Artificial Intelligence news — Wednesday 07 October 2026

AI Business 19:46 UTC

Nvidia-backed open source startup makes splashy entrance. AI hits U.S. K-8 education.

AI Business 17:07 UTC

Process Intelligence helps organizations provide AI agents with the right context and data needed to know how their businesses run.

AI Business 16:11 UTC

As AI moves into K-8 instruction, district technology leaders must weigh external evidence, data protection and results-based contracts before scaling these systems.

Towards Data Science 15:30 UTC

A well-built MMM can still be wrong, because the spend it learns from never held the information it needs. This article tests whether changing when you spend, not how much, can fix that. The post How Wrong Is Your Marketing Mix Model…

AI Business 15:24 UTC

AI adoption in the public sector is on the rise, but data, legacy systems and governance remain barriers to effectively scaling the tech.

Towards Data Science 14:00 UTC

When machines learn by themselves The post Introduction to Reinforcement Learning: Multi-Armed Bandit Simulation in Python appeared first on Towards Data Science .

Towards Data Science 12:30 UTC

Mapping structural variance against execution outputs to estimate coding agent reliability without ground truth. The post The Consistency Quadrant: A Visual Guide to LLM Reliability appeared first on Towards Data Science .

MIT Technology Review Biotech 12:10 UTC

This is today’s edition of The Download , our weekday newsletter that provides a daily dose of what’s going on in the world of technology. Weight-loss drugs show signs of slowing biological aging, say drugmakers Popular weight-loss drugs…

OpenAI Blog 12:00 UTC

College Planner is coming to ChatGPT for Teens to help students manage college applications, alongside new flashcards, quizzes, and a teen AI council.

Towards Data Science 11:00 UTC

I put a physics-informed neural network up against a plain finite-difference solver twice: once in 1D and once in 5D. The winner changed. The post When Do PINNs Beat Classical Numerical Methods? A 1D vs 5D Experiment appeared first on…

OpenAI Blog 07:00 UTC

Radisson partnered with Accenture to build a ChatGPT plugin using OpenAI technology, helping travelers find, compare, and book hotels while planning their trips.

arXiv cs.CV 04:00 UTC

arXiv:2610.08070v1 Announce Type: new Abstract: Recent diffusion-based image generation backbones have grown substantially in scale, making the network inference cost increase rapidly. While diffusion distillation techniques can reduce the…

arXiv cs.CV 04:00 UTC

arXiv:2610.07987v1 Announce Type: new Abstract: Multimodal large language models have become the dominant paradigm for visual understanding, but incur substantial costs by encoding inputs into dense, fixed-size patch tokens. However…

arXiv cs.CV 04:00 UTC

arXiv:2607.15271v2 Announce Type: replace Abstract: Online novel view synthesis from multi-view streaming videos faces a fundamental trade-off: maintaining a persistent, long-horizon memory to reconstruct temporarily occluded regions while…

arXiv cs.CV 04:00 UTC

arXiv:2610.07802v1 Announce Type: new Abstract: Bird monitoring in natural environments is challenging due to the small size of some species of birds relative to the scene, background clutter, variability in illumination, and the…

arXiv cs.CV 04:00 UTC

arXiv:2610.07795v1 Announce Type: new Abstract: This paper presents a novel effective Gaussian Splatting (GS) sequence Compression method that utilizes the Video codec (GSCV). Existing video-based GS sequence compression relies on the…

arXiv cs.CV 04:00 UTC

arXiv:2610.08433v1 Announce Type: new Abstract: Modern action recognition models rely on video transformers pretrained on massive collections of web-crawled videos, such as Kinetics-700. However, the use of such data raises ethical…

arXiv cs.CL 04:00 UTC

arXiv:2610.03025v2 Announce Type: replace-cross Abstract: What makes a short story gripping; a news article newsworthy; or a math proof elegant? These constructs resist articulation or verification; their meaning is at least partially…

arXiv cs.CV 04:00 UTC

arXiv:2610.07694v1 Announce Type: new Abstract: The integrative analysis of histopathological Whole-Slide Images (WSIs) and transcriptomic profiles holds significant promise for cancer survival prediction. However, existing methods…

arXiv cs.CL 04:00 UTC

arXiv:2610.06889v1 Announce Type: new Abstract: We study the application of large language models (LLMs) to the visual exploration of textual corpora. We introduce zero-shot visualization (ZSV), a task in which users specify concepts in…

arXiv cs.CV 04:00 UTC

arXiv:2610.07903v1 Announce Type: new Abstract: Adapting vision-language models to downstream tasks has achieved remarkable success by leveraging pseudo-labels generated from unlabeled data. Existing methods typically assume a uniform…

arXiv cs.CV 04:00 UTC

arXiv:2608.27550v2 Announce Type: replace-cross Abstract: Scaling robot data is crucial for building generalist Vision-Language-Action (VLA) models, yet robot trajectories are harder to scale than web-scale image-text data because embodied…

arXiv cs.LG 04:00 UTC

arXiv:2610.08355v1 Announce Type: new Abstract: Flow-matching models start from an isotropic Gaussian source, the standard choice when the correlation structure of the data is unknown in advance. For multi-channel brain recordings…

arXiv cs.LG 04:00 UTC

arXiv:2610.08745v1 Announce Type: new Abstract: We study linear bandits under exact sliding-window constraints, where every consecutive block of actions must belong to a prescribed feasible set. In the offline setting, where the reward…

arXiv cs.CL 04:00 UTC

arXiv:2610.07032v1 Announce Type: new Abstract: Large-scale pretrained transformer models have achieved state-of-the-art performance across diverse machine translation tasks, including multilingual settings. Knowledge distillation has…

arXiv cs.CL 04:00 UTC

arXiv:2610.07109v1 Announce Type: new Abstract: When an LLM judge scores an output, its score distribution retains uncertainty and disagreement information that is lost after scalar compression. We introduce JudgeMoE, a lightweight…

arXiv cs.CL 04:00 UTC

arXiv:2610.07186v1 Announce Type: new Abstract: Large language models make claims about themselves that are both consequential and increasingly difficult to verify from behavior alone. How can we distinguish plausible confabulations from…

arXiv cs.CL 04:00 UTC

arXiv:2610.07587v1 Announce Type: new Abstract: LLM orchestration investigates how an orchestrator coordinates a group of autonomous agents to achieve common goals or maximize collective welfare. The agents are typically heterogeneous…

arXiv cs.CL 04:00 UTC

arXiv:2610.08208v1 Announce Type: new Abstract: We introduce STRUCTURALCOST, a self-paced reading dataset of 475 participants and 40,800 observations isolating the processing cost of long-distance subject-verb dependency resolution. We…

arXiv cs.CL 04:00 UTC

arXiv:2610.08303v1 Announce Type: new Abstract: Current evaluation of multilingual Large Language Models (LLMs) rests on an implicit Translation-Isomorphism Assumption (TIA): that semantic structures across languages are congruent and…

arXiv cs.CL 04:00 UTC

arXiv:2610.08660v1 Announce Type: new Abstract: Background: Biomedical AI can generate plausible explanations without reliably verifying whether each statement is supported by patient-specific evidence. We developed a neuro-semantic…

arXiv cs.CL 04:00 UTC

arXiv:2610.08719v1 Announce Type: new Abstract: Reusing the scores that select a Best-of-$N$ winner can overstate its expected reward. We study evaluation from a fixed matrix of $K$ independent scores per candidate for a policy that…

arXiv cs.CL 04:00 UTC

arXiv:2610.06971v1 Announce Type: cross Abstract: Traditional data pipelines are notoriously brittle, often failing due to upstream schema drift, API contract changes, or website DOM modifications. Present observability tools only raise…

arXiv cs.CL 04:00 UTC

arXiv:2610.07091v1 Announce Type: cross Abstract: The evolution of machine learning has progressively changed where intelligence resides in an AI system. In conventional machine learning the task, data representation, labels and model…

arXiv cs.AI 04:00 UTC

arXiv:2610.05334v1 Announce Type: new Abstract: Frameworks that use large language models for scientific discovery typically rely on a fixed, human-designed algorithm that decides what the model sees at each step, leaving the model only…

arXiv cs.CV 04:00 UTC

arXiv:2512.23073v2 Announce Type: replace-cross Abstract: Fine-tuning has become the dominant paradigm for adapting Vision-Language Models (VLMs), yet most approaches rely on explicit weight updates that introduce a fundamental trade-off…

arXiv cs.CV 04:00 UTC

arXiv:2610.03797v2 Announce Type: replace Abstract: World Action Models (WAMs) leverage pretrained video foundation models for robot manipulation, but their large backbones and video-action co-prediction are expensive. Although existing…

arXiv cs.CV 04:00 UTC

arXiv:2609.31234v2 Announce Type: replace Abstract: Problem. Ultra-high-resolution (UHR) remote sensing with vague user intents has two bottlenecks: visual tokens are expensive, and tool calling must be format-reliable (pretrained models…

arXiv cs.CV 04:00 UTC

arXiv:2610.07269v1 Announce Type: new Abstract: Cross-view geo-localization is commonly solved as an image retrieval problem, matching a ground-level image against a database of satellite tiles through a jointly trained embedding. Such…

arXiv cs.CV 04:00 UTC

arXiv:2610.07783v1 Announce Type: new Abstract: Bird's-eye-view (BEV) representations have become a widely used interface between perception and planning in autonomous driving, but they encode what is in a scene, not what is behaviorally…

arXiv cs.CL 04:00 UTC

arXiv:2610.01108v2 Announce Type: replace Abstract: Retrieval-based speculative decoding (SD) drafts tokens by copying continuations from existing text, which suits coding agents that repeatedly reproduce code, logs, and earlier attempts…

arXiv cs.CL 04:00 UTC

arXiv:2610.08388v1 Announce Type: new Abstract: Large language models (LLMs) have demonstrated strong capabilities in question answering, yet they still frequently suffer from hallucinations on knowledge-intensive tasks. Knowledge graphs…

arXiv cs.CV 04:00 UTC

arXiv:2605.06021v2 Announce Type: replace Abstract: Systematic reviews and meta-analyses often need numerical data reported only in figures, and extracting them with interactive digitisers usually requires a person to select and calibrate…

arXiv cs.CV 04:00 UTC

arXiv:2602.14512v3 Announce Type: replace Abstract: Autoregressive pretraining has been key to the scalability of large language models, yet medical generative foundation models remain predominantly based on diffusion. Here we introduce…

arXiv cs.CV 04:00 UTC

arXiv:2610.07117v1 Announce Type: new Abstract: Understanding and modeling interactions between autonomous agents is a fundamental challenge in robotics, with broad implications for collaborative systems, social robotics, and human-robot…

arXiv cs.LG 04:00 UTC

arXiv:2610.07825v1 Announce Type: cross Abstract: Time series forecasting models are typically compared on pointwise error, which scores a prediction in isolation from the decision it is produced for, and a lower forecast error does not…

arXiv cs.CV 04:00 UTC

arXiv:2610.08526v1 Announce Type: cross Abstract: Vision-Language-Action (VLA) models have achieved impressive results in robotic manipulation and ground-mobile navigation, yet language-conditioned control of unmanned aerial vehicles…

arXiv cs.CV 04:00 UTC

arXiv:2610.07110v1 Announce Type: new Abstract: High-quality 3D reconstruction of lunar terrain from sparse rover images is indispensable for autonomous lunar exploration, but remains challenging because viewpoint overlap is insufficient…

arXiv cs.CV 04:00 UTC

arXiv:2610.07698v1 Announce Type: new Abstract: Accurate building footprint extraction from high-resolution remote sensing imagery is essential for urban planning, disaster response, and environmental monitoring. However, obtaining dense…

arXiv cs.CV 04:00 UTC

arXiv:2610.07444v1 Announce Type: cross Abstract: A GUI agent decides which action to take and where to take it; we ask how a small grounding model should receive the action type. Fine-tuning Qwen2-VL-2B with LoRA on Android in the Wild…

arXiv cs.CV 04:00 UTC

arXiv:2610.07217v1 Announce Type: cross Abstract: Despite its promise for scaling robot learning, egocentric manipulation data is still scarce today. Collection at scale requires vertically integrating ergonomic hardware with…

arXiv cs.CV 04:00 UTC

arXiv:2610.07059v1 Announce Type: new Abstract: Yield forecasts help planners and farmers decide on inputs, storage and imports, but small agricultural tables can make reported accuracy fail on a new season. We built a crop-yield prototype…

arXiv cs.LG 04:00 UTC

arXiv:2610.06950v1 Announce Type: new Abstract: Injecting skills into a frozen language model currently costs a million parameters and a reinforcement-learning pipeline. We introduce \method{}, a System-1 decision operator trained by…

arXiv cs.LG 04:00 UTC

arXiv:2610.06861v1 Announce Type: new Abstract: Reinforcement learning with verifiable rewards (RLVR) has become the dominant paradigm for eliciting multi-step reasoning in large language models, and a recent wave of methods (LUFFY, ExPO…

arXiv cs.CV 04:00 UTC

arXiv:2610.07091v1 Announce Type: cross Abstract: The evolution of machine learning has progressively changed where intelligence resides in an AI system. In conventional machine learning the task, data representation, labels and model…

arXiv cs.CL 04:00 UTC

arXiv:2609.37858v2 Announce Type: replace-cross Abstract: Many localized large language model (LLM) unlearning methods select a small parameter subset from a localization signal and keep it fixed during optimization. The parameters most…

arXiv cs.LG 04:00 UTC

arXiv:2610.06980v1 Announce Type: new Abstract: Sensing technologies have advanced rapidly across industries ranging from energy to automotive manufacturing. These systems generate high-dimensional (HD) data characterized by complex…

arXiv cs.LG 04:00 UTC

arXiv:2610.06989v1 Announce Type: new Abstract: Pavement agencies must translate a spatially distributed distress inventory into a bounded, actionable repair-lot plan: accident-critical defects (potholes) must always be addressed…

arXiv cs.LG 04:00 UTC

arXiv:2610.07033v1 Announce Type: new Abstract: Predicting transient urban winds is fundamental to understanding urban microclimates and designing climate-resilient cities. Building-resolving large-eddy simulation produces detailed…

arXiv cs.LG 04:00 UTC

arXiv:2610.07323v1 Announce Type: new Abstract: Security evaluation of learning-based systems requires more than just testing the system against a fixed collection of attacks. It requires adaptive mechanisms that can efficiently discover…

arXiv cs.LG 04:00 UTC

arXiv:2610.07405v1 Announce Type: new Abstract: pass@$k$, the fraction of problems a model solves within $k$ sampled attempts, is the field's default protocol for deciding whether reinforcement-learning (RL) post-training on verifiable…

arXiv cs.LG 04:00 UTC

arXiv:2610.07444v1 Announce Type: new Abstract: A GUI agent decides which action to take and where to take it; we ask how a small grounding model should receive the action type. Fine-tuning Qwen2-VL-2B with LoRA on Android in the Wild, we…

arXiv cs.LG 04:00 UTC

arXiv:2610.07499v1 Announce Type: new Abstract: Multimodal wearable systems must remain reliable when sensor streams become noisy or unavailable. Existing multimodal test-time adaptation (TTA) methods often assess reliability online, but…

arXiv cs.LG 04:00 UTC

arXiv:2610.07555v1 Announce Type: new Abstract: Optimal-transport couplings have been shown to reduce training variance in unconditional flow models, but their role in conditional generation remains unclear. A natural approach constructs…

arXiv cs.LG 04:00 UTC

arXiv:2610.07804v1 Announce Type: new Abstract: Prior Fitted Networks (PFNs) such as TabPFN now rival established statistical procedures across prediction and estimation tasks. A natural explanation is that PFNs have the property of…

arXiv cs.LG 04:00 UTC

arXiv:2610.07792v1 Announce Type: new Abstract: Large language model agents are increasingly deployed to perform complex tasks in real-world environments. However, the knowledge required for correct behavior in these environments is often…

arXiv cs.LG 04:00 UTC

arXiv:2610.07810v1 Announce Type: new Abstract: Search filters help guests navigate vast catalogs in two-sided marketplaces like Airbnb, and recommending the right filters can meaningfully lift booking conversion. Many such production…

arXiv cs.LG 04:00 UTC

arXiv:2610.07910v1 Announce Type: new Abstract: Deep Reinforcement Learning policies can produce nonsmooth action oscillations that hinder deployment on physical robots. Existing architectural and penalty-based approaches seek spatial…

arXiv cs.LG 04:00 UTC

arXiv:2610.07981v1 Announce Type: new Abstract: Higher-order models (e.g., hypergraph neural networks) often outperform lower-order baselines on hypergraph learning benchmarks, and their advantages are commonly attributed to their ability…

arXiv cs.LG 04:00 UTC

arXiv:2610.08069v1 Announce Type: new Abstract: A mean shift between two data sources can be easy to detect but hard to remove without substantially changing their representations. We cast its removal as a statistical decision problem…

arXiv cs.LG 04:00 UTC

arXiv:2610.08200v1 Announce Type: new Abstract: We ask whether specific attention heads, and more finely specific neurons inside those heads, are responsible for recognizing that a language model's context contains network infrastructure…

arXiv cs.LG 04:00 UTC

arXiv:2610.06880v1 Announce Type: new Abstract: Machine learning classifiers for bearing fault detection produce scalar confidence scores that conflate confident errors with genuinely ambiguous predictions, and the conventional…

arXiv cs.LG 04:00 UTC

arXiv:2610.08367v1 Announce Type: new Abstract: Several discrete design tasks, such as molecular discovery, require diverse collections of useful candidates at low computational cost. High validity alone does not guarantee a useful…

arXiv cs.LG 04:00 UTC

arXiv:2610.08561v1 Announce Type: new Abstract: Reinforcement learning (RL) has become a standard tool for post-training language models on reasoning tasks, where the policy is updated by reward feedback while exploring the space of…

arXiv cs.LG 04:00 UTC

arXiv:2610.08565v1 Announce Type: new Abstract: This article is a geometric rediscovery of the singular value decomposition, with a further claim: the construction it builds is the machinery behind much of machine learning. The same…

arXiv cs.CV 04:00 UTC

arXiv:2610.08539v1 Announce Type: new Abstract: Remote sensing scene classification is a fundamental task in Earth observation and geospatial analysis. Existing approaches mainly follow three paradigms: task-specific visual classification…

arXiv cs.LG 04:00 UTC

arXiv:2610.06858v1 Announce Type: cross Abstract: This demo paper presents the conceptual foundations and the first steps towards implementation of a novel no-code solution for movement data analytics based on the open-source Python…

arXiv cs.LG 04:00 UTC

arXiv:2610.06919v1 Announce Type: cross Abstract: This paper concerns how semantic context determines geometry in learned vector representations. Similarity is typically measured using cosine similarity, which provides a single fixed…

arXiv cs.LG 04:00 UTC

arXiv:2610.07005v1 Announce Type: cross Abstract: We audit frequency and decoder-depth claims for AdvWave-P, an additive audio jailbreak, on Qwen2-Audio. The protocol masks frequency components of the perturbation in the short-time Fourier…

arXiv cs.LG 04:00 UTC

arXiv:2610.07037v1 Announce Type: cross Abstract: AlphaFold 3-style cofolding models predict biomolecular complexes with high structural accuracy, yet a large fraction of their outputs are physically invalid: chains overlap at interfaces…

arXiv cs.LG 04:00 UTC

arXiv:2610.07094v1 Announce Type: cross Abstract: LLM deployment is shifting from single-turn completion to agentic trajectories in which a model plans, calls tools, reads results and reasons at test time before acting. This inverts the…

arXiv cs.LG 04:00 UTC

arXiv:2610.07130v1 Announce Type: cross Abstract: We placed a modern AI coding assistant in an unintended role: as the mind of a body on an unknown digital island. With only a minimal instruction mentioning no specific task, reward, or…

arXiv cs.LG 04:00 UTC

arXiv:2610.07269v1 Announce Type: cross Abstract: Cross-view geo-localization is commonly solved as an image retrieval problem, matching a ground-level image against a database of satellite tiles through a jointly trained embedding. Such…

arXiv cs.LG 04:00 UTC

arXiv:2610.07258v1 Announce Type: cross Abstract: Enterprise AI agents that share a memory store face two unaddressed risks: sensitive data can leak through legitimately computed results the requester could not derive, and departments can…

arXiv cs.LG 04:00 UTC

arXiv:2610.07388v1 Announce Type: cross Abstract: Joint Models simultaneously model longitudinal and survival outcomes, leveraging patterns in patients' longitudinal trajectory to improve the prediction of survival outcomes. The classical…

arXiv cs.LG 04:00 UTC

arXiv:2610.07383v1 Announce Type: cross Abstract: Synthetic patient data generation is a promising solution to the dual challenge of data scarcity and privacy constraints in healthcare machine learning. Realistic synthesis of patient-level…

arXiv cs.LG 04:00 UTC

arXiv:2610.07497v1 Announce Type: cross Abstract: Muon combines current and past gradients into matrix momentum. For $M=U\Sigma V^\top$, the idealized polar update $Q=UV^\top$ gives every singular direction the same weight. We refer to…

arXiv cs.LG 04:00 UTC

arXiv:2610.07533v1 Announce Type: cross Abstract: Audio language models must handle dozens of distinct skills, from pitch comparison and speaker counting to musical tempo estimation and emotion recognition. Joint training on all skills at…

arXiv cs.AI 04:00 UTC

arXiv:2610.06765v1 Announce Type: new Abstract: Medical question answering spans specialties and clinical operations that may benefit from different adaptation directions. We propose ARBOR, a parameter-efficient method that selects…

arXiv cs.LG 04:00 UTC

arXiv:2610.08020v1 Announce Type: cross Abstract: Classical force fields (FFs) remain the workhorse for large-scale simulations even as machine-learned interatomic potentials (MLIPs) approach ab initio accuracy. They decompose total…

arXiv cs.LG 04:00 UTC

arXiv:2610.08077v1 Announce Type: cross Abstract: Reinforcement learning with verifiable rewards (RLVR) turns agent experience into learning signals primarily through scalar outcome rewards after interaction. For group-relative objectives…

arXiv cs.LG 04:00 UTC

arXiv:2610.08078v1 Announce Type: cross Abstract: Standard causal identification methods often assume no unmeasured confounding and can fail when relevant confounders are unobserved. Proximal causal inference instead uses proxy variables…

arXiv cs.LG 04:00 UTC

arXiv:2610.08123v1 Announce Type: cross Abstract: End-to-end planners based on waypoint regression achieve strong open-loop accuracy, but they primarily learn to mimic expert geometry and remain difficult to adapt to deployment-time safety…

arXiv cs.LG 04:00 UTC

arXiv:2610.08268v1 Announce Type: cross Abstract: Pervasive intelligent applications are increasingly deployed on mobile and Internet of Things (IoT) edge devices. Consequently, Large Language Models (LLMs) are increasingly used to support…

arXiv cs.LG 04:00 UTC

arXiv:2610.08337v1 Announce Type: cross Abstract: Public redispatch records provide empirical data for grid congestion forecasting, but delayed reporting, zero-inflated distributions, and temporal shift present major modeling challenges…

arXiv cs.LG 04:00 UTC

arXiv:2610.08345v1 Announce Type: cross Abstract: Using a replica-symmetric high-dimensional characterization, we develop an inferential framework for sparse support vector machines when the sample size and number of features grow…

arXiv cs.LG 04:00 UTC

arXiv:2610.08540v1 Announce Type: cross Abstract: Whether alignment gets easier or harder as models grow is often argued from isolated findings, as if alignment were one property. We treat it as a family of measurable scaling relations…

arXiv cs.LG 04:00 UTC

arXiv:2610.08560v1 Announce Type: cross Abstract: Streaming video-language models must decide not only what to answer, but whether the evidence needed for the current question has arrived. Existing systems learn that decision as a separate…

arXiv cs.LG 04:00 UTC

arXiv:2610.08571v1 Announce Type: cross Abstract: Retrieval-Augmented Generation (RAG) systems are vulnerable to prompt-injection attacks embedded in retrieved content. We introduce RAG-PIBench, a benchmark for RAG-style prompt-injection…

arXiv cs.CV 04:00 UTC

arXiv:2610.06919v1 Announce Type: cross Abstract: This paper concerns how semantic context determines geometry in learned vector representations. Similarity is typically measured using cosine similarity, which provides a single fixed…

arXiv cs.CV 04:00 UTC

arXiv:2610.06938v1 Announce Type: new Abstract: Medical image segmentation remains fragmented along two axes: segmentation paradigms and data dimensionality. Existing methods are typically developed separately for semantic, in-context, and…

arXiv cs.CV 04:00 UTC

arXiv:2610.06978v1 Announce Type: new Abstract: Gaussian Belief Propagation (GBP) is a distributed inference algorithm that passes messages in graphical models, making it attractive for scalable spatial intelligence. However, we find GBP…

arXiv cs.CL 04:00 UTC

arXiv:2604.20658v2 Announce Type: replace Abstract: Multi-agent systems built from teams of large language models (LLMs) are increasingly deployed for collaborative scientific reasoning and problem-solving. These systems require agents to…

arXiv cs.CL 04:00 UTC

arXiv:2609.09815v2 Announce Type: replace-cross Abstract: Compound LLM systems often solve a coordination problem by adding a higher-level LLM. The resulting meta-agent reads workers' outputs, writes the final answer, allocates later…

arXiv cs.CL 04:00 UTC

arXiv:2602.18899v4 Announce Type: replace-cross Abstract: Self-supervised speech models (S3Ms) are known to encode rich phonetic information, yet how this information is structured remains underexplored. We conduct a comprehensive study…

arXiv cs.CV 04:00 UTC

arXiv:2610.08674v1 Announce Type: new Abstract: Current large video-language models (LVLMs) still face challenges when dealing with long videos, mainly because frames are often processed independently, making it difficult to capture…

arXiv cs.CL 04:00 UTC

arXiv:2511.20718v3 Announce Type: replace-cross Abstract: Reinforcement learning (RL) algorithms such as PPO and GRPO are widely used to train large language models (LLMs) for multi-turn agentic tasks. However, in off-policy training…

arXiv cs.CL 04:00 UTC

arXiv:2606.06840v2 Announce Type: replace Abstract: Reasoning-trained language models can perform, zero-shot, multi-label tasks that require selecting a small set of relevant labels from a universe of thousands to hundreds of thousands of…

arXiv cs.CV 04:00 UTC

arXiv:2610.08620v1 Announce Type: new Abstract: High-beam-count LiDAR sensors are costly, yet many perception pipelines require dense angular sampling. Using a pretrained Stable Diffusion model as the backbone, we fine-tune a…

arXiv cs.CV 04:00 UTC

arXiv:2610.06945v1 Announce Type: new Abstract: Mechanistic interpretability often relies on the Linear Representation Hypothesis (LRH), which assumes that high-level concepts are encoded as linear directions in activation space. Yet a…

arXiv cs.CL 04:00 UTC

arXiv:2510.22954v2 Announce Type: replace Abstract: Language models (LMs) often struggle to generate diverse, human-like creative content, raising concerns about the long-term homogenization of human thought through repeated exposure to…

arXiv cs.CL 04:00 UTC

arXiv:2503.22764v3 Announce Type: replace Abstract: The large language model (LLM) is typically integrated into the mainstream optimization protocol. However, it remains underexplored whether maintaining the model integrity is…

arXiv cs.CV 04:00 UTC

arXiv:2610.08560v1 Announce Type: new Abstract: Streaming video-language models must decide not only what to answer, but whether the evidence needed for the current question has arrived. Existing systems learn that decision as a separate…

arXiv cs.LG 04:00 UTC

arXiv:2509.03647v3 Announce Type: replace-cross Abstract: Large language models (LLMs) increasingly serve as automated evaluators, yet they suffer from "self-preference bias": a tendency to favor their own outputs over those of other…

arXiv cs.LG 04:00 UTC

arXiv:2501.18158v4 Announce Type: replace-cross Abstract: Cryptocurrencies are widely used, yet current methods for analyzing transactions often rely on opaque, black-box models. While these models may achieve high performance, their…

arXiv cs.CL 04:00 UTC

arXiv:2610.08647v1 Announce Type: cross Abstract: LLM-based agents solve complex multi-step tasks, but sequential execution incurs substantial latency. In principle, parallelizing work across multiple agents should yield near-linear…

arXiv cs.LG 04:00 UTC

arXiv:2407.07111v2 Announce Type: replace-cross Abstract: The rapid development of diffusion models (DMs) has significantly advanced image and video applications, making "what you want is what you see" a reality. Among these, video editing…

arXiv cs.LG 04:00 UTC

arXiv:2610.04946v2 Announce Type: replace Abstract: Cross-system transfer of longitudinal Electronic Health Record (EHR) representations is challenging because clinical coding, patient populations, and healthcare workflows differ…

arXiv cs.CL 04:00 UTC

arXiv:2610.08560v1 Announce Type: cross Abstract: Streaming video-language models must decide not only what to answer, but whether the evidence needed for the current question has arrived. Existing systems learn that decision as a separate…

arXiv cs.LG 04:00 UTC

arXiv:2605.05780v2 Announce Type: replace-cross Abstract: In the mid-twentieth century, mathematician and polymath John von Neumann created a computational system on an array of cells as a simple model of the human brain, where each cell…

arXiv cs.LG 04:00 UTC

arXiv:2608.09972v2 Announce Type: replace-cross Abstract: AI weather models are often reported to underestimate extremes, but most evidence concerns deterministic regression models verified against reanalysis. We evaluate twelve physical…

arXiv cs.LG 04:00 UTC

arXiv:2608.19693v2 Announce Type: replace-cross Abstract: Sparse keypoint extraction and matching underpin core tasks in geometric computer vision, including structure-from-motion, visual SLAM, augmented reality, and medical image…

arXiv cs.CV 04:00 UTC

arXiv:2610.08518v1 Announce Type: new Abstract: Many modern learning approaches are still struggling with spatial reasoning tasks, i.e. they lack the ability to utilize geometric information of perceived entities and their spatial relation…