https://ax-news.com/?article=184376341 AX-NEWS en 2026-09-30T04:00:00+00:00 OptiArena: Can LLMs Improve Executable Algorithms under Fixed Resource Budgets? https://ax-news.com/?article=184376348 AX-NEWS en 2026-09-30T04:00:00+00:00 Language Distances are Practical for Equitable Cross-Lingual Transfer https://ax-news.com/?article=184376351 AX-NEWS en 2026-09-30T04:00:00+00:00 FA-Bench: A Benchmark for Word-Level and Phone-Level Forced-Alignment and ASR Timestamps Under Clean and Noisy Conditions https://ax-news.com/?article=184376353 AX-NEWS en 2026-09-30T04:00:00+00:00 Shared Worlds, Private Minds: Structured Memory for Long-Form Writing as World Creation https://ax-news.com/?article=184376355 AX-NEWS en 2026-09-30T04:00:00+00:00 DualGuard: Dual-Mode Quality Control for Logic-Preserving Data Augmentation https://ax-news.com/?article=184376358 AX-NEWS en 2026-09-30T04:00:00+00:00 What Should the Reflector See? An Empirical Study of Evidence in Reflective Prompt Optimization https://ax-news.com/?article=184376362 AX-NEWS en 2026-09-30T04:00:00+00:00 Explaining Textual Entailment with Lexical Entailments: Using LLMs to Supply Lexical Relations for Formal Proofs https://ax-news.com/?article=184376367 AX-NEWS en 2026-09-30T04:00:00+00:00 How to Reduce Whisper Hallucination https://ax-news.com/?article=184376370 AX-NEWS en 2026-09-30T04:00:00+00:00 KV-Lingo: Learning KV-Cache Translators with Distillation https://ax-news.com/?article=184376373 AX-NEWS en 2026-09-30T04:00:00+00:00 MixDetect: Word-Level Localization and Quantification of AI Editing https://ax-news.com/?article=184376375 AX-NEWS en 2026-09-30T04:00:00+00:00 From Knowing to Abstaining: Bridging the Representation-Action Gap in Vision-Language Models https://ax-news.com/?article=184376376 AX-NEWS en 2026-09-30T04:00:00+00:00 Focusing Condition: Inference-Time Self-Contrastive Steering Elicits Better Conditional Text Embeddings in LLMs https://ax-news.com/?article=184376386 AX-NEWS en 2026-09-30T04:00:00+00:00 TCMQA: A 38K-Question Traditional Chinese Medicine Benchmark with a Licensed-Practitioner Reference https://ax-news.com/?article=184376391 AX-NEWS en 2026-09-30T04:00:00+00:00 MedRouter: Demystifying Knowledge Differences Across Medical LLMs for Routing-Based Reasoning https://ax-news.com/?article=184376395 AX-NEWS en 2026-09-30T04:00:00+00:00 Generalization Dynamics of LM Pre-training https://ax-news.com/?article=184376397 AX-NEWS en 2026-09-30T04:00:00+00:00 Scoring the Wrong Question: Readout Failures in Constrained-Option Evaluation https://ax-news.com/?article=184376403 AX-NEWS en 2026-09-30T04:00:00+00:00 The Text Beside the Image: Detection, Utility and Leakage for Trustworthy Multimodal Medical Data and Beyond https://ax-news.com/?article=184376409 AX-NEWS en 2026-09-30T04:00:00+00:00 CHI: A Composite Hallucination Index Unifying Entity, Relation, and Quantity Dimensions for Summarization Evaluation https://ax-news.com/?article=184376410 AX-NEWS en 2026-09-30T04:00:00+00:00 Language Discrimination Improves Linguistic Learning in Multilingual Speech Models https://ax-news.com/?article=184376412 AX-NEWS en 2026-09-30T04:00:00+00:00 From Position Risks to Block Survival: Faster Generation for Diffusion Language Models https://ax-news.com/?article=184376413 AX-NEWS en 2026-09-30T04:00:00+00:00 Preserving Morphemes: Morphology-Guided Pre-Tokenization for Nepali https://ax-news.com/?article=184376417 AX-NEWS en 2026-09-30T04:00:00+00:00 MIC: Explaining Image-Claim Inconsistencies in AI-Generated Multimodal Misinformation https://ax-news.com/?article=184376421 AX-NEWS en 2026-09-30T04:00:00+00:00 DISCO: Distributed Long Context Scaling with Grounding-Reasoning Disaggregation https://ax-news.com/?article=184376423 AX-NEWS en 2026-09-30T04:00:00+00:00 E-CONAN (Entailment, CONtradition And Neutral) Diagnostics Dataset Investigating Linguistic Phenomena in Arabic Natural Language Understanding https://ax-news.com/?article=184376425 AX-NEWS en 2026-09-30T04:00:00+00:00 Jev Matches 7B Language Models for Speech-Neuroprosthesis Rescoring https://ax-news.com/?article=184376428 AX-NEWS en 2026-09-30T04:00:00+00:00 Learning to Learn from Context: Synthetic Training from Perturbed Public Documents https://ax-news.com/?article=184376432 AX-NEWS en 2026-09-30T04:00:00+00:00 Reset Is Not Recovery: Evaluating Recoverability from False Conversational Context via Sycophancy Hysteresis https://ax-news.com/?article=184376446 AX-NEWS en 2026-09-30T04:00:00+00:00 SlopBench: How Well Can We Rank Language Models by Slop? A Multi-Domain Benchmark of Repetitive AI Writing https://ax-news.com/?article=184376454 AX-NEWS en 2026-09-30T04:00:00+00:00 RewardExplainer: Learning Reward Model Explanations from Counterfactual Preference Feedback https://ax-news.com/?article=184376461 AX-NEWS en 2026-09-30T04:00:00+00:00 Quantitative Measurement of Language Distance among Closely Related Indo-European Languages Using Pretrained Language Models: A Case Study on the North Germanic Branch https://ax-news.com/?article=184376477 AX-NEWS en 2026-09-30T04:00:00+00:00 Reciprocal Guidance: Orchestrating Draft and Verify Budgets for Advancing the Diffusion-AR Self-Speculation Frontier https://ax-news.com/?article=184376480 AX-NEWS en 2026-09-30T04:00:00+00:00 Remember by Asking: Retrieval-Induced Memory Evolution for LLM Agents https://ax-news.com/?article=184376483 AX-NEWS en 2026-09-30T04:00:00+00:00 RGDT-Bench: Benchmarking LLM Reasoning for Rule-Governed Decisions and Their Justifications https://ax-news.com/?article=184376484 AX-NEWS en 2026-09-30T04:00:00+00:00 CARDAMOM: A Micro-Dialectal Arabic Speech Dataset for ASR https://ax-news.com/?article=184376486 AX-NEWS en 2026-09-30T04:00:00+00:00 RoPE is Dead, Long Live RoPE: Towards Scalable Data-aware Positional Encodings https://ax-news.com/?article=184376488 AX-NEWS en 2026-09-30T04:00:00+00:00 The Model Knows When to Stop: Training-Free Early Stopping for Long-Context Reading https://ax-news.com/?article=184376489 AX-NEWS en 2026-09-30T04:00:00+00:00 Rewarding Novel Deductions: Solver-guided Process Rewards for Logical Reasoning https://ax-news.com/?article=184376495 AX-NEWS en 2026-09-30T04:00:00+00:00 LongPuzzleBench: Evaluating GUI Agents on Long-Horizon Visual Puzzles https://ax-news.com/?article=184376499 AX-NEWS en 2026-09-30T04:00:00+00:00 Pass or Fail? Evaluating LLMs on Two Greek Examination Benchmarks https://ax-news.com/?article=184376506 AX-NEWS en 2026-09-30T04:00:00+00:00 The Right Lesson at the Right Step: Deriving Control Updates for Self-Evolving Agents https://ax-news.com/?article=184376526 AX-NEWS en 2026-09-30T04:00:00+00:00 AraDynFact: Dynamic Evaluation of Factual Knowledge in Arabic https://ax-news.com/?article=184376529 AX-NEWS en 2026-09-30T04:00:00+00:00 Beyond Token Scale: Chunk-Level Sparse Autoencoders for Reliable Semantic Feature Discovery https://ax-news.com/?article=184376532 AX-NEWS en 2026-09-30T04:00:00+00:00 FactorEngram: Factorized N-gram Memory with Basis-Level Gating for Language Models https://ax-news.com/?article=184376542 AX-NEWS en 2026-09-30T04:00:00+00:00 Improving Test-Time Scaling with Adaptive Looped Transformers https://ax-news.com/?article=184376559 AX-NEWS en 2026-09-30T04:00:00+00:00 Improving Medical Calculation of LLMs with Embedded Coding https://ax-news.com/?article=184376563 AX-NEWS en 2026-09-30T04:00:00+00:00 Amnesia by Design, Memory By Necessity: Persistent State for Document Intelligence https://ax-news.com/?article=184376565 AX-NEWS en 2026-09-30T04:00:00+00:00 On Evaluating and Improving Conversational Agents in Production https://ax-news.com/?article=184376566 AX-NEWS en 2026-09-30T04:00:00+00:00 Checking Leakage Witnesses versus Certifying Bounded Non-Leakage https://ax-news.com/?article=184376567 AX-NEWS en 2026-09-30T04:00:00+00:00 HM-ROUTER: Joint Model and Harness Routing for Agentic Systems https://ax-news.com/?article=184376576 AX-NEWS en 2026-09-30T04:00:00+00:00 Do Audio LLMs Listen Before They Act? Diagnosing Acoustic-Context Gating in Voice Agents https://ax-news.com/?article=184376578 AX-NEWS en 2026-09-30T04:00:00+00:00 Reading Is Not Leaking: Local, Auditable Measurement and Reduction of Inference Exposure from Public Footprints https://ax-news.com/?article=184376583 AX-NEWS en 2026-09-30T04:00:00+00:00 The GUI Is Not the State: Diagnosing State Aliasing in GUI World Models https://ax-news.com/?article=184376584 AX-NEWS en 2026-09-30T04:00:00+00:00 IGSD: Environment-Verified Hindsight Self-Distillation for Search Agents https://ax-news.com/?article=184376586 AX-NEWS en 2026-09-30T04:00:00+00:00 MassAlloc Attention: Let Attention Allocate Its Own Compute https://ax-news.com/?article=184376593 AX-NEWS en 2026-09-30T04:00:00+00:00 Decision-Sufficient State Representations: Measuring and Reducing Write-Time Regret https://ax-news.com/?article=184376595 AX-NEWS en 2026-09-30T04:00:00+00:00 Overwhelmed by Choice: Studying LLM Decision Making at Scale https://ax-news.com/?article=184376598 AX-NEWS en 2026-09-30T04:00:00+00:00 Multimodal LLMs Outperform Pathology Foundation Models in Cross-Domain Histological Similarity https://ax-news.com/?article=184376606 AX-NEWS en 2026-09-30T04:00:00+00:00 Save Your Saturated Data: Learning Beyond Reward Saturation in Group-Based RL https://ax-news.com/?article=184376609 AX-NEWS en 2026-09-30T04:00:00+00:00 Teach Yourself Where to Look: On-Policy Attention Self-Distillation for Reasoning https://ax-news.com/?article=184376626 AX-NEWS en 2026-09-30T04:00:00+00:00 TGRL: Temperature-Grouped Reinforcement Learning for Efficient Exploration in LLMs https://ax-news.com/?article=184376631 AX-NEWS en 2026-09-30T04:00:00+00:00 Auditing Agent Actions through Query-Conditioned Attribution https://ax-news.com/?article=184376637 AX-NEWS en 2026-09-30T04:00:00+00:00 ChemOPD: Multi-Teacher On-Policy Distillation for Multi-Task Chemical Reasoning https://ax-news.com/?article=184376639 AX-NEWS en 2026-09-30T04:00:00+00:00 Rethinking Contextualization by Reinterpreting Attention Head Channels https://ax-news.com/?article=184376640 AX-NEWS en 2026-09-30T04:00:00+00:00 Program-Verified Self-Evolution for Vision-Language Models https://ax-news.com/?article=184376646 AX-NEWS en 2026-09-30T04:00:00+00:00 RAGWarrant: Evidence-Preserving Governance for RAG Policy Promotion Under Quality, Cost, Latency, and Risk Constraints https://ax-news.com/?article=184376650 AX-NEWS en 2026-09-30T04:00:00+00:00 Loop Dropout: Regularizing Shared Updates in Looped Language Models https://ax-news.com/?article=184376651 AX-NEWS en 2026-09-30T04:00:00+00:00 When Does Selection Replace Extraction? A Pre-Registered Test of Agent Memory with a Typed Decision Model https://ax-news.com/?article=184376656 AX-NEWS en 2026-09-30T04:00:00+00:00 Knowing When Thinking Is Not Enough: Teaching Small Reasoning Models to Reason Beyond Their Parametric Knowledge https://ax-news.com/?article=184376657 AX-NEWS en 2026-09-30T04:00:00+00:00 Commutator Memory: Sparse, Path-Local Reading and Steering in Language Models https://ax-news.com/?article=184376661 AX-NEWS en 2026-09-30T04:00:00+00:00 The Last Mile Is the File: OfficeEditBench for Preservation-Aware Office Editing https://ax-news.com/?article=184376666 AX-NEWS en 2026-09-30T04:00:00+00:00 Nudgeability: Reasoning Models Follow Confidence Signals Without Tracking Their Own Competence https://ax-news.com/?article=184376671 AX-NEWS en 2026-09-30T04:00:00+00:00 When Do Model Internals Help? Exploring the Role of Representation Engineering in LLM Safety https://ax-news.com/?article=184376672 AX-NEWS en 2026-09-30T04:00:00+00:00 BV Loss: Block Verification-Aware Loss for Block Diffusion Speculative Decoding https://ax-news.com/?article=184376677 AX-NEWS en 2026-09-30T04:00:00+00:00 Sample What You Say: Aligning Language Models to Sample the Distributions They State https://ax-news.com/?article=184376679 AX-NEWS en 2026-09-30T04:00:00+00:00 See it, Say it, Sorted: Mechanistic Diagnosis and Parameter-Space Mitigation of Emergent Misalignment in LLMs https://ax-news.com/?article=184376683 AX-NEWS en 2026-09-30T04:00:00+00:00 5W1H+Which: Context-Valid Semantic Indexing with Progressive Ontology Binding https://ax-news.com/?article=184376688 AX-NEWS en 2026-09-30T04:00:00+00:00 Self-Adapting Group of Experts for Multi-Agent Reasoning https://ax-news.com/?article=184376694 AX-NEWS en 2026-09-30T04:00:00+00:00 Share-Borne AI Virus: Memory-Hopping Attacks Across LLM Agents https://ax-news.com/?article=184376699 AX-NEWS en 2026-09-30T04:00:00+00:00 SANTA++: Sampling Attention through Representative Keys https://ax-news.com/?article=184376703 AX-NEWS en 2026-09-30T04:00:00+00:00 Shockingly Simple Self-retrospection Improves Agentic Models Without RL https://ax-news.com/?article=184376705 AX-NEWS en 2026-09-30T04:00:00+00:00 LaSEr-Edit: Localized Span-level Error Editing with Energy-based Localization https://ax-news.com/?article=184376707 AX-NEWS en 2026-09-30T04:00:00+00:00 ALAS: An Automatic Latent Alignment Score for Audio Language Models https://ax-news.com/?article=184376708 AX-NEWS en 2026-09-30T04:00:00+00:00 Adaptive Activation Steering for Efficient LLM Reasoning via Closed-Loop PID Control https://ax-news.com/?article=184376711 AX-NEWS en 2026-09-30T04:00:00+00:00 Towards Inclusive Toxic Content Moderation: Addressing Vulnerabilities to Adversarial Attacks in Toxicity Classifiers Tackling LLM-generated Content https://ax-news.com/?article=184376712 AX-NEWS en 2026-09-30T04:00:00+00:00 One Model, Many Morals: Uncovering Cross-Linguistic Misalignments in Computational Moral Reasoning https://ax-news.com/?article=184376713 AX-NEWS en 2026-09-30T04:00:00+00:00 In Their Own Words: Reasoning Traces Tailored for Small Models Make Them Better Reasoners https://ax-news.com/?article=184376714 AX-NEWS en 2026-09-30T04:00:00+00:00 Test-Time Policy Adaptation for Enhanced Multi-Turn Interactions with LLMs https://ax-news.com/?article=184376715 AX-NEWS en 2026-09-30T04:00:00+00:00 Parallel Tokenizers: Rethinking Vocabulary Design in Cross-Lingual Transfer of Low-Resource Languages https://ax-news.com/?article=184376717 AX-NEWS en 2026-09-30T04:00:00+00:00 NOSA: Native and Offloadable Sparse Attention https://ax-news.com/?article=184376722 AX-NEWS en 2026-09-30T04:00:00+00:00 MAPLE: Medical Aspect-Based Summarization with Phrase-Level Evidence https://ax-news.com/?article=184376728 AX-NEWS en 2026-09-30T04:00:00+00:00 NOVA: NOise-aware Verbal Confidence CAlibration for Robust Large Language Models in RAG Systems https://ax-news.com/?article=184376734 AX-NEWS en 2026-09-30T04:00:00+00:00 OVD: On-policy Verbal Distillation https://ax-news.com/?article=184376741 AX-NEWS en 2026-09-30T04:00:00+00:00 A theoretical model of dynamical grammatical gender shifting based on set-valued set function https://ax-news.com/?article=184376742 AX-NEWS en 2026-09-30T04:00:00+00:00 SalamahBench: Dialect and Category Level Safety Evaluation of Arabic Language Models https://ax-news.com/?article=184376759 AX-NEWS en 2026-09-30T04:00:00+00:00 One Turn Too Late: Learning When to Intervene Against Multi-Turn Malicious Intent https://ax-news.com/?article=184376767 AX-NEWS en 2026-09-30T04:00:00+00:00 Where Should Diffusion Enter a Language Model? Geometry-Guided Hidden-State Replacement https://ax-news.com/?article=184376774 AX-NEWS en 2026-09-30T04:00:00+00:00 Beyond Imitation: Reflective On-Policy Self-Distillation for LLM Reasoning https://ax-news.com/?article=184376779 AX-NEWS en 2026-09-30T04:00:00+00:00 DySem: Uncovering Dynamic Semantic Components of Large Language Models for Calculating Semantic Textual Similarity https://ax-news.com/?article=184376783 AX-NEWS en 2026-09-30T04:00:00+00:00 Defending Against Malicious Finetuning by Scaling Train-time Adversarial Attacks https://ax-news.com/?article=184376803 AX-NEWS en 2026-09-30T04:00:00+00:00 SERL-SQL: Selective Hindsight Distillation for Text-to-SQL Reinforcement Agentic Learning https://ax-news.com/?article=184376804 AX-NEWS en 2026-09-30T04:00:00+00:00 Preferred, Not Safer: Pairwise Preference Is a Poor Proxy for Clinical Safety https://ax-news.com/?article=184376821 AX-NEWS en 2026-09-30T04:00:00+00:00 Verbalizing Multi-Token Concepts in LLMs https://ax-news.com/?article=184376823 AX-NEWS en 2026-09-30T04:00:00+00:00 Compression Beyond the Uncompressed: A Two-Stage Training Recipe for Soft Context Compression in RAG https://ax-news.com/?article=184376828 AX-NEWS en 2026-09-30T04:00:00+00:00 When the Wrong Key Wins: Understanding and Detecting Hallucinations in LLMs https://ax-news.com/?article=184376829 AX-NEWS en 2026-09-30T04:00:00+00:00 SlopShape: Identifying AI-Generated Commercial Web Content https://ax-news.com/?article=184376837 AX-NEWS en 2026-09-30T04:00:00+00:00 Preserving What Matters: Semantic Scaffolds Beyond Saturation in Summarization Evaluation https://ax-news.com/?article=184376854 AX-NEWS en 2026-09-30T04:00:00+00:00 MA-SAPO: Multi-Agent Reasoning for Score-Aware Prompt Optimization https://ax-news.com/?article=184376857 AX-NEWS en 2026-09-30T04:00:00+00:00 Deep Delta Learning https://ax-news.com/?article=184376860 AX-NEWS en 2026-09-30T04:00:00+00:00 Latent Chain-of-Thought as Planning: Decoupling Reasoning from Verbalization https://ax-news.com/?article=184376861 AX-NEWS en 2026-09-30T04:00:00+00:00 TSR: Trajectory-Search Rollouts for Multi-Turn RL of LLM Agents https://ax-news.com/?article=184376869 AX-NEWS en 2026-09-30T04:00:00+00:00 Relative Density Ratio Optimization for Stable and Statistically Consistent Model Alignment https://ax-news.com/?article=184376875 AX-NEWS en 2026-09-30T04:00:00+00:00 Demystifying the Unreasonable Effectiveness of Greedy Alignment Methods https://ax-news.com/?article=184376885 AX-NEWS en 2026-09-30T04:00:00+00:00 To MRL or not to MRL: Text Embeddings are Robust to Truncation Without Matryoshka Learning, Except In Heavy Truncation Scenarios https://ax-news.com/?article=184376889 AX-NEWS en 2026-09-30T04:00:00+00:00 AgentCL: Toward Rigorous Evaluation of Continual Learning in Language Agents https://ax-news.com/?article=184376892 AX-NEWS en 2026-09-30T04:00:00+00:00 Benchmarking and Exploring the Capabilities of LLMs for Attack Investigations https://ax-news.com/?article=184376895 AX-NEWS en 2026-09-30T04:00:00+00:00 Multi-Bitwidth Quantization for LLMs Using Additive Codebooks https://ax-news.com/?article=184376896 AX-NEWS en 2026-09-30T04:00:00+00:00 When Can We Trust the Sparse Lens? A Certification Framework for SAE Faithfulness https://ax-news.com/?article=184376899 AX-NEWS en 2026-09-30T04:00:00+00:00 EpiKV: Epiphany-Aware KV Cache Eviction Without the Attention Matrix https://ax-news.com/?article=184376900 AX-NEWS en 2026-09-30T04:00:00+00:00 TurnOPD: Making On-Policy Distillation Turn-Aware for Efficient Long-Horizon Agent Training https://ax-news.com/?article=184376901 AX-NEWS en 2026-09-30T04:00:00+00:00 Towards Mechanistically Understanding Why Memorized Knowledge Fails to Generalize in Large Language Model Finetuning https://ax-news.com/?article=184376904 AX-NEWS en 2026-09-30T04:00:00+00:00 How LLM Task-Adaptation Reshapes Alignment: A Multi-dimensional Study of Behavioral and Representational Drift https://ax-news.com/?article=184376906 AX-NEWS en 2026-09-30T04:00:00+00:00 dots.tts.edit: Precisely Controlled Speech Editing with a Continuous Autoregressive Model https://ax-news.com/?article=184376909 AX-NEWS en 2026-09-30T04:00:00+00:00 Which Decisions Low-Bit Quantization Breaks, and How to Predict Them https://ax-news.com/?article=184376920 AX-NEWS en 2026-09-30T04:00:00+00:00 Q2D-Web: A Large-Scale Benchmark for Retrieval in Agentic RAG Systems https://ax-news.com/?article=184376921 AX-NEWS en 2026-09-30T04:00:00+00:00 MLLMs Hallucinate when Information Distribution Drifts in Synergy Heads https://ax-news.com/?article=184376922 AX-NEWS en 2026-09-30T04:00:00+00:00 In RAG We Trust? Measuring Robustness of Retrieval-Augmented Generation Under Post-Retrieval Context Tampering https://ax-news.com/?article=184376923 AX-NEWS en 2026-09-30T04:00:00+00:00 A Dominant Supplier Slows Recursive Drift More Than It Steers It https://ax-news.com/?article=184376932 AX-NEWS en 2026-09-30T04:00:00+00:00 EnSIMem: Entity-Structured Indexing for Long-Term Agent Memory https://ax-news.com/?article=184376936 AX-NEWS en 2026-09-30T04:00:00+00:00 EEGAgentBench: Benchmarking LLM Agents on Short- and Long-Horizon EEG Analysis https://ax-news.com/?article=184376937 AX-NEWS en 2026-09-30T04:00:00+00:00 Enhancing generalization in endwall film cooling prediction: Incorporating the superposition principle into transformer-based neural operators https://ax-news.com/?article=184376940 AX-NEWS en 2026-09-30T04:00:00+00:00 Grounding Vision-Language Models in Driving Semantics: A Multi-Dataset Predicate Framework for Explainable Reasoning https://ax-news.com/?article=184376953 AX-NEWS en 2026-09-30T04:00:00+00:00 Beyond the Graph: An Adaptive Meta-Learner Fuses Explainability, Weather, and Dynamics for Robust Bus ETA Prediction https://ax-news.com/?article=184376961 AX-NEWS en 2026-09-30T04:00:00+00:00 Same Probe, Different Numbers: Are Activation Probes Robust to Inference-Time Numerical Non-Determinism? https://ax-news.com/?article=184376966 AX-NEWS en 2026-09-30T04:00:00+00:00 Deep Reinforcement Learning for Equity Trading: Benchmarking Actor-Critic Methods with Forward Retraining https://ax-news.com/?article=184376967 AX-NEWS en 2026-09-30T04:00:00+00:00 TemporalGraphLLM: Temporal Graph Neural Networks with Large Language Models for Dynamic Text-Attributed Graphs https://ax-news.com/?article=184376972 AX-NEWS en 2026-09-30T04:00:00+00:00 ROTE: Benchmarking Neural Memorization on Complexity-Controlled Symbolic Sequences https://ax-news.com/?article=184376974 AX-NEWS en 2026-09-30T04:00:00+00:00 Cache-Aware Conv3D Lowering Across Embedded World-Model Decoders https://ax-news.com/?article=184376990 AX-NEWS en 2026-09-30T04:00:00+00:00 Depth Laws for the Precision Floor of Trained Neural Networks: Amplification, Residual Scaling, and a Quantization-Aware Training Paradox https://ax-news.com/?article=184376991 AX-NEWS en 2026-09-30T04:00:00+00:00 When Should a Human Take Back Control? Optimal Delegation under Turbulent AI Risk https://ax-news.com/?article=184376999 AX-NEWS en 2026-09-30T04:00:00+00:00 Latency-Aware Client Assignment for Parallel Split Learning With Global Sampling https://ax-news.com/?article=184377004 AX-NEWS en 2026-09-30T04:00:00+00:00 Uncertainty-Aware Selection of Online Algorithms with Simulator Ensembles https://ax-news.com/?article=184377007 AX-NEWS en 2026-09-30T04:00:00+00:00 Rethinking Cross-Channel Importance in Time-Series Forecasting https://ax-news.com/?article=184377008 AX-NEWS en 2026-09-30T04:00:00+00:00 HM-ROUTER: Joint Model and Harness Routing for Agentic Systems https://ax-news.com/?article=184377009 AX-NEWS en 2026-09-30T04:00:00+00:00 DP-Rec: Towards Dynamic Patching for Efficient Long-Sequence Recommendation https://ax-news.com/?article=184377011 AX-NEWS en 2026-09-30T04:00:00+00:00 "Where Can I Trust You?": Boundary-Aware Evaluation of Surrogate Fidelity https://ax-news.com/?article=184377013 AX-NEWS en 2026-09-30T04:00:00+00:00 Anytime-Valid LLM Leaderboards via Benchmark-weighted and Block-Factorized e-Processes https://ax-news.com/?article=184377019 AX-NEWS en 2026-09-30T04:00:00+00:00 Topology-Adaptive Hyperbolic Graph Attention Networks Guided by the Hyperbolic Sombor Index https://ax-news.com/?article=184377020 AX-NEWS en 2026-09-30T04:00:00+00:00 HyperLabel: Multi-Label Classification via Hypergraph-Based Label Correlation Modeling https://ax-news.com/?article=184377024 AX-NEWS en 2026-09-30T04:00:00+00:00 FUND: Density Flow for Sampling Unnormalised Distributions https://ax-news.com/?article=184377025 AX-NEWS en 2026-09-30T04:00:00+00:00 Refresh or Realize? Compute Allocation in Drifting Models https://ax-news.com/?article=184377026 AX-NEWS en 2026-09-30T04:00:00+00:00 When Does Synergy Help Active Feature Acquisition? A PID-Based Study https://ax-news.com/?article=184377028 AX-NEWS en 2026-09-30T04:00:00+00:00 What Can a Leaderboard Certify? Compositional Controllability for Fair Evaluation and Training of Biomedical Literature-Review Agents https://ax-news.com/?article=184377036 AX-NEWS en 2026-09-30T04:00:00+00:00 Analog-Friendly Predictive Coding without Activation Derivatives https://ax-news.com/?article=184377037 AX-NEWS en 2026-09-30T04:00:00+00:00 Editable Map-Conditioned Trajectory Generation for Human Mobility Simulation https://ax-news.com/?article=184377039 AX-NEWS en 2026-09-30T04:00:00+00:00 DiffPTS: Rethinking Diffusion ELBO for Probabilistic Time Series Forecasting https://ax-news.com/?article=184377057 AX-NEWS en 2026-09-30T04:00:00+00:00 What Should Federated LoRA Share? FedSAIL via Input-aware Subspace Alignment https://ax-news.com/?article=184377058 AX-NEWS en 2026-09-30T04:00:00+00:00 Elastic Selective Spectral Hybrids for Train-Once, Export-Many Budgeted Inference https://ax-news.com/?article=184377071 AX-NEWS en 2026-09-30T04:00:00+00:00 Trapped by Their Own Rollouts: Understanding Aggregation--Rollout Feedback in Federated On-Policy Distillation https://ax-news.com/?article=184377075 AX-NEWS en 2026-09-30T04:00:00+00:00 AnchorRep: Defending LLMs Against Cross-Model Adversarial Transfer via Representation Repulsion https://ax-news.com/?article=184377082 AX-NEWS en 2026-09-30T04:00:00+00:00 Distance-KV: Exploiting Relative Distance for Efficient Long-Context Inference https://ax-news.com/?article=184377085 AX-NEWS en 2026-09-30T04:00:00+00:00 SIFT: Enhancing Time Series Foundation Models via Semantic Invariance and Structural Fidelity Fine-Tuning https://ax-news.com/?article=184377091 AX-NEWS en 2026-09-30T04:00:00+00:00 Predicting the Financial Impact of Supply Chain Risk for Major AI-Related Semiconductor Firms: A Heterogeneous Graph Patch Transformer Approach https://ax-news.com/?article=184377095 AX-NEWS en 2026-09-30T04:00:00+00:00 AnchorMixGAN: Anchor-Aligned Generative Semi-Supervision for DDoS Detection in Cloud-Integrated IoT Networks https://ax-news.com/?article=184377096 AX-NEWS en 2026-09-30T04:00:00+00:00 Structuring Relations Among Learning Paradigms via Protocol--Objective--Resource Reductions https://ax-news.com/?article=184377097 AX-NEWS en 2026-09-30T04:00:00+00:00 Continual Learning via Self-Probe Gradients https://ax-news.com/?article=184377103 AX-NEWS en 2026-09-30T04:00:00+00:00 Understanding and Exploiting Anisotropy in Post-Training https://ax-news.com/?article=184377104 AX-NEWS en 2026-09-30T04:00:00+00:00 Derivative-Informed Training of Neural Operators On-the-Fly via Sketched Tangent Consistency https://ax-news.com/?article=184377106 AX-NEWS en 2026-09-30T04:00:00+00:00 Change the Product, Keep the Parameters: Associative Algebra Layers for Transformers https://ax-news.com/?article=184377109 AX-NEWS en 2026-09-30T04:00:00+00:00 Over-the-Air Federated Learning in Heterogeneous Mobile Wireless Networks https://ax-news.com/?article=184377114 AX-NEWS en 2026-09-30T04:00:00+00:00 Muon Under Gradient Noise and the Limits of Orthogonalization Near Optima https://ax-news.com/?article=184377115 AX-NEWS en 2026-09-30T04:00:00+00:00 Staying on the Attractor: Supervising Neural Surrogates of 3D Turbulence Where They Leave It https://ax-news.com/?article=184377118 AX-NEWS en 2026-09-30T04:00:00+00:00 A Function-Level Vulnerability Score Measures Flag Rate More Than the Model: Protocol Effects on Paired Benchmarks https://ax-news.com/?article=184377119 AX-NEWS en 2026-09-30T04:00:00+00:00 Optimizing H-Graph Hybridization for Diffusion-Guided RRT https://ax-news.com/?article=184377122 AX-NEWS en 2026-09-30T04:00:00+00:00 Allspark: Weak to Strong Transfer via Alternating Chain of Thought https://ax-news.com/?article=184377123 AX-NEWS en 2026-09-30T04:00:00+00:00 Adaptive Latent Capacity for World Models https://ax-news.com/?article=184377126 AX-NEWS en 2026-09-30T04:00:00+00:00 Efficient Dynamic Algorithms for Graph Neural Networks with Non-Linear Propagation https://ax-news.com/?article=184377127 AX-NEWS en 2026-09-30T04:00:00+00:00 Counting on Thinking: Tracing Evidence Integration in Language Models https://ax-news.com/?article=184377131 AX-NEWS en 2026-09-30T04:00:00+00:00 TwinS-GCN: Spectral conjugate for Spectral Graph Convolutional Networks https://ax-news.com/?article=184377138 AX-NEWS en 2026-09-30T04:00:00+00:00 Self-Confirming Superposition Traps in Reinforcement Learning https://ax-news.com/?article=184377147 AX-NEWS en 2026-09-30T04:00:00+00:00 Balancing Early Performance Sacrifices with Long-Term Gains: Scaling Learning-Rate Warmup Duration Across Training Horizons https://ax-news.com/?article=184377150 AX-NEWS en 2026-09-30T04:00:00+00:00 SketchSSM: Write to the Full State, Read from a Compact Sketch https://ax-news.com/?article=184377151 AX-NEWS en 2026-09-30T04:00:00+00:00 Deep Learning Techniques for Phoneme Recognition in Italian Children' s Speech https://ax-news.com/?article=184377153 AX-NEWS en 2026-09-30T04:00:00+00:00 Algorithmic Harms Associated with Generative Model-Augmented Recommendation Systems https://ax-news.com/?article=184377163 AX-NEWS en 2026-09-30T04:00:00+00:00 Mycelium: A Generalizable Cross-Grid Multi-Task Model for Electrical Distribution Systems https://ax-news.com/?article=184377169 AX-NEWS en 2026-09-30T04:00:00+00:00 Beyond the Training Horizon: Mechanisms and Limits of Length Generalization in Looped Transformers https://ax-news.com/?article=184377182 AX-NEWS en 2026-09-30T04:00:00+00:00 RMB: Reward Model Boosting Mitigates Reward Hacking https://ax-news.com/?article=184377183 AX-NEWS en 2026-09-30T04:00:00+00:00 MTLiquid: Enabling Efficient Multi-Task Learning using Liquid Neural Networks for Lightweight Healthcare Monitoring Systems https://ax-news.com/?article=184377186 AX-NEWS en 2026-09-30T04:00:00+00:00 Feedback-Robust AI for Patient Knowledge Graphs https://ax-news.com/?article=184377187 AX-NEWS en 2026-09-30T04:00:00+00:00 BERT4DTI : BERT-based Model for Predicting Drug-Protein Interactions https://ax-news.com/?article=184377194 AX-NEWS en 2026-09-30T04:00:00+00:00 ZeroGAR: Benchmarking the Adversarial Robustness of Zero-Shot Graph Models https://ax-news.com/?article=184377197 AX-NEWS en 2026-09-30T04:00:00+00:00 Safe Score Matching: Diffusion Policies with Hamilton-Jacobi Reachability for Online Safe Reinforcement Learning https://ax-news.com/?article=184377202 AX-NEWS en 2026-09-30T04:00:00+00:00 How Much Imprecision is Enough Imprecision in my Classifier? A Practical Elicitation Procedure https://ax-news.com/?article=184377205 AX-NEWS en 2026-09-30T04:00:00+00:00 Optimal Transport Dropout for Structured Predictive Uncertainty https://ax-news.com/?article=184377207 AX-NEWS en 2026-09-30T04:00:00+00:00 Beyond Timestamps: Decision-Aligned On-Policy Distillation for Long-Horizon Agents https://ax-news.com/?article=184377215 AX-NEWS en 2026-09-30T04:00:00+00:00 SchemaMem: Schema-Indexed Recurrent Memory for Delayed State Retrieval https://ax-news.com/?article=184377217 AX-NEWS en 2026-09-30T04:00:00+00:00 Elucidating the Design Space of Regression-based Diffusion Reinforcement Learning https://ax-news.com/?article=184377219 AX-NEWS en 2026-09-30T04:00:00+00:00 A Cheap Verifier is Good Enough: LLM Post-training is Robust to Erroneous Rewards https://ax-news.com/?article=184377228 AX-NEWS en 2026-09-30T04:00:00+00:00 Source Anchoring for Physical Consistency in Flow Matching Models https://ax-news.com/?article=184377230 AX-NEWS en 2026-09-30T04:00:00+00:00 LLM4Trust: Exploring the Capabilities of Large Language Models for Trust Evaluation https://ax-news.com/?article=184377231 AX-NEWS en 2026-09-30T04:00:00+00:00 Discovering Symmetries in Neural Network Parameter Spaces https://ax-news.com/?article=184377236 AX-NEWS en 2026-09-30T04:00:00+00:00 OOD Generalization as a Bifurcation Problem https://ax-news.com/?article=184377237 AX-NEWS en 2026-09-30T04:00:00+00:00 MA-JEPA: Joint-Embedding World Models for Multi-Agent Reinforcement Learning https://ax-news.com/?article=184377239 AX-NEWS en 2026-09-30T04:00:00+00:00 HiLoRe: What to Store, Compress, or Recompute for Efficient GRPO Training https://ax-news.com/?article=184377240 AX-NEWS en 2026-09-30T04:00:00+00:00 Compressing Value Predictions for Learning-Augmented Metrical Task Systems https://ax-news.com/?article=184377241 AX-NEWS en 2026-09-30T04:00:00+00:00 Approximating Softmax in Pretrained LLMs: Model Sensitivity and Kernel Acceleration https://ax-news.com/?article=184377242 AX-NEWS en 2026-09-30T04:00:00+00:00 TGRL: Temperature-Grouped Reinforcement Learning for Efficient Exploration in LLMs https://ax-news.com/?article=184377261 AX-NEWS en 2026-09-30T04:00:00+00:00 DuoOPD: Learning from Joint Teacher-Student Outcomes for Multi-Task On-Policy Distillation https://ax-news.com/?article=184377264 AX-NEWS en 2026-09-30T04:00:00+00:00 ALDER: Discovering the Laws of a World by Acting in It https://ax-news.com/?article=184377271 AX-NEWS en 2026-09-30T04:00:00+00:00 Beyond Fixed Features: Architecture-Dependent Sensitivity to Node Representations under Heterophily https://ax-news.com/?article=184377273 AX-NEWS en 2026-09-30T04:00:00+00:00 Selecting Diverse SFT Traces Improves Post-RL Generalization https://ax-news.com/?article=184377280 AX-NEWS en 2026-09-30T04:00:00+00:00 ChemOPD: Multi-Teacher On-Policy Distillation for Multi-Task Chemical Reasoning https://ax-news.com/?article=184377293 AX-NEWS en 2026-09-30T04:00:00+00:00 Training Witnesses: Trusting the Training without Trusting the Trainer https://ax-news.com/?article=184377306 AX-NEWS en 2026-09-30T04:00:00+00:00 Fisher-Informed Recalibration for Feedback-Based On-Policy Self-Distillation of LLMs https://ax-news.com/?article=184377317 AX-NEWS en 2026-09-30T04:00:00+00:00 KVCMAS: Efficient KV cache Correction for Shared Context in Multi-Agent Systems https://ax-news.com/?article=184377318 AX-NEWS en 2026-09-30T04:00:00+00:00 Counterexamples to Local Reconstruction Gain as a Proxy for Final Fidelity in Residual Completion https://ax-news.com/?article=184377323 AX-NEWS en 2026-09-30T04:00:00+00:00 TRACE: Expert-Aligned ECG Representation Learning with Rigorous Benchmarking and Real-World Validation in Acute Cardiac Care https://ax-news.com/?article=184377341 AX-NEWS en 2026-09-30T04:00:00+00:00 Learning to Optimize through Solver-Grounded Self-Play https://ax-news.com/?article=184377359 AX-NEWS en 2026-09-30T04:00:00+00:00 Commutator Memory: Sparse, Path-Local Reading and Steering in Language Models https://ax-news.com/?article=184377361 AX-NEWS en 2026-09-30T04:00:00+00:00 FORGE: Form-Optimal Routing of Grounded Evidence for Frozen LLM Agents https://ax-news.com/?article=184377365 AX-NEWS en 2026-09-30T04:00:00+00:00 LRC-JEPA: Disentangling Dynamics and Residual Context for Efficient World Models https://ax-news.com/?article=184377377 AX-NEWS en 2026-09-30T04:00:00+00:00 Making LLMs Truly Forget: Deep Unlearning by Searching, Selecting, and Severing Knowledge Paths https://ax-news.com/?article=184377379 AX-NEWS en 2026-09-30T04:00:00+00:00 SPACE-LoRA: Allocating Activation-Subspace Protection for Continual Learning https://ax-news.com/?article=184377383 AX-NEWS en 2026-09-30T04:00:00+00:00 Deep kernel hedging https://ax-news.com/?article=184377384 AX-NEWS en 2026-09-30T04:00:00+00:00 Causal Routing for Unlearning https://ax-news.com/?article=184377385 AX-NEWS en 2026-09-30T04:00:00+00:00 Learn Here, Move Less Elsewhere: Input-Conditioned Plasticity from Retained-Domain Activation Atlases https://ax-news.com/?article=184377387 AX-NEWS en 2026-09-30T04:00:00+00:00 When Less Data Favors Smaller Teachers: Rethinking Teacher Capacity and Data Selection for Knowledge Distillation https://ax-news.com/?article=184377388 AX-NEWS en 2026-09-30T04:00:00+00:00 M3OS: A Monte Carlo Graph Search-Orchestrated Multi-Agent LLM System for Evidence-Traced Molecular Optimization https://ax-news.com/?article=184377398 AX-NEWS en 2026-09-30T04:00:00+00:00 Verifying Neural Networks with Reinforcement Learning https://ax-news.com/?article=184377406 AX-NEWS en 2026-09-30T04:00:00+00:00 When local gains fail to transfer: Frozen Earth-observation embeddings across wildfires https://ax-news.com/?article=184377412 AX-NEWS en 2026-09-30T04:00:00+00:00 DisKO: Deep Koopman Learning in Distribution Space from Unpaired Snapshots https://ax-news.com/?article=184377426 AX-NEWS en 2026-09-30T04:00:00+00:00 Predicting Delayed Train Trajectories on the Dutch Railway Network: Explainable AI Evaluation of Topological, Operational and Weather Features with Tree Based Ensemble Methods https://ax-news.com/?article=184377431 AX-NEWS en 2026-09-30T04:00:00+00:00 No Pain, More Gain: Iterative Merging for Effective Multi-Teacher On-Policy Distillation https://ax-news.com/?article=184377432 AX-NEWS en 2026-09-30T04:00:00+00:00 A Unifying Framework of Concept-based Explainable AI with Completeness Guarantees https://ax-news.com/?article=184377454 AX-NEWS en 2026-09-30T04:00:00+00:00 ALICE: In-context, Zero-shot, Mutual Information Estimation https://ax-news.com/?article=184377456 AX-NEWS en 2026-09-30T04:00:00+00:00 See it, Say it, Sorted: Mechanistic Diagnosis and Parameter-Space Mitigation of Emergent Misalignment in LLMs https://ax-news.com/?article=184377464 AX-NEWS en 2026-09-30T04:00:00+00:00 VEX-Bench: Benchmarking Verification Complexity of LLM-Generated Misinformation https://ax-news.com/?article=184377467 AX-NEWS en 2026-09-30T04:00:00+00:00 BA-DPO: Bias-Adjusted Direct Preference Optimization for Language Model Alignment https://ax-news.com/?article=184377469 AX-NEWS en 2026-09-30T04:00:00+00:00 TIDE: Teacher-Student Transition via Informative Distillation and Exploration for Agentic RL https://ax-news.com/?article=184377477 AX-NEWS en 2026-09-30T04:00:00+00:00 GraphHCA: Closed-Form Hindsight Credit Assignment for Long-Horizon LLM Agents https://ax-news.com/?article=184377482 AX-NEWS en 2026-09-30T04:00:00+00:00 SymbolicArena: A Unified Infrastructure for Benchmark Distillation and Dynamic Evaluation in Symbolic Regression https://ax-news.com/?article=184377494 AX-NEWS en 2026-09-30T04:00:00+00:00 ConRAG: Lightweight inference of multi-hop relations https://ax-news.com/?article=184377498 AX-NEWS en 2026-09-30T04:00:00+00:00 Long-Horizon Scaling: How Model Capabilities Shape the Returns to Computation https://ax-news.com/?article=184377508 AX-NEWS en 2026-09-30T04:00:00+00:00 LionMuon: Alternating Spectral and Sign Descent for Efficient Training https://ax-news.com/?article=184377509 AX-NEWS en 2026-09-30T04:00:00+00:00 When Should a Satellite Estimate Be Changed? Stress-Testing Neural Corrections for Evapotranspiration https://ax-news.com/?article=184377520 AX-NEWS en 2026-09-30T04:00:00+00:00 Fiona: Accelerating FHE Inference with Packing-Aware Ternary Weights https://ax-news.com/?article=184377527 AX-NEWS en 2026-09-30T04:00:00+00:00 Persistent Partners Raise Prices Among Learning Agents https://ax-news.com/?article=184377530 AX-NEWS en 2026-09-30T04:00:00+00:00 ReSPO: Reshaped Sequence Policy Optimization for Gradient Starvation in Off-Policy Learning https://ax-news.com/?article=184377531 AX-NEWS en 2026-09-30T04:00:00+00:00 SOLO: Pretraining Billion-Parameter Language Models with Shared-Output Local Learning https://ax-news.com/?article=184377535 AX-NEWS en 2026-09-30T04:00:00+00:00 CLIMB: A Clinical Multimorbidity Benchmark for Diagnosing Co-occurring Conditions through Multiturn Conversations https://ax-news.com/?article=184377537 AX-NEWS en 2026-09-30T04:00:00+00:00 An analysis of Mirror-Descent Soft Actor-Critic https://ax-news.com/?article=184377551 AX-NEWS en 2026-09-30T04:00:00+00:00 Simplex Diffusion Models https://ax-news.com/?article=184377553 AX-NEWS en 2026-09-30T04:00:00+00:00 Output-aware Residual Stream Pruning for Large Language Models https://ax-news.com/?article=184377567 AX-NEWS en 2026-09-30T04:00:00+00:00 Rethinking Personalized Generation: Test-Time Alignment via Factorized Ranking Models https://ax-news.com/?article=184377573 AX-NEWS en 2026-09-30T04:00:00+00:00 X-Reset: Scaling Object-Centric Reinforcement Learning via Cross-Embodiment Resets https://ax-news.com/?article=184377579 AX-NEWS en 2026-09-30T04:00:00+00:00 Kolmogorov-Arnold networks in nuclear binding energy prediction https://ax-news.com/?article=184377582 AX-NEWS en 2026-09-30T04:00:00+00:00 FUSION: a skill-based research agent for publicly obtainable nuclear-physics codes https://ax-news.com/?article=184377584 AX-NEWS en 2026-09-30T04:00:00+00:00 ChestPheNoT: Deployable, Auditable Label-Status-Evidence Extraction from Radiology Reports https://ax-news.com/?article=184377589 AX-NEWS en 2026-09-30T04:00:00+00:00 Cross-Dataset Transfer and Unknown-Class Detection in Imbalanced SAR Ship Classification https://ax-news.com/?article=184377593 AX-NEWS en 2026-09-30T04:00:00+00:00 Data Processing for Offline Evaluation in Recommender Systems: a Survey https://ax-news.com/?article=184377616 AX-NEWS en 2026-09-30T04:00:00+00:00 CaptchaArena: A Large-Scale, Fine-Grained Dataset for Training Computer-Use Agents on Interactive CAPTCHAs https://ax-news.com/?article=184377618 AX-NEWS en 2026-09-30T04:00:00+00:00 Bridging Stochastic Flow Maps and Boltzmann Generators with Normalizing Flows https://ax-news.com/?article=184377620 AX-NEWS en 2026-09-30T04:00:00+00:00 Communication between Frozen Large Language Models via Prompt Optimization in a Referential Game https://ax-news.com/?article=184377622 AX-NEWS en 2026-09-30T04:00:00+00:00 What Does the Rank Buy? A Spectral and Distributional Analysis of Low-Rank Adaptation https://ax-news.com/?article=184377627 AX-NEWS en 2026-09-30T04:00:00+00:00 A Unified Optimism-Agnostic Framework for Linear Bandits over Spherical Action Sets https://ax-news.com/?article=184377630 AX-NEWS en 2026-09-30T04:00:00+00:00 Uncertainty Quantification of Next Generation Reservoir Computing with Applications to Memory-Driven Dynamical Systems https://ax-news.com/?article=184377634 AX-NEWS en 2026-09-30T04:00:00+00:00 SparSP: Exploiting Communication Sparsity for Sequence-Parallel Video DiTs https://ax-news.com/?article=184377636 AX-NEWS en 2026-09-30T04:00:00+00:00 Kernel-Based Steering of CLIP with Vision-Language Model Preferences https://ax-news.com/?article=184377638 AX-NEWS en 2026-09-30T04:00:00+00:00 Federated Subspace Guided Vision-Language-Action Policy Distillation for Non-IID Multi-Robot Manipulation https://ax-news.com/?article=184377653 AX-NEWS en 2026-09-30T04:00:00+00:00 Memory as a cache: Exact context reuse and deletion by construction https://ax-news.com/?article=184377657 AX-NEWS en 2026-09-30T04:00:00+00:00 Controllable GNN Explanations via Multi-Metric Preference Selection https://ax-news.com/?article=184377658 AX-NEWS en 2026-09-30T04:00:00+00:00 Masking Frequent Tokens Sharpens Direct Preference Optimization https://ax-news.com/?article=184377673 AX-NEWS en 2026-09-30T04:00:00+00:00 In-Flight KV Cache with Clean Anchors for Faster Autoregressive Video Diffusion https://ax-news.com/?article=184377681 AX-NEWS en 2026-09-30T04:00:00+00:00 Schur-Neural KF: Learned Schur-Consistent Corrections to the Extended Kalman Filter https://ax-news.com/?article=184377683 AX-NEWS en 2026-09-30T04:00:00+00:00 MixBench-TS: A Multivariate Time Series Forecasting Benchmark Where Channel Mixing Pays Off https://ax-news.com/?article=184377685 AX-NEWS en 2026-09-30T04:00:00+00:00 When Better Gets Worse: Improvement Fidelity for Self-Improving Agents in Adaptive Worlds https://ax-news.com/?article=184377690 AX-NEWS en 2026-09-30T04:00:00+00:00 One-Step Generative Modeling via Unbalanced Optimal Transport https://ax-news.com/?article=184377693 AX-NEWS en 2026-09-30T04:00:00+00:00 Plan-to-Synthesis: Cross-City Human Mobility Generation via Semantic Latent Flow Matching https://ax-news.com/?article=184377706 AX-NEWS en 2026-09-30T04:00:00+00:00 Re-derivability Decides What a Staged Agent Pipeline Recovers After an Upstream Fault https://ax-news.com/?article=184377709 AX-NEWS en 2026-09-30T04:00:00+00:00 USAI-Quant: A Quantitative Reasoning Benchmark for Vision-Language Models in Built Environments https://ax-news.com/?article=184377718 AX-NEWS en 2026-09-30T04:00:00+00:00 Is H＆E Image-to-Spatial Transcriptomics Simpler Than It Looks? https://ax-news.com/?article=184377721 AX-NEWS en 2026-09-30T04:00:00+00:00 Multimodal LLMs Outperform Pathology Foundation Models in Cross-Domain Histological Similarity https://ax-news.com/?article=184377724 AX-NEWS en 2026-09-30T04:00:00+00:00 The Key Handoff: Retrieval in Hybrid Language Models https://ax-news.com/?article=184377726 AX-NEWS en 2026-09-30T04:00:00+00:00 CAPEX: Efficiently Distilling Foundation Model Behavior into Deployable Robot Policies through Experience-Adaptive Reasoning https://ax-news.com/?article=184377728 AX-NEWS en 2026-09-30T04:00:00+00:00 Byzantine-Robust Federated RAG via Aligned Calibration and Fixed-Membership Conformal Prediction https://ax-news.com/?article=184377733 AX-NEWS en 2026-09-30T04:00:00+00:00 Evolving Dexterous Robots from Scratch https://ax-news.com/?article=184377738 AX-NEWS en 2026-09-30T04:00:00+00:00 Dynamic Manipulation with World-Action Models via Counterfactual Planning https://ax-news.com/?article=184377740 AX-NEWS en 2026-09-30T04:00:00+00:00 Which Self-Improvements Should We Trust? Reliable Self-Improvement When Agents Reuse Their Benchmarks https://ax-news.com/?article=184377741 AX-NEWS en 2026-09-30T04:00:00+00:00 Identifying Temporal Features within Transcoders for Time Sensitive Factual Recall https://ax-news.com/?article=184377742 AX-NEWS en 2026-09-30T04:00:00+00:00 Offline Policy Evaluation via Mixed Bellman Residuals and Adaptive Critic Representations https://ax-news.com/?article=184377745 AX-NEWS en 2026-09-30T04:00:00+00:00 Schr\"odinger--F\"ollmer Actor--Critic: Diffusion Policy Improvement with Finite-Sample Analysis https://ax-news.com/?article=184377747 AX-NEWS en 2026-09-30T04:00:00+00:00 Modelling non-linear aeroelastic loads in long-span bridges with extreme learning machines https://ax-news.com/?article=184377748 AX-NEWS en 2026-09-30T04:00:00+00:00 The Statistical Benefits of Multiple Responses for Learning from Demonstrations https://ax-news.com/?article=184377756 AX-NEWS en 2026-09-30T04:00:00+00:00 Recursive Harness Distillation across Agents for Robot Manipulation https://ax-news.com/?article=184377761 AX-NEWS en 2026-09-30T04:00:00+00:00 Sharp training-conditional coverage for conformal prediction under covariate shift https://ax-news.com/?article=184377769 AX-NEWS en 2026-09-30T04:00:00+00:00 Sparsity by Default: The Theory and Practice of ARD in Gaussian Process Regression for Variable Selection https://ax-news.com/?article=184377780 AX-NEWS en 2026-09-30T04:00:00+00:00 TopoMamba: A Load-Support Relation-Guided Multi-Directional State-Space Model for Topology Optimization https://ax-news.com/?article=184377789 AX-NEWS en 2026-09-30T04:00:00+00:00 Positions Are Not Facts: The Mismatch Between KV Caches and Memory https://ax-news.com/?article=184377790 AX-NEWS en 2026-09-30T04:00:00+00:00 EfficientAgent: What Makes KV Cache Offloading Work for Concurrent Agents? https://ax-news.com/?article=184377793 AX-NEWS en 2026-09-30T04:00:00+00:00 RAISE: Reinforcing Access Control Policy Synthesis in LLMs via Symbolic Evaluation https://ax-news.com/?article=184377807 AX-NEWS en 2026-09-30T04:00:00+00:00 Curating Merchant-Matching Training Data with Two Confidence-Gated Local LLM Judges https://ax-news.com/?article=184377810 AX-NEWS en 2026-09-30T04:00:00+00:00 Prospective Interpretation Risk: Principled Communication Control Between LLMs https://ax-news.com/?article=184377812 AX-NEWS en 2026-09-30T04:00:00+00:00 Residual-Stream Burden Shapes Representation Learning in Diffusion Transformers https://ax-news.com/?article=184377817 AX-NEWS en 2026-09-30T04:00:00+00:00 ThinkNet: Compact Architecture Selection and Validation-Gated Ensembles for Subject-Independent MI-EEG Decoding https://ax-news.com/?article=184377820 AX-NEWS en 2026-09-30T04:00:00+00:00 Adapting neural operators for mechanics decisions under changing operating conditions https://ax-news.com/?article=184377821 AX-NEWS en 2026-09-30T04:00:00+00:00 High-Level Text Preprocessing for Semantic Similarity Analysis of Discursive Texts: A Framework and Empirical Demonstration https://ax-news.com/?article=184377828 AX-NEWS en 2026-09-30T04:00:00+00:00 Singularities of Non-negative Matrix Factorization and their application to Bayesian inference https://ax-news.com/?article=184377829 AX-NEWS en 2026-09-30T04:00:00+00:00 Kafila: Serving Large Language Models on a Trusted Set of Heterogeneous Commodity Machines https://ax-news.com/?article=184377832 AX-NEWS en 2026-09-30T04:00:00+00:00 The Double-Edged Sword of Information: Revealed versus Hidden Lotteries in School Choice https://ax-news.com/?article=184377839 AX-NEWS en 2026-09-30T04:00:00+00:00 AlphaPareto: Formulaic Alpha Discovery with LLM-Guided Multi-Objective Reinforcement Learning https://ax-news.com/?article=184377847 AX-NEWS en 2026-09-30T04:00:00+00:00 Query Expansion and Key Specialization in Transformer Attention Geometry https://ax-news.com/?article=184377849 AX-NEWS en 2026-09-30T04:00:00+00:00 Dexterous Tactile World Model https://ax-news.com/?article=184377852 AX-NEWS en 2026-09-30T04:00:00+00:00 Predictive Semantic Safety: From Visual Physical Reasoning to Safety-Critical Control https://ax-news.com/?article=184377854 AX-NEWS en 2026-09-30T04:00:00+00:00 Look Before You Select: Rethinking Vocabulary Sparsification in On-Policy Distillation https://ax-news.com/?article=184377855 AX-NEWS en 2026-09-30T04:00:00+00:00 P2P: Cross-View Population Denoising for Unpaired Single-Cell Perturbation Response Prediction https://ax-news.com/?article=184377856 AX-NEWS en 2026-09-30T04:00:00+00:00 Unbiased Top-$k$ Estimation for On-Policy Distillation https://ax-news.com/?article=184377858 AX-NEWS en 2026-09-30T04:00:00+00:00 When Does Structured Knowledge Help Neural Theorem Proving? https://ax-news.com/?article=184377863 AX-NEWS en 2026-09-30T04:00:00+00:00 Nudgeability: Reasoning Models Follow Confidence Signals Without Tracking Their Own Competence https://ax-news.com/?article=184377867 AX-NEWS en 2026-09-30T04:00:00+00:00 Probabilistic Geodesic Flow Matching on Location-Scale Families https://ax-news.com/?article=184377876 AX-NEWS en 2026-09-30T04:00:00+00:00 SeLMRoute: Probabilistic Semantic Evidence for Large Language Model Routing https://ax-news.com/?article=184377883 AX-NEWS en 2026-09-30T04:00:00+00:00 Finite-Time Concentration and Convergence Rates for Projected Two-Time-Scale Stochastic Approximation with Markov Noise https://ax-news.com/?article=184377884 AX-NEWS en 2026-09-30T04:00:00+00:00 Physics-Attested Federated Learning: Securing Collaborative Anomaly Detection in Critical Water Infrastructure https://ax-news.com/?article=184377887 AX-NEWS en 2026-09-30T04:00:00+00:00 Accelerator Choice Is Not Enough: AlphaFold2 Inference on Cloud TPUs https://ax-news.com/?article=184377889 AX-NEWS en 2026-09-30T04:00:00+00:00 From Soft Targets to Reward Signals: How Assignment and Reward Objectives Interact https://ax-news.com/?article=184377893 AX-NEWS en 2026-09-30T04:00:00+00:00 Don't Throw Away the Tail: Action Upcycling for Policy Acceleration https://ax-news.com/?article=184377902 AX-NEWS en 2026-09-30T04:00:00+00:00 Graph-Based Learning for Multi-Horizon Martian Atmospheric Forecasting https://ax-news.com/?article=184377906 AX-NEWS en 2026-09-30T04:00:00+00:00 Continuous Variational Synthesis https://ax-news.com/?article=184377913 AX-NEWS en 2026-09-30T04:00:00+00:00 A Hierarchy of Entropy-Shapley Games for Multivariate Predictive Uncertainty https://ax-news.com/?article=184377919 AX-NEWS en 2026-09-30T04:00:00+00:00 Convex Optimization Is Free When Accuracy Is Expensive https://ax-news.com/?article=184377928 AX-NEWS en 2026-09-30T04:00:00+00:00 Beyond Token Scale: Chunk-Level Sparse Autoencoders for Reliable Semantic Feature Discovery https://ax-news.com/?article=184377929 AX-NEWS en 2026-09-30T04:00:00+00:00 Less Sycophancy, Stronger Refusal? Lessons for AI Safety from Mechanistic Interpretability https://ax-news.com/?article=184377931 AX-NEWS en 2026-09-30T04:00:00+00:00 Share-Borne AI Virus: Memory-Hopping Attacks Across LLM Agents https://ax-news.com/?article=184377946 AX-NEWS en 2026-09-30T04:00:00+00:00 Advanced Policies: A First-Principles Path from Policy Gradient to Q-Learning https://ax-news.com/?article=184377971 AX-NEWS en 2026-09-30T04:00:00+00:00 Learning Domain- and Class-Disentangled Prototypes for Domain-Generalized EEG Emotion Recognition https://ax-news.com/?article=184377981 AX-NEWS en 2026-09-30T04:00:00+00:00 Adam or Gauss-Newton? A Comparative Study In Terms of Basis Alignment and SGD Noise https://ax-news.com/?article=184377992 AX-NEWS en 2026-09-30T04:00:00+00:00 CAT: Can Trust be Predicted with Context-Awareness in Dynamic Heterogeneous Networks? https://ax-news.com/?article=184377995 AX-NEWS en 2026-09-30T04:00:00+00:00 Shapley-based Data Valuation for LLM Alignment via Sequential Preference Optimization https://ax-news.com/?article=184377997 AX-NEWS en 2026-09-30T04:00:00+00:00 SB-TRPO: Towards Safe Reinforcement Learning with Hard Constraints https://ax-news.com/?article=184378002 AX-NEWS en 2026-09-30T04:00:00+00:00 Just-In-Time Reinforcement Learning: Continual Learning in LLM Agents Without Gradient Updates https://ax-news.com/?article=184378015 AX-NEWS en 2026-09-30T04:00:00+00:00 Preventing Rank Collapse in Federated Low-Rank Adaptation with Client Heterogeneity https://ax-news.com/?article=184378017 AX-NEWS en 2026-09-30T04:00:00+00:00 Pseudo-differential-enhanced physics-informed neural networks https://ax-news.com/?article=184378019 AX-NEWS en 2026-09-30T04:00:00+00:00 Neural Proposals, Symbolic Guarantees: Neuro-Symbolic Graph Generative Modeling https://ax-news.com/?article=184378028 AX-NEWS en 2026-09-30T04:00:00+00:00 FlashSampling: Fast and Memory-Efficient Exact Sampling https://ax-news.com/?article=184378030 AX-NEWS en 2026-09-30T04:00:00+00:00 Discovering What You Can Control: Interventional Boundary Discovery for Reinforcement Learning https://ax-news.com/?article=184378032 AX-NEWS en 2026-09-30T04:00:00+00:00 Joint Surrogate Learning of Objectives, Constraints, and Sensitivities for Efficient Multi-objective Optimization of Neural Dynamical Systems https://ax-news.com/?article=184378041 AX-NEWS en 2026-09-30T04:00:00+00:00 Relative Density Ratio Optimization for Stable and Statistically Consistent Model Alignment https://ax-news.com/?article=184378044 AX-NEWS en 2026-09-30T04:00:00+00:00 EvoLen: Evolution-Guided Tokenization for DNA Language Model https://ax-news.com/?article=184378046 AX-NEWS en 2026-09-30T04:00:00+00:00 Lightning OPD: Efficient Post-Training for Large Reasoning Models with Offline On-Policy Distillation https://ax-news.com/?article=184378053 AX-NEWS en 2026-09-30T04:00:00+00:00 Demystifying Manifold Constraints in LLM Pre-training https://ax-news.com/?article=184378063 AX-NEWS en 2026-09-30T04:00:00+00:00 Enabling Unsupervised Training of Deep EEG Denoisers With Intelligent Partitioning https://ax-news.com/?article=184378065 AX-NEWS en 2026-09-30T04:00:00+00:00 On Privacy in Data-Space Tabular Diffusion Models: Influential Factors, Attacker Knowledge, and Metrics https://ax-news.com/?article=184378068 AX-NEWS en 2026-09-30T04:00:00+00:00 CellScientist: From Execution Feedback to Auditable Model-Revision Trajectories for Cellular Perturbation Prediction https://ax-news.com/?article=184378072 AX-NEWS en 2026-09-30T04:00:00+00:00 Recovering Physical Dynamics from Discrete Observations via Intrinsic Differential Consistency https://ax-news.com/?article=184378079 AX-NEWS en 2026-09-30T04:00:00+00:00 When and How to Canonize: A Generalization Perspective https://ax-news.com/?article=184378081 AX-NEWS en 2026-09-30T04:00:00+00:00 Internalizing Curriculum Judgment for LLM Reinforcement Fine-Tuning https://ax-news.com/?article=184378084 AX-NEWS en 2026-09-30T04:00:00+00:00 Hypernetworks for Dynamic Feature Selection https://ax-news.com/?article=184378086 AX-NEWS en 2026-09-30T04:00:00+00:00 Hessian Matching for Machine-Learned Coarse-Grained Molecular Dynamics https://ax-news.com/?article=184378102 AX-NEWS en 2026-09-30T04:00:00+00:00 Reasoning-Trace Collapse: Evaluating the Loss of Explicit Reasoning During Fine-Tuning https://ax-news.com/?article=184378103 AX-NEWS en 2026-09-30T04:00:00+00:00 EntmaxKV: Support-Aware Decoding for Entmax Attention https://ax-news.com/?article=184378105 AX-NEWS en 2026-09-30T04:00:00+00:00 Learned Relay Representations for Forward-Thinking Discrete Diffusion Models https://ax-news.com/?article=184378111 AX-NEWS en 2026-09-30T04:00:00+00:00 Effective Biological Representation Learning by Masking Gene Expression https://ax-news.com/?article=184378112 AX-NEWS en 2026-09-30T04:00:00+00:00 BitsMoE: Cost-Aware Bit Allocation in Spectral Space for MoE LLM Quantization https://ax-news.com/?article=184378115 AX-NEWS en 2026-09-30T04:00:00+00:00 SPR: Toward a Graph Foundation Model for Transferable Graph Cognition via Spectral Patterns and Relational Geometry https://ax-news.com/?article=184378116 AX-NEWS en 2026-09-30T04:00:00+00:00 Large Language Models Hack Rewards, and Society https://ax-news.com/?article=184378119 AX-NEWS en 2026-09-30T04:00:00+00:00 The Routing Plateau: Understanding the Accuracy Limits of LLM Routers https://ax-news.com/?article=184378121 AX-NEWS en 2026-09-30T04:00:00+00:00 nCMD: Benign-Anchored Feature Selection for Imbalanced Network Intrusion Detection https://ax-news.com/?article=184378123 AX-NEWS en 2026-09-30T04:00:00+00:00 Claw-SWE-Bench: A Benchmark for Evaluating OpenClaw-style Agent Harnesses on Coding Tasks https://ax-news.com/?article=184378130 AX-NEWS en 2026-09-30T04:00:00+00:00 Filtered Conformal Ellipsoids for Graph-Native Time Series https://ax-news.com/?article=184378131 AX-NEWS en 2026-09-30T04:00:00+00:00 Recursive Scaling in Masked Diffusion Models https://ax-news.com/?article=184378138 AX-NEWS en 2026-09-30T04:00:00+00:00 The Interplay of Harness Design and Post-Training in LLM Agents https://ax-news.com/?article=184378157 AX-NEWS en 2026-09-30T04:00:00+00:00 What Does Model Growth Really Add? Functional Capacity Beyond Parameter Count https://ax-news.com/?article=184378159 AX-NEWS en 2026-09-30T04:00:00+00:00 TRACE: Trajectory-Based Safety Patch Learning for LLM Post-Training Realignment https://ax-news.com/?article=184378162 AX-NEWS en 2026-09-30T04:00:00+00:00 CriPO: Enhancing Rubric-based RL via Self-Distillation https://ax-news.com/?article=184378163 AX-NEWS en 2026-09-30T04:00:00+00:00 Conditioned Direct Feedback Alignment via Activity and Error Geometry https://ax-news.com/?article=184378165 AX-NEWS en 2026-09-30T04:00:00+00:00 Interval and fuzzy physics-augmented neural networks (iPANN and fPANN) for uncertainty quantification and propagation in constitutive modeling https://ax-news.com/?article=184378176 AX-NEWS en 2026-09-30T04:00:00+00:00 DASH-OPD: Discrepancy-Aware Switching with Hysteresis for On-Policy Distillation https://ax-news.com/?article=184378180 AX-NEWS en 2026-09-30T04:00:00+00:00 SSTQ:Privacy-Preserving Vector Quantization via Subsampled Stochastic TurboQuant https://ax-news.com/?article=184378187 AX-NEWS en 2026-09-30T04:00:00+00:00 HOPPER: Learnable Hop Extraction for Linearized Graph Sequence Models https://ax-news.com/?article=184378191 AX-NEWS en 2026-09-30T04:00:00+00:00 Towards Understanding On-Policy Distillation through the Lens of Test-Time Scaling https://ax-news.com/?article=184378199 AX-NEWS en 2026-09-30T04:00:00+00:00 Reinforced Planning with Latent World Models https://ax-news.com/?article=184378200 AX-NEWS en 2026-09-30T04:00:00+00:00 Beyond Multimodal Alignment: Shared Physical Representations Across Sensors and Action Orders https://ax-news.com/?article=184378210 AX-NEWS en 2026-09-30T04:00:00+00:00 Nonparametric Contextual Pricing and Inventory Learning under Censored Demand https://ax-news.com/?article=184378117 AX-NEWS en 2026-09-30T04:00:00+00:00 Dual Advantage Fields https://ax-news.com/?article=184378212 AX-NEWS en 2026-09-30T04:00:00+00:00 How Do Language Models Choose Between Context and Memory? https://ax-news.com/?article=184378217 AX-NEWS en 2026-09-30T04:00:00+00:00 TabBench-Bio: A Living Benchmark for Machine Learning on High-Dimensional Biomedical Tables https://ax-news.com/?article=184378222 AX-NEWS en 2026-09-30T04:00:00+00:00 Solving Few-Shot Multiobjective Multitask Optimization via Iterative Sequential Transfer https://ax-news.com/?article=184378223 AX-NEWS en 2026-09-30T04:00:00+00:00 Certified Safety Curation: Distribution-Free Guarantees for Safe Offline Reinforcement Learning https://ax-news.com/?article=184378228 AX-NEWS en 2026-09-30T04:00:00+00:00 Sharp Regret Bounds and a Task-Covariance Correction for Spectral Representation Learning https://ax-news.com/?article=184378237 AX-NEWS en 2026-09-30T04:00:00+00:00 WaveFront Decoding: Parallelized Self-Speculative Decoding for Looped Language Models https://ax-news.com/?article=184378238 AX-NEWS en 2026-09-30T04:00:00+00:00 CSC: Calibrated Simplicity for Conflict-Aware Social Bot Detection in the LLM Era https://ax-news.com/?article=184378241 AX-NEWS en 2026-09-30T04:00:00+00:00 Misaligned Clinical Risk Classification and Cost Asymmetry in Open-Weight Large Language Models https://ax-news.com/?article=184378243 AX-NEWS en 2026-09-30T04:00:00+00:00 iSDFT: Information-Proximal Self-Distillation for Continual Learning in LLMs https://ax-news.com/?article=184378244 AX-NEWS en 2026-09-30T04:00:00+00:00 What Should a Self-Teacher See? Privileged Context Design for On-Policy Self-Distillation https://ax-news.com/?article=184378245 AX-NEWS en 2026-09-30T04:00:00+00:00 Graph Domain Adaptation Does Not End with Representation Learning https://ax-news.com/?article=184378250 AX-NEWS en 2026-09-30T04:00:00+00:00 Not Every Token Is Worth Distilling: Selective Supervision for Direct-OPD https://ax-news.com/?article=184378251 AX-NEWS en 2026-09-30T04:00:00+00:00 Beyond Feature Reliability: Repeat-Informed Multifractal Curve Regression for Brain-Age Prediction https://ax-news.com/?article=184378268 AX-NEWS en 2026-09-30T04:00:00+00:00 TACO: Training-free Sound Prompted Segmentation via Semantically Constrained Audio-visual CO-factorization https://ax-news.com/?article=184378271 AX-NEWS en 2026-09-30T04:00:00+00:00 Optimization on the Oblique Manifold for Sparse Simplex Constraints via Multiplicative Updates https://ax-news.com/?article=184378276 AX-NEWS en 2026-09-30T04:00:00+00:00 Accelerating Natural Gradient Descent for PINNs with Randomized Numerical Linear Algebra https://ax-news.com/?article=184378279 AX-NEWS en 2026-09-30T04:00:00+00:00 Identifiable Convex-Concave Regression via Sub-gradient Regularised Least Squares https://ax-news.com/?article=184378284 AX-NEWS en 2026-09-30T04:00:00+00:00 Synthetic data for ratemaking: imputation-based methods vs adversarial networks and autoencoders https://ax-news.com/?article=184378285 AX-NEWS en 2026-09-30T04:00:00+00:00 A Kernel-based Stochastic Approximation Framework for Nonlinear Operator Learning https://ax-news.com/?article=184378286 AX-NEWS en 2026-09-30T04:00:00+00:00 The Platonic Universe: Do Foundation Models See the Same Sky? https://ax-news.com/?article=184378292 AX-NEWS en 2026-09-30T04:00:00+00:00 AlignBeat: A Latent Variable Model for Multi-Class Beat Tracking from Partially Labeled Data https://ax-news.com/?article=184378296 AX-NEWS en 2026-09-30T04:00:00+00:00 Disciplined Biconvex Programming https://ax-news.com/?article=184378300 AX-NEWS en 2026-09-30T04:00:00+00:00 Digital Agriculture Sandbox for Collaborative Research https://ax-news.com/?article=184378308 AX-NEWS en 2026-09-30T04:00:00+00:00 Do Latent-CoT Models Think Step-by-Step? A Mechanistic Study on Sequential Reasoning Tasks https://ax-news.com/?article=184378311 AX-NEWS en 2026-09-30T04:00:00+00:00 Instance-optimal high-precision shadow tomography with few-copy measurements: A metrological approach https://ax-news.com/?article=184378313 AX-NEWS en 2026-09-30T04:00:00+00:00 Efficient reduction of stellar contamination and noise in planetary transmission spectra using neural networks https://ax-news.com/?article=184378314 AX-NEWS en 2026-09-30T04:00:00+00:00 TSR: Trajectory-Search Rollouts for Multi-Turn RL of LLM Agents https://ax-news.com/?article=184378318 AX-NEWS en 2026-09-30T04:00:00+00:00 ReLoop: Structured Modeling and Behavioral Verification for Reliable LLM-Based Optimization https://ax-news.com/?article=184378319 AX-NEWS en 2026-09-30T04:00:00+00:00 Universal Pose Pretraining for Generalizable Vision-Language-Action Policies https://ax-news.com/?article=184378327 AX-NEWS en 2026-09-30T04:00:00+00:00 Learning Transferable Sensor Models via Language-Informed Pretraining https://ax-news.com/?article=184378329 AX-NEWS en 2026-09-30T04:00:00+00:00 When Should Humans Step In? Optimal Human Dispatching in AI-Assisted Decisions https://ax-news.com/?article=184378330 AX-NEWS en 2026-09-30T04:00:00+00:00 Patient-level validation of a foundation-model pipeline for pediatric lung sounds: physician-annotated adventitious events are recognized, disease groups are not reliably predicted https://ax-news.com/?article=184378345 AX-NEWS en 2026-09-30T04:00:00+00:00 BALAR : A Bayesian Agentic Loop for Active Reasoning https://ax-news.com/?article=184378346 AX-NEWS en 2026-09-30T04:00:00+00:00 Are We Making Progress in Multimodal Domain Generalization? A Comprehensive Benchmark Study https://ax-news.com/?article=184378349 AX-NEWS en 2026-09-30T04:00:00+00:00 TrajGANR: Trajectory-Centric Urban Multimodal Learning via Geospatially Aligned Neural Representations https://ax-news.com/?article=184378353 AX-NEWS en 2026-09-30T04:00:00+00:00 Memory-Efficient Looped Transformer: Decoupling Compute from Memory in Looped Language Models https://ax-news.com/?article=184378355 AX-NEWS en 2026-09-30T04:00:00+00:00 ProcVLM: Learning Procedure-Grounded Progress Rewards for Robotic Manipulation https://ax-news.com/?article=184378357 AX-NEWS en 2026-09-30T04:00:00+00:00 Max-pooling Network Revisited: Analyzing the Role of Semantic Probability in Multiple Instance Learning for Hallucination Detection https://ax-news.com/?article=184378362 AX-NEWS en 2026-09-30T04:00:00+00:00 EHR-RAGp: Prototype-Guided Retrieval of Longitudinal Electronic Health Records for Clinical Prediction Models https://ax-news.com/?article=184378366 AX-NEWS en 2026-09-30T04:00:00+00:00 CM-EVS: Sparse Panoramic RGB-D-Pose Data for Complete Scene Coverage https://ax-news.com/?article=184378374 AX-NEWS en 2026-09-30T04:00:00+00:00 PhoneWorld: From Real-App Trajectories to Dynamic and Verifiable Environments for Phone-Use Agents https://ax-news.com/?article=184378376 AX-NEWS en 2026-09-30T04:00:00+00:00 Shared Doubt: Zero-Shot Cross-Lingual Confidence Estimation for Language Models https://ax-news.com/?article=184378377 AX-NEWS en 2026-09-30T04:00:00+00:00 Diagnosing Visual Ignorance in Vision-Language Models https://ax-news.com/?article=184378378 AX-NEWS en 2026-09-30T04:00:00+00:00 Driving Video Retrieval for Complex Queries with Structured Grounding https://ax-news.com/?article=184378382 AX-NEWS en 2026-09-30T04:00:00+00:00 Toward Proactive RF Charging Scheduling: Generative AI for Decision Support https://ax-news.com/?article=184378385 AX-NEWS en 2026-09-30T04:00:00+00:00 Capability Provenance in Language Models: A Case Study in Social Reasoning https://ax-news.com/?article=184378394 AX-NEWS en 2026-09-30T04:00:00+00:00 Dithered Gaussian Mechanism for Randomness-Efficient Differential Privacy https://ax-news.com/?article=184378396 AX-NEWS en 2026-09-30T04:00:00+00:00 NetInjectBench: Benchmarking Indirect Prompt Injection in Tool-Using Large Language Model Agents for Network Operations https://ax-news.com/?article=184378401 AX-NEWS en 2026-09-30T04:00:00+00:00 Simulating Eutopia: Revisiting Long-term Fairness with Outcomes, Performativity, and Dynamics https://ax-news.com/?article=184378402 AX-NEWS en 2026-09-30T04:00:00+00:00 Priors learned from legacy reconstructions inherit undetectable overconfidence https://ax-news.com/?article=184378408 AX-NEWS en 2026-09-30T04:00:00+00:00 AgentStream: How Well Do Self-Evolving LLM Agents Perform Under Streaming Tasks? https://ax-news.com/?article=184378409 AX-NEWS en 2026-09-30T04:00:00+00:00 Preferred, Not Safer: Pairwise Preference Is a Poor Proxy for Clinical Safety https://ax-news.com/?article=184378411 AX-NEWS en 2026-09-30T04:00:00+00:00 Tokenizer-Generator Coupling in Medical Image Generation https://ax-news.com/?article=184378414 AX-NEWS en 2026-09-30T04:00:00+00:00 What is Missing from AI Post-Training AI: An Empirical Analysis https://ax-news.com/?article=184378417 AX-NEWS en 2026-09-30T04:00:00+00:00 Scaling Reinforcement Learning for Diffusion Models via Velocity Matching https://ax-news.com/?article=184378424 AX-NEWS en 2026-09-30T04:00:00+00:00 ActionSplice: In-Flight Action Editing for Interactive World Models https://ax-news.com/?article=184378428 AX-NEWS en 2026-09-30T04:00:00+00:00 Break Step: Recursive Training Resonates with Replayed Sampling Noise https://ax-news.com/?article=184378429 AX-NEWS en 2026-09-30T04:00:00+00:00 Near-Optimal Reinforcement Learning with Multi-Step Transition Lookahead https://ax-news.com/?article=184378432 AX-NEWS en 2026-09-30T04:00:00+00:00 SpliTEE: Fast and Private LLM Inference by Coupling GPU-Assisted Trusted Execution Environments with Differential Privacy https://ax-news.com/?article=184378440 AX-NEWS en 2026-09-30T04:00:00+00:00 Learning and Control Beyond Linearity: Towards a Non-asymptotic Theory for Bilinear Systems https://ax-news.com/?article=184378442 AX-NEWS en 2026-09-30T04:00:00+00:00 A Bayesian Vertical Federated Learning Framework for Multivariate Reduced-Rank High-Dimensional Regression https://ax-news.com/?article=184378444 AX-NEWS en 2026-09-30T04:00:00+00:00 FREESIA: Covariance-Aware Posterior Transport for Expressive and Scalable Data Assimilation https://ax-news.com/?article=184378454 AX-NEWS en 2026-09-30T04:00:00+00:00 Cost-Sensitive Online Window Size Selection for Portfolio Management https://ax-news.com/?article=184378455 AX-NEWS en 2026-09-30T04:00:00+00:00 Low-Rank Friction for Memory-Efficient Transformer Pretraining https://ax-news.com/?article=184378460 AX-NEWS en 2026-09-30T04:00:00+00:00 More Programs or More Rolls? Separating Coverage from Specialization in LLM Harnesses https://ax-news.com/?article=184378465 AX-NEWS en 2026-09-30T04:00:00+00:00 Grab a Coffee: Future-Aware Guidance for Discrete Diffusion with Compiled Objectives https://ax-news.com/?article=184378468 AX-NEWS en 2026-09-30T04:00:00+00:00 PowerZooJax: A JAX-based Power System Benchmark for Reinforcement Learning https://ax-news.com/?article=184378469 AX-NEWS en 2026-09-30T04:00:00+00:00 GeoWind2Plan: Mission-Time 3D Urban Wind Prediction for Energy-Efficient UAV Planning https://ax-news.com/?article=184378474 AX-NEWS en 2026-09-30T04:00:00+00:00 GeoOutageBench: Benchmarking Ambiguity-aware, Ontology-grounded Geospatiotemporal KGQA for Multimodal Power Outage and Resilience Analysis https://ax-news.com/?article=184378480 AX-NEWS en 2026-09-30T04:00:00+00:00 Principled Thoughts for Latent Recursive LLM Systems https://ax-news.com/?article=184378500 AX-NEWS en 2026-09-30T04:00:00+00:00 ARCagent: An Adaptive Retrieval Calibration Agent for Clinical Question Answering https://ax-news.com/?article=184378507 AX-NEWS en 2026-09-30T04:00:00+00:00 Learning to Harvest Without Collapse in a Regenerative Commons: A Lagrangian Framework https://ax-news.com/?article=184378510 AX-NEWS en 2026-09-30T04:00:00+00:00 BRIDGE: Bilevel Retrieval-Credit-Aware Agentic Reinforcement Learning https://ax-news.com/?article=184378516 AX-NEWS en 2026-09-30T04:00:00+00:00 Transformers Stop Thinking Too Early, and a Tiny LoRA Fixes It https://ax-news.com/?article=184378520 AX-NEWS en 2026-09-30T04:00:00+00:00 DualTrack: Synchronized speech-gesture generation via symmetric coupling of pretrained priors https://ax-news.com/?article=184378543 AX-NEWS en 2026-09-30T04:00:00+00:00 The Default Trap: Rethinking Plan Evaluation in Tool-Using LLM Agents https://ax-news.com/?article=184378547 AX-NEWS en 2026-09-30T04:00:00+00:00 When Upstream Messages Override Correct Answers: A Controlled Study of Multi-Agent LLM Collaboration https://ax-news.com/?article=184378551 AX-NEWS en 2026-09-30T04:00:00+00:00 Beyond Sub-Gaussian Detector Scores: Robust Weighted Profile-Loss Change Point Detection for Human-LLM Text Segmentation https://ax-news.com/?article=184378554 AX-NEWS en 2026-09-30T04:00:00+00:00 STAR-GRPO: Canonical Anchoring and Reliability-First Advantages against Representation-Dependent Reward Hacking https://ax-news.com/?article=184378559 AX-NEWS en 2026-09-30T04:00:00+00:00 CoEM: Empowering Long-Context Reasoning with Commit-on-Evidence Memory https://ax-news.com/?article=184378565 AX-NEWS en 2026-09-30T04:00:00+00:00 CADOC: Cache-Aware Dynamic Object Context for Long-Horizon Agents https://ax-news.com/?article=184378569 AX-NEWS en 2026-09-30T04:00:00+00:00 Beyond Low-Rank Parameterization: Narrowing the Gap Between LoRA and Full Fine-Tuning via Gradient Decomposition https://ax-news.com/?article=184378575 AX-NEWS en 2026-09-30T04:00:00+00:00 Learning from Viable Failure Prefixes: Milestone Viability Potential Policy Optimization for Long-Horizon LLM Agents https://ax-news.com/?article=184378576 AX-NEWS en 2026-09-30T04:00:00+00:00 When Should Agents Check External State? Budgeting Observations for Stored Intentions https://ax-news.com/?article=184378584 AX-NEWS en 2026-09-30T04:00:00+00:00 Accelerated surrogate dynamics for dynamical, stochastic system evolution https://ax-news.com/?article=184378600 AX-NEWS en 2026-09-30T04:00:00+00:00 Teaching LLMs to Generate Challenging MILP Instances via Solver Feedback https://ax-news.com/?article=184378614 AX-NEWS en 2026-09-30T04:00:00+00:00 Rational Clarification by Assistive Agents via Value-of-Information Reasoning https://ax-news.com/?article=184378615 AX-NEWS en 2026-09-30T04:00:00+00:00 FOCUS: Training-Free Decision-Preserving Context Compression for LLM Agents https://ax-news.com/?article=184378618 AX-NEWS en 2026-09-30T04:00:00+00:00 Beyond a single latent space: a dual-latent world model for long-horizon planning https://ax-news.com/?article=184378624 AX-NEWS en 2026-09-30T04:00:00+00:00 WISE-ATTA: When to Ask for Labels in Budgeted Active Test-Time Adaptation https://ax-news.com/?article=184378634 AX-NEWS en 2026-09-30T04:00:00+00:00 DIET: Deletion-response Expert Trimming for Video Diffusion Transformers https://ax-news.com/?article=184378637 AX-NEWS en 2026-09-30T04:00:00+00:00 Active Budget Can Kill Sensitivity: Diagnosing and Repairing TopK Sparse Autoencoder Reliability https://ax-news.com/?article=184378643 AX-NEWS en 2026-09-30T04:00:00+00:00 Video-RSI: Recursive Self-Improvement of Video Understanding Agents via Harness Evolution https://ax-news.com/?article=184378644 AX-NEWS en 2026-09-30T04:00:00+00:00 Topological Coherence for Self-evolving Multi-agent Systems https://ax-news.com/?article=184378647 AX-NEWS en 2026-09-30T04:00:00+00:00 KV-Kaizen: Learning Context-Adaptive Cache Compression Choices https://ax-news.com/?article=184378651 AX-NEWS en 2026-09-30T04:00:00+00:00 Brain-SAD: A Brain-Inspired Safe Autonomous Driving Control Framework with Dynamic Fear-Oriented Constraint on Dual-Policy https://ax-news.com/?article=184378652 AX-NEWS en 2026-09-30T04:00:00+00:00 PE-EK-PINN: Physics Embedding with Evolving Kernel for Scalable Physics-Informed Neural Networks https://ax-news.com/?article=184378653 AX-NEWS en 2026-09-30T04:00:00+00:00 Retrieval-Augmented Skill Optimization via Cross-Harness Adaptation https://ax-news.com/?article=184378657 AX-NEWS en 2026-09-30T04:00:00+00:00 NeuronEye: Query-Guided Visual Concept Activation for Vision-Language Reasoning https://ax-news.com/?article=184378660 AX-NEWS en 2026-09-30T04:00:00+00:00 AdviSD: Learning to Advise Frontier LLMs via Targeted Multi-Turn Self-Distillation https://ax-news.com/?article=184378661 AX-NEWS en 2026-09-30T04:00:00+00:00 Learning Meta-Skills for Agent Harness Design in Test-Time AI4AI https://ax-news.com/?article=184378663 AX-NEWS en 2026-09-30T04:00:00+00:00 Bathtubs, Boundaries, and Sandboxes: AI Regulatory Learning under Legal Uncertainty https://ax-news.com/?article=184378689 AX-NEWS en 2026-09-30T04:00:00+00:00 CruxBench: A Benchmark of Information Discovery https://ax-news.com/?article=184378691 AX-NEWS en 2026-09-30T04:00:00+00:00 SINGED: Correct Outputs Do Not Certify Safe Execution in LLM Agents https://ax-news.com/?article=184378694 AX-NEWS en 2026-09-30T04:00:00+00:00 Cheap to Hypothesize, Costly to Verify: The Defense Surface of Agentic Vulnerability Discovery https://ax-news.com/?article=184378702 AX-NEWS en 2026-09-30T04:00:00+00:00 Same Bytes, Different Authority: Reserved-Token Representations in Chat-Template Prompt Injection https://ax-news.com/?article=184378705 AX-NEWS en 2026-09-30T04:00:00+00:00 PrivacySkills: How Privacy Guidance Shapes Source Selection in LLM Agents https://ax-news.com/?article=184378706 AX-NEWS en 2026-09-30T04:00:00+00:00 Intrinsic Associative Memory on Riemannian Manifolds: Curvature, Capacity, and Emergent Modes https://ax-news.com/?article=184378708 AX-NEWS en 2026-09-30T04:00:00+00:00 ROSS: Relearning from Self-Generated Rollouts through Selective Supervision https://ax-news.com/?article=184378710 AX-NEWS en 2026-09-30T04:00:00+00:00 Systematic Multi-Agent Vision-and-Language Navigation: Formulation, Benchmark, and Method https://ax-news.com/?article=184378711 AX-NEWS en 2026-09-30T04:00:00+00:00 Causal and Interpretable Structures in LLM Compositional Tasks https://ax-news.com/?article=184378712 AX-NEWS en 2026-09-30T04:00:00+00:00 Infrared Subtraction with Artificial Intelligence https://ax-news.com/?article=184378713 AX-NEWS en 2026-09-30T04:00:00+00:00 TORQUE: Optimizing What (not) to Quantize Before and After Rotation https://ax-news.com/?article=184378715 AX-NEWS en 2026-09-30T04:00:00+00:00 Improving scalable oversight with co-trained monitors https://ax-news.com/?article=184378716 AX-NEWS en 2026-09-30T04:00:00+00:00 What if automating AI R＆D triggers an intelligence explosion? https://ax-news.com/?article=184378720 AX-NEWS en 2026-09-30T04:00:00+00:00 AerialDojo-200K: A Large-Scale Benchmark Suite for Open-World Aerial Object-Goal Search https://ax-news.com/?article=184378723 AX-NEWS en 2026-09-30T04:00:00+00:00 PADM\'E: Preference Alignment Data Synthesis for Meta-Evaluation of LM Agent Evaluators https://ax-news.com/?article=184378725 AX-NEWS en 2026-09-30T04:00:00+00:00 One Geometry, Different Outcomes: Readout-Dependent Effects of the Modality Gap in Vision-Language Models https://ax-news.com/?article=184378731 AX-NEWS en 2026-09-30T04:00:00+00:00 Language Models Are "Insecure" Reporters https://ax-news.com/?article=184378737 AX-NEWS en 2026-09-30T04:00:00+00:00 PreviewDiff: Multimodal Critic-Guided Search over Diffusion Latents https://ax-news.com/?article=184378738 AX-NEWS en 2026-09-30T04:00:00+00:00 SCOUT: Synergizing Reasoning and Tool-Use for Computer-Use Safety https://ax-news.com/?article=184378740 AX-NEWS en 2026-09-30T04:00:00+00:00 CineSubBench: Evaluating LLMs on Long-Form Narrative and Cultural Understanding from Multilingual Movie Subtitles https://ax-news.com/?article=184378751 AX-NEWS en 2026-09-30T04:00:00+00:00 Periodic Weak Spots: Phase Sensitivity from Chunked KV-Cache Compression https://ax-news.com/?article=184378758 AX-NEWS en 2026-09-30T04:00:00+00:00 Cross-attention encoding models reveal dynamic spatiotemporal routing across human higher visual cortex https://ax-news.com/?article=184378760 AX-NEWS en 2026-09-30T04:00:00+00:00 LatentSift: Policy-State Filtering for Token-Efficient Verification of Software Engineering Agents https://ax-news.com/?article=184378762 AX-NEWS en 2026-09-30T04:00:00+00:00 Quantization Enables Private Dense Retrieval against Malicious Service Providers https://ax-news.com/?article=184378767 AX-NEWS en 2026-09-30T04:00:00+00:00 FineART: Fine-grained Annotated Robotic Trajectory Dataset and Vision-Language-Action Model for Bimanual Manipulation https://ax-news.com/?article=184378769 AX-NEWS en 2026-09-30T04:00:00+00:00 Reliable Parallel Decoding in Masked Diffusion Language Models https://ax-news.com/?article=184378785 AX-NEWS en 2026-09-30T04:00:00+00:00 Interactive-Policy Distillation with Bidirectional Propose-and-Verify https://ax-news.com/?article=184378786 AX-NEWS en 2026-09-30T04:00:00+00:00 SERA: Scale-Equalized Rollout Allocation for Maximum Likelihood Reinforcement Learning https://ax-news.com/?article=184378787 AX-NEWS en 2026-09-30T04:00:00+00:00 How Medical VLMs Underutilize Their Vision Encoders: A Dermatology Perspective https://ax-news.com/?article=184378802 AX-NEWS en 2026-09-30T04:00:00+00:00 Where Predictive Supervision Goes Shapes What VLA Policies Learn https://ax-news.com/?article=184378814 AX-NEWS en 2026-09-30T04:00:00+00:00 VAA-CSEC: Vote-guided Advantage Allocation for Chinese Semantic Error Correction https://ax-news.com/?article=184378816 AX-NEWS en 2026-09-30T04:00:00+00:00 Diffusion Policy Improvement with Proposal-Conditioned Refinement Flows https://ax-news.com/?article=184378852 AX-NEWS en 2026-09-30T04:00:00+00:00 Identifying ODEs from Unstructured Data with Causal Representation Learning https://ax-news.com/?article=184378858 AX-NEWS en 2026-09-30T04:00:00+00:00 Unlocking the Critic: Reward-Free Policy Optimization for LLM Post-Training https://ax-news.com/?article=184378859 AX-NEWS en 2026-09-30T04:00:00+00:00 SQUARE: Structured Quantum Representation Adapters as Compact Quadratic Feature Maps for Frozen Language Models https://ax-news.com/?article=184378860 AX-NEWS en 2026-09-30T04:00:00+00:00 Lucid Dreaming for World Models: Learning to Doubt Imagination and Decide by Trust https://ax-news.com/?article=184378864 AX-NEWS en 2026-09-30T04:00:00+00:00 ToolFence: Fine-Grained Authorization for Secure Tool-Using LLM Agents https://ax-news.com/?article=184378869 AX-NEWS en 2026-09-30T04:00:00+00:00 DatalogBench: Evaluating Large Language Models on Text-to-Datalog Synthesis https://ax-news.com/?article=184378873 AX-NEWS en 2026-09-30T04:00:00+00:00 UniAfford: Token-Routed Multitask Learning for Generalizable 2D-3D Affordance Perception https://ax-news.com/?article=184378878 AX-NEWS en 2026-09-30T04:00:00+00:00 A Sharp Transition in Data Reconstruction under Differential Privacy https://ax-news.com/?article=184378895 AX-NEWS en 2026-09-30T04:00:00+00:00 DScale: Scaling Block-Diffusion Speculative Decoding with Adaptive Verification https://ax-news.com/?article=184378896 AX-NEWS en 2026-09-30T04:00:00+00:00 Risk-Aware Semantic Grounding for Trustworthy LLM-Based Robot Planning https://ax-news.com/?article=184378900 AX-NEWS en 2026-09-30T04:00:00+00:00 Learning as Deepfakes Evolve: RF-Prompt for Continual Audio Deepfake Detection https://ax-news.com/?article=184378901 AX-NEWS en 2026-09-30T04:00:00+00:00 ReLMem: Learning Recurrent Memory for Longitudinal EHR Modeling https://ax-news.com/?article=184378904 AX-NEWS en 2026-09-30T04:00:00+00:00 AS$^2$D: Accelerating On-Demand Audio Understanding on Mobile Devices https://ax-news.com/?article=184378906 AX-NEWS en 2026-09-30T04:00:00+00:00 SPLASH: Switching Parallel Layouts of Attention with Seamless Handoff for LLM Serving https://ax-news.com/?article=184378911 AX-NEWS en 2026-09-30T04:00:00+00:00 Retrieve, Reproduce, Reveal: Dissecting Retrieval-Augmented Software Vulnerability Detection https://ax-news.com/?article=184378924 AX-NEWS en 2026-09-30T04:00:00+00:00 Pixel-Level Transformers in Remote Sensing: A Canopy Height Case Study https://ax-news.com/?article=184378926 AX-NEWS en 2026-09-30T04:00:00+00:00 Thinking in Depth, Speaking Directly: Recurrent Latent Reasoning for Paralinguistically Grounded Spoken Dialogue https://ax-news.com/?article=184378929 AX-NEWS en 2026-09-30T04:00:00+00:00 Scaling Influence Functions in LLMs through Eigenbasis-Corrected One-Bit Gradient Projection https://ax-news.com/?article=184378930 AX-NEWS en 2026-09-30T04:00:00+00:00 Is manual software optimization a thing of the past? https://ax-news.com/?article=184378932 AX-NEWS en 2026-09-30T04:00:00+00:00 It's Not What the Image Shows: Irrelevant Context Destabilises VLM Judges Without Informing Them https://ax-news.com/?article=184378936 AX-NEWS en 2026-09-30T04:00:00+00:00 Boids of a Feather Flock Together - Evolving Prey Behaviours Under Different Predator Attack Strategies https://ax-news.com/?article=184378939 AX-NEWS en 2026-09-30T04:00:00+00:00 The Unequal Influence of Bad Advice: Using Training Data Attribution to Modulate Emergent Misalignment https://ax-news.com/?article=184378946 AX-NEWS en 2026-09-30T04:00:00+00:00 BITEM at the NTCIR-19 R2C2 Task: Predicting Confidence from Agentic RAG Pipeline Signals https://ax-news.com/?article=184378951 AX-NEWS en 2026-09-30T04:00:00+00:00 doPlan: A Variable-Horizon Dataset for Multi-Stage Language-Conditioned Planning in Autonomous Driving https://ax-news.com/?article=184378955 AX-NEWS en 2026-09-30T04:00:00+00:00 Correct Answers, Invalid Traces: What Verifiable Grade-School Math Reveals About Chain-of-Thought Traces https://ax-news.com/?article=184378958 AX-NEWS en 2026-09-30T04:00:00+00:00 Beyond the Timeline: Augmenting Long-Video Memory with Grounded Entity Biographies https://ax-news.com/?article=184378961 AX-NEWS en 2026-09-30T04:00:00+00:00 Skill-Space Shooting for Autonomous Robot Policy Improvement https://ax-news.com/?article=184378967 AX-NEWS en 2026-09-30T04:00:00+00:00 FloCA: Towards Faithful and Logically Consistent Flowchart Reasoning https://ax-news.com/?article=184378968 AX-NEWS en 2026-09-30T04:00:00+00:00 Evaluating Test-Time Scaling of General LLM Agents https://ax-news.com/?article=184378974 AX-NEWS en 2026-09-30T04:00:00+00:00 Process Matters more than Output for Distinguishing Humans from Machines https://ax-news.com/?article=184378975 AX-NEWS en 2026-09-30T04:00:00+00:00 EquiMem: Calibrating Shared Memory in Multi-Agent Debate via Game-Theoretic Equilibrium https://ax-news.com/?article=184378976 AX-NEWS en 2026-09-30T04:00:00+00:00 Are Agents Ready to Teach? A Multi-Stage Benchmark for Real-World Teaching Workflows https://ax-news.com/?article=184378979 AX-NEWS en 2026-09-30T04:00:00+00:00 Harnessing LLM Agents with Skill Programs https://ax-news.com/?article=184378980 AX-NEWS en 2026-09-30T04:00:00+00:00 DemoEvolve: Demonstration-Guided Harness Evolution under Sparse Feedback https://ax-news.com/?article=184378983 AX-NEWS en 2026-09-30T04:00:00+00:00 Diversifying RLVR Rollouts via First-Token Exploration https://ax-news.com/?article=184378984 AX-NEWS en 2026-09-30T04:00:00+00:00 DeepSurvey: Agent-Oriented Automated Survey Generation with Analytical Depth and Citation Reliability https://ax-news.com/?article=184379005 AX-NEWS en 2026-09-30T04:00:00+00:00 Hapi: A Multivariable Land-Surface Transformer for Medium-Range Hydrological Forecasting at Continental Scale https://ax-news.com/?article=184379012 AX-NEWS en 2026-09-30T04:00:00+00:00 RepoMAS: Solving Progressively Specified Tasks with Issue-Driven Multi-Agent Systems https://ax-news.com/?article=184379014 AX-NEWS en 2026-09-30T04:00:00+00:00 Decision-Sufficient State Representations: Measuring and Reducing Write-Time Regret https://ax-news.com/?article=184379029 AX-NEWS en 2026-09-30T04:00:00+00:00 Just Initialize: A Training-Free Initialization Component for Large-Scale Routing Optimization https://ax-news.com/?article=184379032 AX-NEWS en 2026-09-30T04:00:00+00:00 Reasoning with Continuous Latent Diffusion https://ax-news.com/?article=184379038 AX-NEWS en 2026-09-30T04:00:00+00:00 Gondola: Grounded Vision Language Planning for Robotic Manipulation https://ax-news.com/?article=184379041 AX-NEWS en 2026-09-30T04:00:00+00:00 LLM Serving Optimization with Variable Prefill and Decode Lengths https://ax-news.com/?article=184379054 AX-NEWS en 2026-09-30T04:00:00+00:00 Phaedra: Learning High-Fidelity Discrete Tokenization for the Physical Science https://ax-news.com/?article=184379055 AX-NEWS en 2026-09-30T04:00:00+00:00 From Concept Erasure to Style Purification: Contrastive Eigenbases for Artist Style Protection https://ax-news.com/?article=184379058 AX-NEWS en 2026-09-30T04:00:00+00:00 Robo-Saber: Generating and Simulating Virtual Reality Players https://ax-news.com/?article=184379068 AX-NEWS en 2026-09-30T04:00:00+00:00 Suppression Is Not Forgetting: Residual Recoverability in Visual Concept Unlearning for VLMs https://ax-news.com/?article=184379069 AX-NEWS en 2026-09-30T04:00:00+00:00 Revisiting the Capacity Gap in Chain-of-Thought Distillation from a Practical Perspective https://ax-news.com/?article=184379071 AX-NEWS en 2026-09-30T04:00:00+00:00 Collective Opinion Dynamics in Structured LLM Populations https://ax-news.com/?article=184379073 AX-NEWS en 2026-09-30T04:00:00+00:00 Amortized Optimal Transport from Sliced Potentials https://ax-news.com/?article=184379076 AX-NEWS en 2026-09-30T04:00:00+00:00 Utility-Aware Data Pricing: Token-Level Quality and Empirical Training Gain for LLMs https://ax-news.com/?article=184379079 AX-NEWS en 2026-09-30T04:00:00+00:00 GRAVITY: Architecture-Agnostic Structured Anchoring for Long-Horizon Conversational Memory https://ax-news.com/?article=184379080 AX-NEWS en 2026-09-30T04:00:00+00:00 Trojan Hippo Bench: A Dynamic Benchmark for Persistent Memory Attacks and Defenses in LLM Agents https://ax-news.com/?article=184379089 AX-NEWS en 2026-09-30T04:00:00+00:00 Edge-AI-Driven Learning-to-Rank for Decentralized Task Allocation in Circular Smart Manufacturing https://ax-news.com/?article=184379093 AX-NEWS en 2026-09-30T04:00:00+00:00 Accelerating Video Inverse Problem Solvers with Autoregressive Diffusion Models https://ax-news.com/?article=184379094 AX-NEWS en 2026-09-30T04:00:00+00:00 EvoScene-VLA: Evolving Scene Beliefs Inside the Action Decoder for Chunked Robot Control https://ax-news.com/?article=184379095 AX-NEWS en 2026-09-30T04:00:00+00:00 Decomposing and Measuring Evaluation Awareness https://ax-news.com/?article=184379097 AX-NEWS en 2026-09-30T04:00:00+00:00 Adaptive Mass-Segmented KV Compression for Long-Context Reasoning https://ax-news.com/?article=184379101 AX-NEWS en 2026-09-30T04:00:00+00:00 Do Proactive Agents Need an LLM to Decide When to Act? https://ax-news.com/?article=184379102 AX-NEWS en 2026-09-30T04:00:00+00:00 Reasoning with Sampling: Cutting at Decision Points https://ax-news.com/?article=184379108 AX-NEWS en 2026-09-30T04:00:00+00:00 UPLOTS: A Unified Pretrained Language Model for Constrained Time-series Generation https://ax-news.com/?article=184379113 AX-NEWS en 2026-09-30T04:00:00+00:00 CRAX: Fast Safe Reinforcement Learning Benchmarking https://ax-news.com/?article=184379114 AX-NEWS en 2026-09-30T04:00:00+00:00 Is Agent Code Less Maintainable Than Human Code? https://ax-news.com/?article=184379115 AX-NEWS en 2026-09-30T04:00:00+00:00 Low-power analogue neural networks with trainable nonlinear connections for continuous control https://ax-news.com/?article=184379118 AX-NEWS en 2026-09-30T04:00:00+00:00 Weight-Adjusted Gradients Reveal Parameter Importance and Failure Modes in LLMs https://ax-news.com/?article=184379120 AX-NEWS en 2026-09-30T04:00:00+00:00 Distilled Reinforcement Learning for LLM Post-training https://ax-news.com/?article=184379122 AX-NEWS en 2026-09-30T04:00:00+00:00 Unlocking Spatial Grounding in Large Audio-Visual Retrieval models https://ax-news.com/?article=184379125 AX-NEWS en 2026-09-30T04:00:00+00:00 PAC-MAN: Perception-Aware CBF-RL for Whole-Body Safety in Humanoid Dodgeball https://ax-news.com/?article=184379138 AX-NEWS en 2026-09-30T04:00:00+00:00 Flow-JEPA: Robust Latent Dynamics for JEPA World Models via Flow Matching https://ax-news.com/?article=184379139 AX-NEWS en 2026-09-30T04:00:00+00:00 Linguistic Trajectory Encoding for Efficient Long-Horizon Spatial Memory in Embodied Agents https://ax-news.com/?article=184379145 AX-NEWS en 2026-09-30T04:00:00+00:00 Label-free steering: Compressing test-time reinforcement learning into bias-only subspaces https://ax-news.com/?article=184379147 AX-NEWS en 2026-09-30T04:00:00+00:00 NeuroECG: ECGFounder-Based Deep ECG Representation for EEG-Free Neurological Prognostication After Cardiac Arrest https://ax-news.com/?article=184379149 AX-NEWS en 2026-09-30T04:00:00+00:00 Are Coreset Selection Methods Worth Their Cost? https://ax-news.com/?article=184379154 AX-NEWS en 2026-09-30T04:00:00+00:00 Video-to-Music Generation for Gameplay Videos https://ax-news.com/?article=184379156 AX-NEWS en 2026-09-30T04:00:00+00:00 Affordance-Conditioned Decision Making: Bridging the Semantic-Spatial Gap in Zero-Shot Cross-Floor Vision-and-Language Navigation https://ax-news.com/?article=184379157 AX-NEWS en 2026-09-30T04:00:00+00:00 EyeVQA: Benchmarking Ophthalmic Vision-Language Models from Recognition to Spatial Grounding https://ax-news.com/?article=184379164 AX-NEWS en 2026-09-30T04:00:00+00:00 Evaluating System One Models for Agent Security Decisions: Reliability, Calibration, and Selective Automation https://ax-news.com/?article=184379166 AX-NEWS en 2026-09-30T04:00:00+00:00 Counterfactual Rollout Replay: Forkable Environments as Free Process Rewards for Software Engineering Agents https://ax-news.com/?article=184379179 AX-NEWS en 2026-09-30T04:00:00+00:00 KV-streams for Efficient Compaction in Agentic Reinforcement Learning https://ax-news.com/?article=184379180 AX-NEWS en 2026-09-30T04:00:00+00:00 TokenCast: Forecasting Token Consumption During LLM Agent Execution https://ax-news.com/?article=184435191 AX-NEWS en 2026-09-30T04:00:00+00:00 Everything’s bigger in Texas https://ax-news.com/?article=184375275 AX-NEWS en 2026-09-30T04:00:00+00:00 Simultaneously Query-Optimal Quantum Linear-System Algorithm https://ax-news.com/?article=184375280 AX-NEWS en 2026-09-30T04:00:00+00:00 Nonlinear engineering of Hong-Ou-Mandel interference with structured light https://ax-news.com/?article=184375288 AX-NEWS en 2026-09-30T04:00:00+00:00 A threshold for maximal Schmidt number from spectrum https://ax-news.com/?article=184375416 AX-NEWS en 2026-09-30T04:00:00+00:00 Optimal physical approximations of pure-state cloning and transposition are complementary channels https://ax-news.com/?article=184375422 AX-NEWS en 2026-09-30T04:00:00+00:00 Catalytic quantum thermodynamics beyond additivity and reduced-state monotones https://ax-news.com/?article=184375426 AX-NEWS en 2026-09-30T04:00:00+00:00 Efficient Quantum Fourier Transforms For Semisimple Algebras https://ax-news.com/?article=184378466 AX-NEWS en 2026-09-30T04:00:00+00:00 Right Words, Wrong Moment: A Clinician-Grounded Analysis of Distress in 19,930 Conversations between Young People and ChatGPT https://ax-news.com/?article=184378580 AX-NEWS en 2026-09-30T04:00:00+00:00 When Tools Silently Lie: Evaluating and Mitigating Blind Compliance in Tool-Augmented Data Agents https://ax-news.com/?article=184378872 AX-NEWS en 2026-09-30T04:00:00+00:00 Loss-Guided Pretraining Data Selection for Time-Series Foundation Models https://ax-news.com/?article=184375174 AX-NEWS en 2026-09-30T04:00:00+00:00 Mixture-of-Kittens: MoE Megakernel for NVL72s https://ax-news.com/?article=184375286 AX-NEWS en 2026-09-30T04:00:00+00:00 Quantum memory in an effective $\Lambda$-type system using dynamic detuning control of a superconducting qubit pair https://ax-news.com/?article=184376859 AX-NEWS en 2026-09-30T04:00:00+00:00 What If TSF: Reframing Time Series Forecasting as Scenario-Guided Multimodal Forecasting https://ax-news.com/?article=184376881 AX-NEWS en 2026-09-30T04:00:00+00:00 Let the Target Select for Itself: Data Selection via Target-Aligned Paths https://ax-news.com/?article=184376140 AX-NEWS en 2026-09-30T04:00:00+00:00 PrototypeNAS: Rapid Design of Deep Neural Networks for Microcontroller Units https://ax-news.com/?article=184376190 AX-NEWS en 2026-09-30T04:00:00+00:00 Counterfactual Video Generation Enables Scalable Humanoid Loco-Manipulation https://ax-news.com/?article=184378601 AX-NEWS en 2026-09-30T04:00:00+00:00 Pretrain Once, Route Anywhere: Towards a Foundation Model for LLM Routing https://ax-news.com/?article=184376682 AX-NEWS en 2026-09-30T04:00:00+00:00 VEX-Bench: Benchmarking Verification Complexity of LLM-Generated Misinformation https://ax-news.com/?article=184376360 AX-NEWS en 2026-09-30T04:00:00+00:00 AdaTutoRank: Learning to Rerank Document Sets via Adaptive Tutoring Optimization for RAG and Deep Research https://ax-news.com/?article=184376597 AX-NEWS en 2026-09-30T04:00:00+00:00 The Decomposition Tax: LLM Pipelines Lose Up to 40 Accuracy Points at Their Own Interfaces https://ax-news.com/?article=184378397 AX-NEWS en 2026-09-30T04:00:00+00:00 Diversified Multinomial Logit Contextual Bandits https://ax-news.com/?article=184376710 AX-NEWS en 2026-09-30T04:00:00+00:00 DocHop-QA: Towards Multi-Hop Reasoning over Multimodal Document Collections https://ax-news.com/?article=184379062 AX-NEWS en 2026-09-30T04:00:00+00:00 SalamahBench: Dialect and Category Level Safety Evaluation of Arabic Language Models https://ax-news.com/?article=184376562 AX-NEWS en 2026-09-30T04:00:00+00:00 Who Governs Data in the AI Era? A Computational Analysis of the U.S. Privacy Workforce in Job Postings https://ax-news.com/?article=184376684 AX-NEWS en 2026-09-30T04:00:00+00:00 TANGO: Watermarking Masked Diffusion Language Models in Token Pairs https://ax-news.com/?article=184376811 AX-NEWS en 2026-09-30T04:00:00+00:00 Token Distribution versus Data Volume: Domain Balancing in Multi-Domain Meeting Summarisation https://ax-news.com/?article=184376826 AX-NEWS en 2026-09-30T04:00:00+00:00 KVShareArena: KV-Cache Reuse Across Contexts and Model Checkpoints https://ax-news.com/?article=184378933 AX-NEWS en 2026-09-30T04:00:00+00:00 AgentBug-Smith: Automatically Reproducing Real-World Harness Bugs in Agentic Systems https://ax-news.com/?article=184375755 AX-NEWS en 2026-09-30T04:00:00+00:00 SCOUT: Synergizing Reasoning and Tool-Use for Computer-Use Safety https://ax-news.com/?article=184378940 AX-NEWS en 2026-09-30T04:00:00+00:00 RLX: A Unified Multi-Backend Tensor Compiler and Distributed Runtime in Rust https://ax-news.com/?article=184378943 AX-NEWS en 2026-09-30T04:00:00+00:00 Dagger: Decoupling-based Model Stealing Attack against Graph Neural Networks https://ax-news.com/?article=184378947 AX-NEWS en 2026-09-30T04:00:00+00:00 No Scale Left Behind: Multi-Scale Autoencoder with Bi-directional Attention for Time Series Anomaly Detection https://ax-news.com/?article=184378949 AX-NEWS en 2026-09-30T04:00:00+00:00 Auditable Long-Term Memory: A Deterministic Retrieval Chain Measured at 479/475 of 500 on LongMemEval-S https://ax-news.com/?article=184376030 AX-NEWS en 2026-09-30T04:00:00+00:00 Exploring In-Context Learning for Handwritten Text Recognition https://ax-news.com/?article=184377521 AX-NEWS en 2026-09-30T04:00:00+00:00 d-OPD: Future-Aware On-Policy Distillation for Block Diffusion Language Models https://ax-news.com/?article=184376104 AX-NEWS en 2026-09-30T04:00:00+00:00 Learning from synthetic photorealistic raindrop for single image raindrop removal https://ax-news.com/?article=184378977 AX-NEWS en 2026-09-30T04:00:00+00:00 COLLATOR: Compositional Multi-Agent Orchestration with Counterfactual Reinforcement Learning https://ax-news.com/?article=184377730 AX-NEWS en 2026-09-30T04:00:00+00:00 BudgetVerify: Budget-Tiered Verification for Financial QA https://ax-news.com/?article=184378982 AX-NEWS en 2026-09-30T04:00:00+00:00 KLineage: Recovering the Missing When of Kernel Optimization by Deoptimizing Experts https://ax-news.com/?article=184378989 AX-NEWS en 2026-09-30T04:00:00+00:00 When Do Agent Loops Mistake Stagnation for Progress? Self-Evaluation Bias and Externally Grounded Verification in Long-Running Autonomous LLM Agent Loops https://ax-news.com/?article=184376206 AX-NEWS en 2026-09-30T04:00:00+00:00 Event-based Scene Synthesis via Inter-Frame Residual Alignment https://ax-news.com/?article=184378994 AX-NEWS en 2026-09-30T04:00:00+00:00 From Answers to Policies: Efficient In-Context Learning System through Emulating Expert Investigation https://ax-news.com/?article=184379002 AX-NEWS en 2026-09-30T04:00:00+00:00 Root-Cause Attribution Is a Search Problem: Continual Search for Long-Horizon Agent Failures https://ax-news.com/?article=184379006 AX-NEWS en 2026-09-30T04:00:00+00:00 JEV-as-a-Judge: Accept When Confident, Escalate When Unsure https://ax-news.com/?article=184379016 AX-NEWS en 2026-09-30T04:00:00+00:00 Relic: From Multi-Agent Collaboration to Persistent Organizational Capability https://ax-news.com/?article=184375186 AX-NEWS en 2026-09-30T04:00:00+00:00 Joint Effects of GPU Server Topology, Parallelism, and Congestion Control on MoE Inference: A Controlled Simulation Study https://ax-news.com/?article=184375188 AX-NEWS en 2026-09-30T04:00:00+00:00 RLX: A Unified Multi-Backend Tensor Compiler and Distributed Runtime in Rust https://ax-news.com/?article=184375192 AX-NEWS en 2026-09-30T04:00:00+00:00 Quantifying Teleportation Overhead in Distributed Unitary Coupled-Cluster Ans\"atze https://ax-news.com/?article=184377963 AX-NEWS en 2026-09-30T04:00:00+00:00 HERO: Preserving Structure and Semantics in Heterogeneous Continual Graph Learning https://ax-news.com/?article=184377969 AX-NEWS en 2026-09-30T04:00:00+00:00 SHEFL: Sparse Heterogeneous Ensemble Federated Learning with Group-Balanced Aggregation https://ax-news.com/?article=184375201 AX-NEWS en 2026-09-30T04:00:00+00:00 Designing Dense Satellite Clusters for Distributed Space-based Datacenters https://ax-news.com/?article=184375203 AX-NEWS en 2026-09-30T04:00:00+00:00 ASCEND: Personal AI Agents for Autonomous Scientific Computing Across HPC Clusters and GPU Workstations https://ax-news.com/?article=184377472 AX-NEWS en 2026-09-30T04:00:00+00:00 Not All Rollouts Are Worth Learning: On Trajectory Valuation for Post-Training Reinforcement Learning https://ax-news.com/?article=184375212 AX-NEWS en 2026-09-30T04:00:00+00:00 Multi-Depth Temporal Fusion for Feedforward, Locally Trained Spiking Neural Networks https://ax-news.com/?article=184375213 AX-NEWS en 2026-09-30T04:00:00+00:00 Adaptive Rotation for iSOMA: Geometry, Benchmarking, and Noise Robustness in Variational Quantum Objectives https://ax-news.com/?article=184375215 AX-NEWS en 2026-09-30T04:00:00+00:00 HeurEvo: Agentic Evolution of Hybrid Solver-Augmented Heuristics for Time-Critical Mathematical Optimization https://ax-news.com/?article=184375220 AX-NEWS en 2026-09-30T04:00:00+00:00 Kolmogorov-Arnold Classifier Systems as Universal Approximators https://ax-news.com/?article=184375226 AX-NEWS en 2026-09-30T04:00:00+00:00 Dropout Universality: Scaling Laws and Optimal Scheduling at the Edge-of-Chaos https://ax-news.com/?article=184375230 AX-NEWS en 2026-09-30T04:00:00+00:00 Characterising the precision of a clock without any external time reference https://ax-news.com/?article=184375233 AX-NEWS en 2026-09-30T04:00:00+00:00 Quantum Fisher Information as the Speed Limit for Multipartite Entanglement https://ax-news.com/?article=184375242 AX-NEWS en 2026-09-30T04:00:00+00:00 Particles, Localization and "Collapse" https://ax-news.com/?article=184375253 AX-NEWS en 2026-09-30T04:00:00+00:00 Fewer Qubits, Better Choices: Coupling-Aware Sub-QUBO Selection for Quantum-Assisted Traffic Zone Partitioning https://ax-news.com/?article=184375254 AX-NEWS en 2026-09-30T04:00:00+00:00 Exact Gaussian Entanglement Dynamics and Initial-State Control in Coupled Parametric Oscillators https://ax-news.com/?article=184375255 AX-NEWS en 2026-09-30T04:00:00+00:00 Generation of arbitrary quantum states in cavity-atom systems with a three-level ancilla https://ax-news.com/?article=184375256 AX-NEWS en 2026-09-30T04:00:00+00:00 Quantum Machine Learning for Cybersecurity Applications: Simulation and Hardware Validation https://ax-news.com/?article=184375257 AX-NEWS en 2026-09-30T04:00:00+00:00 The wiring sets a phase-blind quantum memory's gap, the weight caps its coherence https://ax-news.com/?article=184375267 AX-NEWS en 2026-09-30T04:00:00+00:00 Preparation-controlled relaxation in an overdamped RLC circuit: A pedagogical route to the spectral Mpemba effect https://ax-news.com/?article=184375273 AX-NEWS en 2026-09-30T04:00:00+00:00 Terminal-Register Certification for Finite-Measurement Learning of Multiscale Quantum States https://ax-news.com/?article=184375278 AX-NEWS en 2026-09-30T04:00:00+00:00 Quantum data processing equality https://ax-news.com/?article=184375285 AX-NEWS en 2026-09-30T04:00:00+00:00 Nakayama's reduction of quantum topos and Bayesian quantum computing https://ax-news.com/?article=184375290 AX-NEWS en 2026-09-30T04:00:00+00:00 Observation of a topological edge state among localized bulk states in the anisotropic quantum Rabi model https://ax-news.com/?article=184375293 AX-NEWS en 2026-09-30T04:00:00+00:00 Coherence Rather Than Error Rate Governs Privacy in Multi-Tenant Quantum Computing https://ax-news.com/?article=184375294 AX-NEWS en 2026-09-30T04:00:00+00:00 Quantum Security of XOR of Permutations via Fourier Analysis https://ax-news.com/?article=184375302 AX-NEWS en 2026-09-30T04:00:00+00:00 Cubic Phase Gate with a Trapped Ion Oscillator https://ax-news.com/?article=184375312 AX-NEWS en 2026-09-30T04:00:00+00:00 Experimental quantum-computing-enhanced sensing using Grover's algorithm https://ax-news.com/?article=184375315 AX-NEWS en 2026-09-30T04:00:00+00:00 From Quantum to Classical Dissipative Spin Dynamics https://ax-news.com/?article=184375316 AX-NEWS en 2026-09-30T04:00:00+00:00 Accurate and bounded approximation of quantum correlation functions https://ax-news.com/?article=184375317 AX-NEWS en 2026-09-30T04:00:00+00:00 Asymptotically Good Quantum Codes with Addressable Transversal T Gates https://ax-news.com/?article=184375319 AX-NEWS en 2026-09-30T04:00:00+00:00 Weakly interacting fermionic Gibbs states are Gaussian mixtures and classically simulable https://ax-news.com/?article=184375321 AX-NEWS en 2026-09-30T04:00:00+00:00 Positronium Laser Deceleration, Cooling and Trapping https://ax-news.com/?article=184375329 AX-NEWS en 2026-09-30T04:00:00+00:00 Zero Knowledge Proofs in Quantum Networks https://ax-news.com/?article=184375331 AX-NEWS en 2026-09-30T04:00:00+00:00 Dilation theorem for continuum quantum stochastic processes https://ax-news.com/?article=184379020 AX-NEWS en 2026-09-30T04:00:00+00:00 GUITAR: Structured Failure Diagnosis of GUI Agents via State Transitions https://ax-news.com/?article=184375336 AX-NEWS en 2026-09-30T04:00:00+00:00 Fourier-Geometric Circuit Design for Gate and Entanglement Placement in Quantum Neural Networks https://ax-news.com/?article=184375341 AX-NEWS en 2026-09-30T04:00:00+00:00 Sublinear Copies Suffice for Fidelity Estimation with Pauli Measurements https://ax-news.com/?article=184375344 AX-NEWS en 2026-09-30T04:00:00+00:00 Exponential lower bounds for low-degree strategies in position-based quantum cryptography