AI news archive.
19,864 articles, newest first, from the outlets listed on the sources page.
- arXiv cs.AIresearchRethinking Pre-pretraining
arXiv:2610.40051v1 Announce Type: cross Abstract: We report that allocating compute to synthetic pre-pretraining (PPT) never outperforms pure natural-language training in our compute-matched experiments. This holds acros…
- arXiv cs.AIresearchOne Vector or Many? Clustered Optimal-Transport Steering under Quantization
arXiv:2610.40055v1 Announce Type: cross Abstract: Activation steering changes what a language model generates by editing its hidden states at inference time. Its most common form adds one vector, the difference of class…
- arXiv cs.AIresearchLocalizing Concepts in Visual Autoregressive Models
arXiv:2610.40061v1 Announce Type: cross Abstract: Understanding the internal routing of visual concepts is crucial for the safe and controllable adaptation of generative models. While concept localization has been widely…
- arXiv cs.AIresearchLearning Safe Flow Matching Robot Policies from Binary Feasibility Oracles
arXiv:2610.40075v1 Announce Type: cross Abstract: Robot foundation models increasingly rely on flow-based action generation for general-purpose manipulation, yet the generated actions are not guaranteed to satisfy physic…
- arXiv cs.AIresearchUpcycling Language Models for Multiple Specialized Domains
arXiv:2610.40091v1 Announce Type: cross Abstract: Effective multi-domain adaptation of large language models requires prioritizing relevant domain knowledge while minimizing interference from irrelevant domains. Existing…
- arXiv cs.AIresearchEscaping Path Mirages in Offline Goal-Conditioned Reinforcement Learning
arXiv:2610.40130v1 Announce Type: cross Abstract: Offline goal-conditioned reinforcement learning remains challenging in stochastic long-horizon settings, where compounding value estimation errors hinder reliable goal re…
- arXiv cs.AIresearchFARE: Factor-Aware Retrieval with Error-Guided Fusion for Retail Forecasting
arXiv:2610.40160v1 Announce Type: cross Abstract: Retail sales forecasting underpins inventory planning, yet promotions and calendar events reshape short-term demand. Although each factor usually has historical occurrenc…
- arXiv cs.AIresearchEventSeeColor: Learning to Reconstruct Color from Monochrome Events
arXiv:2610.40166v1 Announce Type: cross Abstract: Event cameras capture visual brightness changes under challenging lighting conditions. However, traditional event-based image reconstruction targets grayscale intensity a…
- arXiv cs.AIresearchUnderstanding axial attention in TSFMs through single location regression
arXiv:2610.40188v1 Announce Type: cross Abstract: Recent advances in Time Series Foundation Models (TSFMs) increasingly rely on axial attention mechanisms, but despite their empirical success, the theoretical properties…
- arXiv cs.AIagentsLearned Terminal Costs for Short-Horizon Model Predictive Control of Autonomous Trucks in Interactive Highway Traffic
arXiv:2610.40257v1 Announce Type: cross Abstract: Autonomous highway driving for heavy-duty trucks is a challenging control problem. The greater mass, dimensions and intricate dynamics increase the requirements for coope…
- arXiv cs.AIagentsTaskFrame: Connecting Task-Level Planning with Frame-Level Control for Game Agents
arXiv:2610.40276v1 Announce Type: cross Abstract: Building general game agents requires both high-level task reasoning and low-latency action control in rapidly changing visual environments. These capabilities favor mode…
- arXiv cs.AIresearchLatent Prediction Yields Cross-Subject Alignable Representations in Sensory-Evoked fMRI
arXiv:2610.40280v1 Announce Type: cross Abstract: Decoding sensory-evoked functional magnetic resonance imaging (fMRI) data is a central analytical tool in cognitive neuroscience. Here we ask whether self-supervised lear…
- arXiv cs.AIresearchOnly Accepted Tokens Count: An Energy Accounting of Speculative Decoding Under Latency Targets
arXiv:2610.40287v1 Announce Type: cross Abstract: Large language model serving is limited by facility power. Energy per token determines how many tokens a datacenter can serve, while a latency target bounds how quickly e…
- arXiv cs.AIresearchSelf-training for cross-centre coronary vessel segmentation in X-ray angiography using pre-contrast frame subtraction
arXiv:2610.40302v1 Announce Type: cross Abstract: Deep learning models for coronary vessel segmentation in X-ray angiography often perform poorly on data from centres that were not represented in training. Apart from dif…
- arXiv cs.AIresearchHammering with Vampire in Lean
arXiv:2610.40310v1 Announce Type: cross Abstract: We present Vampire-Hammer, a hammer for the Lean interactive theorem prover that discharges goals using the Vampire automated theorem prover and reconstructs proofs check…
- arXiv cs.AIresearchDecision and System One models in rheumatology: accuracy and calibration on specialty-training examination questions and diagnostic case vignettes
arXiv:2610.40318v1 Announce Type: cross Abstract: Objectives: To evaluate the accuracy and calibration of Decision and System One models on rheumatology examination questions and diagnostic vignettes. Methods: Two benchm…
- arXiv cs.AIresearchHow to Loop Your Transformer: Loop Scaling, Specialization, and Parallel Inference
arXiv:2610.40325v1 Announce Type: cross Abstract: Looping in transformer models reuses weights by repeatedly applying the same transformer, or parts of it, making the model deeper without increasing its parameter count.…
- arXiv cs.AIresearchRadiology Guideline-derived Decision Graph for Efficient Clinical Decision Support
arXiv:2610.40327v1 Announce Type: cross Abstract: Radiological risk stratification and management planning are essential downstream tasks in medical imaging. Automating these tasks is challenging because clinical guideli…
- arXiv cs.AIresearchA Unified Hessian-Guided Framework for Post-Training Quantization
arXiv:2610.40345v1 Announce Type: cross Abstract: Low-bit quantization enables efficient deployment of large language models by reducing memory footprint and computational cost. Achieving high accuracy at low precision r…
- arXiv cs.AIagentsThe Athlete as a Scientist of One: Agentic Bayesian Experimental Design for Individualized Physiology from Consumer Wearables
arXiv:2610.40370v1 Announce Type: cross Abstract: Large language model (LLM) agents for personal health read wearable data and recommend, but do not learn about the individual in a way that can be audited or falsified. W…
- arXiv cs.AIresearchScaling Mathematical Proof Supervision from Structured Textbooks
arXiv:2610.40394v1 Announce Type: cross Abstract: Mathematical supervision for language models is typically flattened into isolated problem-solution pairs, discarding the curricular organization and evidential structure…
- arXiv cs.AIresearchUnderstanding and Mitigating Role Spoofing in LLMs
arXiv:2610.40396v1 Announce Type: cross Abstract: Despite growing capabilities, LLMs remain susceptible to prompt injections: malicious inputs that can manipulate or hijack models. In particular, it has recently been obs…
- arXiv cs.AIresearchSCARL: Sequence Confidence-Aligned Reinforcement Learning
arXiv:2610.40407v1 Announce Type: cross Abstract: Reinforcement learning with verifiable rewards (RLVR) improves language-model reasoning by scoring sampled responses with a rule-based verifier and reinforcing those that…
- arXiv cs.AIresearchBridging Neural Representations and Symbolic Semantics in Audio Classification
arXiv:2610.40414v1 Announce Type: cross Abstract: Deep audio classifiers can achieve strong predictive performance, but their hidden representations remain difficult to interpret. Existing audio explainability methods of…
- arXiv cs.AIresearchIMPACT: Inverter-Informed Multimodal Learning for Photovoltaic Generation Forecasting
arXiv:2610.40418v1 Announce Type: cross Abstract: This work develops a physics-informed multimodal deep learning framework for 10- to 110-minute-ahead probabilistic photovoltaic power forecasting. The forecasting model i…
- arXiv cs.AIresearchNECA: Neighbor Event Curve Augmentation for Multi-Horizon ICU Deterioration Prediction
arXiv:2610.40420v2 Announce Type: replace-cross Abstract: Early prediction of ICU organ dysfunction events supports timely clinical monitoring and intervention, but estimating short-term organ-specific risk from early IC…
- arXiv cs.AIresearchMetaRefine: Score Refinement with Multi-Level Features for Image Assessment
arXiv:2610.40487v1 Announce Type: cross Abstract: An image's original dimensions, aspect ratio, and composition provide important cues that can affect its technical and aesthetic quality. Image assessment methods use res…
- arXiv cs.AIresearchFast and accurate neural triage decoding of ultra-high-rate quantum LDPC codes
arXiv:2610.40490v1 Announce Type: cross Abstract: Quantum error correction is essential for fault-tolerant quantum computing. High-rate quantum low-density parity-check (qLDPC) codes have emerged as a promising approach…
- arXiv cs.AIresearchAI in the EGI e-infrastructure -- Past experiences and future strategies
arXiv:2610.40494v1 Announce Type: cross Abstract: The EGI Federation has provided federated e-infrastructure services to European and global science for over 15 years. We review EGI's early experiences with AI in the int…
- arXiv cs.AIresearchHow I Aligned Your Model: Scaling Up Multilingual Safety Training with Templates
arXiv:2610.40516v1 Announce Type: cross Abstract: Safety alignment for Large Language Models is heavily focused on English with limited multilingual representation, particularly damaging low-resource language performance…
- arXiv cs.AIresearchBURGER: Benchmarking and Understanding Robotic Generalization via Embodied Drawing
arXiv:2610.40532v1 Announce Type: cross Abstract: How effectively can vision-language-action (VLA) models learn diverse language-conditioned behaviors as training data scales? Investigating this question requires large a…
- arXiv cs.AIagentsGym-Anything for Robotics: Scaling physical simulations with digital agents
arXiv:2610.40565v1 Announce Type: cross Abstract: Realistic, fast robotics simulations could enable large-scale training of embodied AI models that transfer to the real world. However, despite decades of progress, availa…
- arXiv cs.AIresearchMultistatic ISAC with Deep Learning-Based Clutter Suppression for 5G and Beyond
arXiv:2610.40586v1 Announce Type: cross Abstract: Integrated sensing and communications (ISAC) systems using 5G and beyond signals of opportunity enable joint wireless sensing and communication using shared infrastructur…
- arXiv cs.AIagentsWhen to Assist and What to Suggest: Joint Gating and Memory-Grounded Hint Generation in One Compact Decoder
arXiv:2610.40611v1 Announce Type: cross Abstract: Proactive assistants offer short, memory-grounded hints during a conversation, deciding when to assist and what to suggest. Current systems split this between a gate and…
- arXiv cs.AIresearchTextSeal2: Distortion-Free LLM Watermarking with Copula Mixing and Memoryless Races
arXiv:2610.40613v1 Announce Type: cross Abstract: We present TextSeal2, a distortion-free watermark for large language models that keeps its signal under speculative decoding: tokens that replace rejected drafts remain w…
- arXiv cs.AIresearchProbing Spatial State Representations in Visual Foundation Models
arXiv:2610.40636v1 Announce Type: cross Abstract: An observer sees only part of the surrounding world, yet must keep track of what lies beyond the current view. Spatial perception therefore involves more than recognizing…
- arXiv cs.AIagentsFrom extreme weather to agricultural consequences with agentic AI
arXiv:2610.40641v1 Announce Type: cross Abstract: Extreme weather is forecast days ahead, yet its consequences for agriculture remain hard to predict: a forecast says where a storm will strike, not which crops will suffe…
- arXiv cs.AIresearchLuggage re-identification: A study of strategies towards a real-world application
arXiv:2610.40643v1 Announce Type: cross Abstract: Luggage re-identification (ReID) is a critical task in video surveillance for forensics, security or border management (suspicious or abandoned luggage recognition), as w…
- arXiv cs.AIresearchRead, Allocate, Route: Role-Coupled Tokenization for Pixel-Space Generative Transformers
arXiv:2610.40647v1 Announce Type: cross Abstract: Pixel-space generative Transformers typically use one token per image patch, so capturing finer detail requires more tokens and makes global attention increasingly expens…
- arXiv cs.AIresearchRethinking Neural Thickets Without Weight Perturbations
arXiv:2610.40649v1 Announce Type: cross Abstract: The Neural Thickets hypothesis posits that pretrained language models lie in dense neighborhoods of task-specific experts in weight space, which random Gaussian perturbat…
- arXiv cs.AIresearchInvert4TVG: A Temporal Video Grounding Framework with Inversion Tasks Preserving Action Understanding Ability
arXiv:2508.07388v3 Announce Type: replace Abstract: Temporal Video Grounding (TVG) aims to localize video segments corresponding to a given textual query, which often describes human actions. However, we observe that cur…
- arXiv cs.AIresearchPrompts to Proxies: Emulating Human Preferences via a Compact LLM Ensemble
arXiv:2509.11311v3 Announce Type: replace Abstract: Large language models are increasingly used as proxies for human subjects in social science research, yet external validity requires matching the response distributions…
- arXiv cs.AIresearchPharos-ESG: A Framework for Multimodal Parsing, Contextual Narration, and Hierarchical Labeling of ESG Report
arXiv:2511.16417v4 Announce Type: replace Abstract: Environmental, Social, and Governance (ESG) principles are reshaping the foundations of global financial governance, transforming capital allocation architectures, regu…
- arXiv cs.AIresearchSandwich Reasoning: An Answer-Reasoning-Answer Approach for Low-Latency Query Correction
arXiv:2601.03672v2 Announce Type: replace Abstract: Query correction is a critical entry point in modern search pipelines, demanding high accuracy strictly within real-time latency constraints. Chain-of-Thought (CoT) rea…
- arXiv cs.AIresearchRoSeViT: Role-Separated Vision Transformers for ARC Visual Reasoning
arXiv:2601.13562v2 Announce Type: replace Abstract: ARC tasks can be formulated as visual transformation problems, where a model must infer a high-level transformation rule from a small set of demonstrations and apply it…
- arXiv cs.AIresearchDefining Operational Conditions for Safety-Critical AI-Based Systems from Data
arXiv:2601.22118v4 Announce Type: replace Abstract: Artificial Intelligence (AI) has been on the rise in many domains, including numerous safety-critical applications. However, for complex systems in the real world, defi…
- arXiv cs.AIagentsPRISM: Festina Lente Proactivity -- Risk-Sensitive, Uncertainty-Aware Deliberation for Proactive Agents
arXiv:2602.01532v2 Announce Type: replace Abstract: Proactive agents must decide not only what to say but also whether and when to intervene. Many current systems rely on brittle heuristics or indiscriminate long reasoni…
- arXiv cs.AIresearchPRISM: Pushing the Frontier of Deep Think via Process Reward Model-Guided Inference
arXiv:2603.02479v2 Announce Type: replace Abstract: DEEPTHINK methods improve reasoning by generating, refining, and aggregating populations of candidate solutions, which enables strong performance on complex mathematica…
- arXiv cs.AIresearchMuQ-Eval: An Open-Source Per-Sample Quality Metric for AI Music Generation Evaluation
arXiv:2603.22677v2 Announce Type: replace Abstract: Distributional metrics such as Fr\'echet Audio Distance cannot score individual music clips and correlate poorly with human judgments, while the only per-sample learned…
- arXiv cs.AIagentsLearning to Model Optimization Problems from Solver Outcomes
arXiv:2604.00442v2 Announce Type: replace Abstract: Automating optimization modeling with LLMs is a promising path toward scalable decision intelligence, but existing approaches either rely on agentic pipelines built on…