AI news archive.
19,861 articles, newest first, from the outlets listed on the sources page.
- arXiv cs.AIresearchEnhanced Detective: A Dual-Stage Proactive Defense Against Internal Poisoning Attacks in Financial Fraud Detection Using Federated Learning
arXiv:2610.17523v1 Announce Type: cross Abstract: With recent developments in Artificial Intelligence (AI), the adoption of distributed learning paradigms such as Federated Learning (FL) has emerged. In simple terms, FL…
- arXiv cs.AIresearchBox-WAM: Box Trajectories as Compact State Representations for World Action Models
arXiv:2610.17526v1 Announce Type: cross Abstract: World action models (WAMs) are a category of policy models that ex- plicitly predict both actions and future world states. They have been shown to outperform action-only…
- arXiv cs.AIresearchTowards Green AI: Evaluating Energy Efficiency for Quantized LLM Inference
arXiv:2610.17531v1 Announce Type: cross Abstract: While it is known that quantization of large language models (LLMs) reduces memory usage via lower-bit weights, studies quantifying the resulting impact on energy usage a…
- arXiv cs.AIresearchConvex-Analytic View of Query Selection for Safety Verification of Markov Decision Processes
arXiv:2610.17541v1 Announce Type: cross Abstract: Safety verification of a Markov decision process (MDP) asks whether the probabilities of reaching several failure states jointly lie in a convex safe region under every s…
- arXiv cs.AIagentsMany Steps into One: Reasoning Contraction and the Limits of Safe Memory Reuse for LLM Agents
arXiv:2610.17544v2 Announce Type: replace-cross Abstract: Thought templates, skill libraries, agent memories and caches turn many reasoning steps into one. We call this reasoning contraction. A contracted memory saves re…
- arXiv cs.AIresearchFlashVSR+: Efficient Video Super-Resolution via Hybrid Attention and Reward-Yield Distribution Matching
arXiv:2610.17552v1 Announce Type: cross Abstract: Recent video super-resolution (VSR) models achieve efficient one-step generation through diffusion distillation. However, high-resolution inference remains costly, and di…
- arXiv cs.AIresearchBenchmarking Self-Supervised 3D Medical Vision Foundation Models and Transferability Estimation
arXiv:2610.17573v1 Announce Type: cross Abstract: Self-supervised pretraining has expanded the pool of 3D medical foundation models, but published evaluations use different datasets, endpoints and fine-tuning protocols.…
- arXiv cs.AIresearchDissociating Answerability from Extraction in LLM Question Answering over Radiology Reports
arXiv:2610.17576v1 Announce Type: cross Abstract: Answering questions from radiology reports involves two decisions: whether the report contains an answer and which span gives it. A false answer presents an unsupported c…
- arXiv cs.AIresearchChasing Label Shifters: A Change-Aware Framework for Dynamic Graph Node Classification
arXiv:2610.17582v1 Announce Type: cross Abstract: Entities in real-world systems often evolve over time: users shift between information consumption patterns, researchers migrate between fields, and firms transition betw…
- arXiv cs.AIresearchTaming Softmax at the Limits of Muon: A Unified Approach through Hilbert Geometry
arXiv:2610.17588v1 Announce Type: cross Abstract: Muon controls weight updates through the RMS movement of a linear layer's output. This implicitly treats the linear output as a proxy for the full module, including the n…
- arXiv cs.AIresearchRevisiting the 16x Pretraining Compute Gap between Diffusion and Autoregressive Language Models
arXiv:2610.17590v1 Announce Type: cross Abstract: Diffusion language models (DLMs) have attracted wide attention for their fast, parallel decoding, but they are believed to be far less efficient to train than autoregress…
- arXiv cs.AIresearchTanawpamana: Benchmarking Vision-Language Models on Philippine Cultural Heritage Sites
arXiv:2610.17596v1 Announce Type: cross Abstract: Vision-language models are increasingly used to identify and describe places, yet their recognition and knowledge of specific cultures remain poorly understood, particula…
- arXiv cs.AIresearchMorphology-aware deep learning predicts colorectal cancer survival from whole-slide images
arXiv:2610.17603v2 Announce Type: replace-cross Abstract: Background: Five-year survival prediction from hematoxylin-and-eosin whole-slide images could support risk stratification, but the task is weakly supervised, and…
- arXiv cs.AIresearchRELAY: Selective Self-Distillation with Adaptive Hand-off for Rubric-Based Reinforcement Learning
arXiv:2610.17623v2 Announce Type: replace-cross Abstract: Rubric-based reinforcement learning grades a response against many written criteria but collapses them into one reward, which discards the detail the rubric carri…
- arXiv cs.AIresearch4LC: 4D Latent Cache for Efficient Conditioning in Dynamic World Modeling
arXiv:2610.17625v1 Announce Type: cross Abstract: For video generation in dynamic world modeling, observed static and dynamic content should be efficiently reused to provide conditions for repeated generation at differen…
- arXiv cs.AIresearchThe Tokens Strike Back: Safety-Aware Denoising with Directional Embedding-based Revision
arXiv:2610.17636v1 Announce Type: cross Abstract: The Safety-Aware Denoiser (SAD) is a recent, training-free, safety-guidance framework for text diffusion models. During inference, SAD steers text samples toward safe reg…
- arXiv cs.AIagentsDeltaTTG: Training Multi-Turn Agents with a Token-to-Go Progress Meter
arXiv:2610.17666v1 Announce Type: cross Abstract: Reinforcement learning with verifiable rewards (RLVR) for multi-turn agents relies on sparse terminal rewards that say little about individual steps. Within-group step co…
- arXiv cs.AIresearchPrT-Flow: Probability-Tractable Flow Matching for Reinforcement Learning
arXiv:2610.17667v1 Announce Type: cross Abstract: Diffusion models and Flow Matching can represent flexible distributions over robot actions, but many reinforcement learning algorithms also require the probability of eac…
- arXiv cs.AIresearchDynamic K-Head: Difficulty-Supervised Budget Selection for Continuous Latent Reasoning
arXiv:2610.17679v1 Announce Type: cross Abstract: Chain-of-thought (CoT) improves reasoning but incurs substantial autoregressive rationale cost. Continuous CoT moves intermediate computation into recurrent hidden states…
- arXiv cs.AIagentsLatentRiskBench: Measuring State-Dependent Risks in Enterprise Agents
arXiv:2610.17685v1 Announce Type: cross Abstract: Enterprise agents face safety risks that cannot be determined from individual actions alone. Existing safety benchmarks largely evaluate action-local risks, overlooking f…
- arXiv cs.AIresearchHelpMeOut: A Neuropsychology-Grounded Benchmark for Error-Aware Monitoring of Household Task Execution
arXiv:2610.17694v1 Announce Type: cross Abstract: We introduce HelpMeOut, an embodied AI benchmark for error-aware monitoring of household task execution. Existing embodied household benchmarks typically assume that huma…
- arXiv cs.AIresearchzPocket: Better Pocket Finding with Frozen Co-Folding Features
arXiv:2610.17696v1 Announce Type: cross Abstract: Identifying protein-ligand binding sites (pockets) is important for understanding protein function and developing drugs. However, no public method has leveraged co-foldin…
- arXiv cs.AIresearchLeanPRM: Lean-Grounded Process Supervision for Natural Language Proof Verification
arXiv:2610.17697v2 Announce Type: replace-cross Abstract: AI systems now write long and difficult mathematical proofs, and checking their step-by-step validity is becoming a bottleneck. A learned verifier could check pro…
- arXiv cs.AIresearchFrom Token Correction to Claim Admission: Training-Free Hallucination Mitigation for Large Vision-Language Models
arXiv:2610.17706v1 Announce Type: cross Abstract: Large vision-language models often exhibit object hallucination, generating claims that are not supported by the input image. To mitigate this issue, we propose Evidence-…
- arXiv cs.AIresearchWhere Small Mistakes Matter: Quantifying State Criticality for Imitation Learning
arXiv:2610.17709v2 Announce Type: replace-cross Abstract: Imitation learning typically treats every demonstration state as equally important, optimizing a behavior-cloning objective uniformly across the dataset. Yet not…
- arXiv cs.AIagentsTSRL: Trigger-based Supervised Reinforcement Learning for Continual Agent Training
arXiv:2610.17726v1 Announce Type: cross Abstract: Large language model (LLM) agents excel at complex, multi-step tasks but suffer from catastrophic forgetting during continual learning--acquiring new skills often degrade…
- arXiv cs.AIagentsSkillScreen: High-Recall Screening of Malicious Agent Skills with Decision Models
arXiv:2610.17727v2 Announce Type: replace-cross Abstract: Agent skills turn natural-language instructions into actions, creating a security challenge: legitimate automation and malicious behaviour can look deceptively si…
- arXiv cs.AIresearchCoCA: Criterion-Aware Credit Assignment for Rubric-Based Reinforcement Learning
arXiv:2610.17733v1 Announce Type: cross Abstract: Rubric-based reinforcement learning (RL) evaluates responses against explicit criteria to construct rewards, offering a viable way to train large language models on open-…
- arXiv cs.AIresearchExplore with Memory, Learn without It: In-Context Exploration and Self-Distillation for LLM Reasoning
arXiv:2610.17734v1 Announce Type: cross Abstract: Exploration bounds learning efficiency in reinforcement learning with verifiable rewards (RLVR). Current methods explore mostly through independent sampling, without full…
- arXiv cs.AIresearchTrain for Many, Update with One: Improving Multi-Sample Reasoning via Fenchel-Bregman Posterior Learning
arXiv:2610.17735v1 Announce Type: cross Abstract: Multi-sample reasoning measures candidate coverage, the probability that at least one of $K$ candidates is correct. However, minimizing the average loss of individual att…
- arXiv cs.AIresearchHiSTOR: Structured Treatment-outcome Representation Learning for High-Dimensional Longitudinal Data
arXiv:2610.17739v1 Announce Type: cross Abstract: Estimating potential outcomes under alternative treatment sequences is essential for personalized decision-making, but remains challenging with high-dimensional covariate…
- arXiv cs.AIagentsAuditing Failure Attribution: Label Predictability and Judge Behavior
arXiv:2610.17747v1 Announce Type: cross Abstract: Failure-attribution benchmarks ask an LLM judge which step or agent caused a failure. A high score should mean the judge checked the faulty step against the run (a cross-…
- arXiv cs.AIresearchI3L: Iterative Interactive Imitation Learning for Whole-Body Mobile Manipulation
arXiv:2610.17748v2 Announce Type: replace-cross Abstract: Policies trained offline from teleoperated demonstrations can degrade outside their training distribution. This gap is particularly acute in long-horizon whole-bo…
- arXiv cs.AIagentsDegrees of Freedom in Multi-Agent Coordination: Between Centralized and Decentralized Regimes
arXiv:2610.17751v1 Announce Type: cross Abstract: Large language model (LLM)-based multi-agent systems (MAS) are commonly organized around two coordination regimes. Centralized coordination provides explicit control but…
- arXiv cs.AIagentsGaussian Process Bandits for AI System Optimization with Selectively Verified Feedback
arXiv:2610.17760v1 Announce Type: cross Abstract: Gaussian process bandits exploit similarities among configurations to optimize prompts, retrieval systems, and agent workflows. In these applications, however, inexpensiv…
- arXiv cs.AIresearchEfficiently Learning To Reason or Not to Reason: Root-token Policy Optimization for Adaptive Thinking
arXiv:2610.17767v1 Announce Type: cross Abstract: Large reasoning models (LRMs) achieve strong performance by externalizing explicit reasoning traces before producing the answer, yet suffer from overthinking challenge th…
- arXiv cs.AIresearchPosterior-Averaged Bellman Flow Matching for Distributional Critics
arXiv:2610.17788v1 Announce Type: cross Abstract: Distributional critics model the full return distribution, providing richer signals for exploration and risk-sensitive control. Recent work has shown that flow-based crit…
- arXiv cs.AIresearchGIFT-Eval-CTX: A Benchmark For Contextual Forecasting Model Evaluation
arXiv:2610.17794v1 Announce Type: cross Abstract: Contextual forecasting seeks to improve time series forecasting by incorporating forward-looking information, such as planned events, external conditions, and expert expe…
- arXiv cs.AIresearchLearning from fracture: Teaching language models to design through physical experience
arXiv:2610.17804v1 Announce Type: cross Abstract: How can language models learn to optimize physical designs through experience? We introduce FracLearn, an experience-abstraction-generalization framework evaluated throug…
- arXiv cs.AIresearchSame Attack, Different Judge: A First Controlled Adversarial Comparison of Jev, LLM Judges, and Purpose-Built Safety Classifiers
arXiv:2610.17820v1 Announce Type: cross Abstract: TypeSafe AI's Jev is a new kind of safety judge. It generates no text and no label: it answers questions the developer defines in advance and returns a probability for ea…
- arXiv cs.AIresearchChecking the Checkers: A Synthesis of Verifier Noise and Robustness in RLVR
arXiv:2610.17824v1 Announce Type: cross Abstract: Reinforcement learning with verifiable rewards (RLVR) has become a principal recipe for improving the reasoning of large language models (LLMs). It rests on the assumptio…
- arXiv cs.AIresearchQK-Edit: Revisiting Attention-based Injection in MM-DiT for Image and Video Editing
arXiv:2610.17829v2 Announce Type: replace-cross Abstract: Multimodal Diffusion Transformers (MM-DiTs) have recently emerged as a powerful framework for unified text-vision synthesis, surpassing traditional U-Net architec…
- arXiv cs.AIresearchDiff Diffusion: Predicting Edit Paths with Diffusion Models for Efficient Code Editing
arXiv:2610.17831v1 Announce Type: cross Abstract: Diffusion large language models (dLLMs) are appealing for code generation because they can update many tokens in parallel, yet many are optimized for sequence synthesis r…
- arXiv cs.AIagentsAgentic-MatriBO: Capability-Compiled Agentic Bayesian Optimization for Materials and Chemical Design
arXiv:2610.17832v3 Announce Type: replace-cross Abstract: Materials and chemical optimization must choose the next synthesis, characterization, or high-fidelity simulation from sequential observations under a limited bud…
- arXiv cs.AIresearchA Tutorial on Quantum Amplitude Embedding with Data Re-Uploading
arXiv:2610.17836v1 Announce Type: cross Abstract: Amplitude embedding lets a variational quantum model read many classical features with few qubits, but the model output is then only a quadratic form in the normalized in…
- arXiv cs.AIagentsProtoArena: Can AI Agents Discover and Exploit Real-World Cross-Component Protocol Vulnerabilities?
arXiv:2610.17837v1 Announce Type: cross Abstract: Large language model (LLM) agents are increasingly used for vulnerability analysis, yet existing benchmarks provide limited coverage of exploitation that depends on inter…
- arXiv cs.AIresearchFASHION-RQ: Mining Hierarchical Semantic Structure for Automated Evaluation of Fashion Retrieval
arXiv:2610.17841v1 Announce Type: cross Abstract: Evaluating fashion retrieval systems remains challenging due to the limited availability of benchmarks that capture the fine-grained, open-ended queries encountered in re…
- arXiv cs.AIresearchMMTA: Benchmarking Multimodal Temporal Analysis with Time Series, Text, and Vision
arXiv:2610.17856v3 Announce Type: replace-cross Abstract: Time-series analysis is increasingly studied in multimodal settings, yet most benchmarks pair temporal signals with text or with visualizations derived from the s…
- arXiv cs.AIresearchTStruct: Learning Shared Temporal Structures for Long-Term Time-Series Forecasting
arXiv:2610.17864v1 Announce Type: cross Abstract: Long-term time series forecasting requires temporal dependency modeling that remains stable and generalizable under temporal distribution shifts. However, real-world time…
- arXiv cs.AIresearchRT-J: Large-Scale Pretraining of Relational Transformers for Context-Efficient Predictions
arXiv:2610.17867v3 Announce Type: replace-cross Abstract: Foundation models for tables and relational databases are increasingly used for predictive tasks across various scientific and industrial domains. However, adapti…