AI news archive.
19,861 articles, newest first, from the outlets listed on the sources page.
- arXiv cs.AIresearchSubspace Crystallization in Grokking: Rank Compression Tracks the Phase Transition
arXiv:2610.35112v1 Announce Type: cross Abstract: Grokking describes understanding something deeply and intuitively. In neural networks, it is the phenomenon where a network generalizes long after memorizing its training…
- arXiv cs.AIresearchUTA: Universal Training Adaptive Learning Rate Decay
arXiv:2610.35113v1 Announce Type: cross Abstract: Learning rate decay (LRD) is critical for training high-performance models, yet most designs remain empirically driven. Although the Universal Budget Aware (UBA) LRD offe…
- arXiv cs.AIresearchGenerative AI in Turbulence: Foundations, Applications, Validations and Benchmarks
arXiv:2610.35123v1 Announce Type: cross Abstract: Generative AI offers new approaches to turbulence problems in which incomplete observations or unresolved d.o.f. admit multiple physically plausible solutions. Potential…
- arXiv cs.AIresearchLocked In: Multi-Objective RL for the AI Data Center Build-Out
arXiv:2610.35147v1 Announce Type: cross Abstract: AI data center build-out is a multi-trillion-dollar, multi-decade infrastructure program. Yet siting, power procurement, and cooling decisions are still made with static,…
- arXiv cs.AIresearchSoK: Timestamps Are Not a Time Model: Rethinking Temporal Reasoning in Host-Based Intrusion Detection
arXiv:2610.35151v1 Announce Type: cross Abstract: Host-based intrusion detectors order events, window audit streams and sequence attack stages by their timestamps. Every conclusion they draw therefore rests on assumption…
- arXiv cs.AIresearchFormal Explanations for Linear Temporal Logic over Finite Traces
arXiv:2610.35169v1 Announce Type: cross Abstract: Linear Temporal Logic over Finite Traces (LTLf) is widely used in Artificial Intelligence to specify desired temporal behavior and determine whether finite traces satisfy…
- arXiv cs.AIagentsV$^3$AST-Bench: Verifiable, Valid, and Versatile Safety Evaluation for Coding Agents
arXiv:2610.35188v1 Announce Type: cross Abstract: Large language models increasingly act through code, modifying repositories, executing programs, and interacting with services in agent form. Their actions introduce risk…
- arXiv cs.AIresearchOrthoRF: Exploring Orthogonality in Object-Centric Representations
arXiv:2610.35203v1 Announce Type: cross Abstract: Neural synchrony is hypothesized to help the brain organize visual scenes into structured multi-object representations. In machine learning, synchrony-based models analog…
- arXiv cs.AIresearchEfficient Exact Unlearning for Federated Zeroth-Order Optimization
arXiv:2610.35211v1 Announce Type: cross Abstract: Federated zeroth-order optimization (FedZOO) reduces the memory and communication costs of collaborative training for edge intelligence by avoiding backpropagation while…
- arXiv cs.AIresearchOne-Shot Federated Model Editing for Device Dynamics at the Edge
arXiv:2610.35212v1 Announce Type: cross Abstract: Standard federated learning (FL) requires persistent device connectivity across multiple communication rounds, making it unsuitable for dynamic environments such as vehic…
- arXiv cs.AIagentsSkillLifeBench: Benchmarking Security Across the Lifecycle of Agent Skills
arXiv:2610.35215v1 Announce Type: cross Abstract: Web agents reuse skills whose stored code, selected version, and loaded implementation can diverge across tasks and updates. SkillLifeBench links these states to task out…
- arXiv cs.AIagentsJoint Latent Reasoning and Observation for Agentic Video Understanding
arXiv:2610.35229v2 Announce Type: replace-cross Abstract: Effective video agents must learn not only how to answer, but also where to look next. Transferring this capability to smaller models is challenging because each…
- arXiv cs.AIresearchContext Is Not Free: Carbon-Aware LLM Routing for Multi-Turn LLM Web Services across Geo-Distributed Data Centers
arXiv:2610.35230v1 Announce Type: cross Abstract: The sustainability of the Web has drawn growing attention, as large language model (LLM)-based web services leave a substantial carbon footprint. These services typically…
- arXiv cs.AIresearchReading Beyond OCR Noise: Robust Cross-Lingual RAG for Legislative Archives
arXiv:2610.35240v1 Announce Type: cross Abstract: India's historical public archives present severe computer vision and document image analysis challenges: decades of parliamentary records survive only as degraded, multi…
- arXiv cs.AIresearchBeyond Vision-Language Models: Visual-Semantic Affect Graphs for Emotion Recognition in Artworks
arXiv:2610.35244v1 Announce Type: cross Abstract: Emotion recognition in artworks remains challenging because affective meaning is often subjective, implicit, and shaped by relationships between visual form and semantic…
- arXiv cs.AIresearchSatellite Intelligence: Distributed Training, Collaborative Inference,and LLM Adaptation in LEO Constellation
arXiv:2610.35282v1 Announce Type: cross Abstract: The proliferation of orbital sensing data and the real-time demands of emerging global services are pushing low Earth orbit (LEO) satellite networks from bent-pipe relays…
- arXiv cs.AIresearchReward-Guided RRT* for Budgeted Task and Motion Planning
arXiv:2610.35289v1 Announce Type: cross Abstract: Robotic missions involving spatially distributed tasks often require jointly selecting rewarding locations and planning feasible motions under limited travel budgets. Thi…
- arXiv cs.AIresearchDid the Model Use That? Counterfactual Training Boosts Self-Attribution in Language Models
arXiv:2610.35295v1 Announce Type: cross Abstract: A fundamental challenge for explainable and accountable language models is revealing how external information influences their answers. This paper examines whether models…
- arXiv cs.AIresearchConstrained Decoding: Harmful or Beneficial? Revisiting Its Impact on LLM Performance
arXiv:2610.35328v1 Announce Type: cross Abstract: Constrained decoding guarantees that Large Language Models (LLMs) produce outputs conforming to predefined formats, but is often assumed to inherently degrade reasoning.…
- arXiv cs.AIresearchGeometric Consistency Based Label-Free Validation for Checkpoint Selection in Audio Active Learning
arXiv:2610.35329v1 Announce Type: cross Abstract: Audio active learning (AL) trains a classifier at low annotation cost by labeling only an informative fraction of an unlabeled collection over successive rounds. Each rou…
- arXiv cs.AIagentsRepoTrace: Improving Requirement Tracing in Multi-Round Agent Interactions
arXiv:2610.35333v1 Announce Type: cross Abstract: Code agents have become increasingly capable of performing software engineering tasks through interaction with software environments. However, agents tend to degrade as t…
- arXiv cs.AIresearchShould Pseudo-Labels Share Mini-Batches with Labeled Examples? Semi-Supervised Continual Active Learning with Limited Training Cost
arXiv:2610.35345v1 Announce Type: cross Abstract: Active learning (AL) reduces annotation by querying informative examples. Continual active learning (CAL) also cuts the training cost, the total number of gradient steps,…
- arXiv cs.AIagentsMarkovSim: an LLM Agent Harness with Bounded Context for Long-Horizon Computational Simulation
arXiv:2610.35349v1 Announce Type: cross Abstract: Recent studies have applied large language model (LLM) agent systems to computational simulation workflows. Such workflows are long-horizon, so the information generated…
- arXiv cs.AIresearchShared-Factor-Conditioned Diffusion for Low-Rank Tensor Recovery
arXiv:2610.35368v1 Announce Type: cross Abstract: Tensor recovery spans heterogeneous data structures and observation processes, calling for a representation that can adapt across modalities and tasks. We propose DiffTR,…
- arXiv cs.AIresearchACSAN: All-Convolutional Self-Attention Network Integrating Convolutional Operations with Vision Transformer
arXiv:2610.35375v1 Announce Type: cross Abstract: In the past few years, Vision Transformer (ViT) has achieved excellent performance in the field of computer vision. However, there still some problems remain. For instanc…
- arXiv cs.AIagentsAutonomous Structural Discovery Of Bioprocess Dynamics And Kinetics Via LLM-Driven Agents
arXiv:2610.35391v1 Announce Type: cross Abstract: High-fidelity digital twins in continuous biomanufacturing are often bottlenecked by incomplete kinetic models, while standard data-driven algorithms (e.g., SINDy, PINNs)…
- arXiv cs.AIresearchAn Interactive Evolutionary Multiobjective Optimization Algorithm Based on Interpretable Active Preference Learning
arXiv:2610.35470v1 Announce Type: cross Abstract: Many decision-making tasks are inherently multi-objective. Interactive evolutionary multi-objective optimization algorithms (iEMOAs) are particularly well-suited to help…
- arXiv cs.AIresearchBeyond Words Alone: Disentangling Distributed Evidence for Visually Grounded Cultural Translation
arXiv:2610.35482v1 Announce Type: cross Abstract: Social media enables cross-lingual communication, yet the meaning of user-generated content (UGC) is often distributed across text, images, and cultural knowledge, making…
- arXiv cs.AIagentsThe Hidden Costs of Forgetting: A Study of Trajectory Deletion in Software Engineering Agents
arXiv:2610.35496v1 Announce Type: cross Abstract: Software engineering agents resend their entire trajectory to an LLM at every turn, motivating online trajectory reduction. Prior work shows that randomly deleting 75% of…
- arXiv cs.AIresearchGoverning Enterprise AI Traffic at Scale: Design and Operation of a Policy-Driven, Multi-Vendor LLM Gateway on Envoy
arXiv:2610.35509v1 Announce Type: cross Abstract: Large organizations consume large language models (LLMs) from several vendors at once, each with its own API dialect, credential model, streaming protocol and pricing. In…
- arXiv cs.AIresearchGenerative Structure from Motion with Native 3D Diffusion
arXiv:2610.35522v1 Announce Type: cross Abstract: Recovering an object's 3D structure and camera motion from a few uncalibrated views is a fundamental problem in computer vision. Classical structure from motion methods r…
- arXiv cs.AIresearchRanking Function Generation with LLMs for Termination
arXiv:2610.35523v1 Announce Type: cross Abstract: Ranking functions are a fundamental technique for proving loop termination, but constructing them manually is challenging and requires substantial expertise. We propose R…
- arXiv cs.AIresearchJANUS: Synthesizing Cross-Layer Defenses Against Web Deserialization Attacks
arXiv:2610.35532v2 Announce Type: replace-cross Abstract: Unsafe deserialization turns untrusted data into attacker-controlled execution, and a single vulnerability can admit diverse exploit variants that evade defenses…
- arXiv cs.AIagentsThe Agent in the Middle: How AI-Mediated Access Reshapes Web Vulnerability Exploitation
arXiv:2610.35541v2 Announce Type: replace-cross Abstract: Web services increasingly expose backend interfaces that let users delegate tasks to AI agents, which invoke service operations directly without navigating websit…
- arXiv cs.AIresearchCross-Domain Sequential Recommendation with Representation-Level User Transfer
arXiv:2610.35550v1 Announce Type: cross Abstract: Cross-domain sequential recommendation aims to improve next-item prediction in a target domain by leveraging user behavior from auxiliary source domains. However, real-wo…
- arXiv cs.AIresearchMulti-Fidelity Training Reshapes Uncertainty Decomposition in Atomistic Models
arXiv:2610.35560v2 Announce Type: replace-cross Abstract: Multi-fidelity training, which combines abundant low-fidelity data with scarce high-fidelity labels, is increasingly common in atomistic modeling, but its effect…
- arXiv cs.AIresearchExCal: Optimization-Free Multivariate Time Series Anomaly Detection via Excess Calibration
arXiv:2610.35568v1 Announce Type: cross Abstract: We introduce ExCal, a normal-only multivariate time series anomaly detector that combines raw state retrieval, a signal/derivative subspace, and robust statistics across…
- arXiv cs.AIagentsKAPPA: Checking the Proofs in Statistics Papers with Lean 4 and Language Model Agents
arXiv:2610.35596v1 Announce Type: cross Abstract: Papers in statistical theory rest on long proofs that few readers check line by line. We present KAPPA (Kit of Agents for Proof-checking Papers with a proof Assistant), o…
- arXiv cs.AIresearchMaking Reasoning Visible: Configuration-Aware Diagnostic Modeling for Adaptive Scaffolding in Structured Reasoning Tasks
arXiv:2610.35609v1 Announce Type: cross Abstract: Modeling the latent, multi-step reasoning processes of learners is a core challenge for adaptive tutoring systems, which often rely on simple right/wrong answers rather t…
- arXiv cs.AIagentsFrom Language to Drives: A Multimodal Framework for Aligning Autonomous Robots with Human Purposes
arXiv:2610.35629v1 Announce Type: cross Abstract: This work explores a multimodal approach to the alignment of the behavior of open-ended learning autonomous robots with human purposes through the use of large language m…
- arXiv cs.AIresearchAdapt for Planning, Not just Prediction: Optimistic Test-Time World Model Adaptation
arXiv:2610.35636v1 Announce Type: cross Abstract: Latent world models are typically pre-trained offline and kept frozen at test time, so planning with them can degrade under distribution shift. Test-time adaptation (TTA)…
- arXiv cs.AIresearchProvably Efficient Q-learning for Robust Reinforcement Learning
arXiv:2610.35656v1 Announce Type: cross Abstract: Standard reinforcement learning (RL) algorithms based on Markov Decision Processes (MDPs) are vulnerable to sim-to-real gaps. To address this issue, distributionally robu…
- arXiv cs.AIresearchCounterFlow: Target-Conditioned Flow Matching for Visual Counterfactuals
arXiv:2610.35679v1 Announce Type: cross Abstract: In eXplainable AI, counterfactual explanations have gained significant traction by offering users direct, intuitive, and actionable insights into model decisions. We intr…
- arXiv cs.AIresearchOmniShowcase: Omnidirectional Subject-Consistent Video Generation from Multi-View Images
arXiv:2610.35684v1 Announce Type: cross Abstract: Generating videos of a specific subject from a few reference images remains challenging when the camera reveals surfaces that are not visible in the input. Early subject-…
- arXiv cs.AIresearchAdapting LLM-SC to Living Sacred Heritage: Domain-Specific Extraction, Semantic Networks and Human Evaluation on Pashupatinath Temple Reviews
arXiv:2610.35685v2 Announce Type: replace-cross Abstract: Large language model (LLM) pipelines can turn visitor reviews into structured data, but generic schemes may miss rituals, sacred spaces, cultural restrictions and…
- arXiv cs.AIresearchTrySee: Modular Perception-Enhanced VLM Grounding for Closed-Loop Robot Task Planning in Specialized Domains
arXiv:2610.35687v1 Announce Type: cross Abstract: Vision Language Models (VLMs) have shown impressive capabilities in high-level reasoning and task planning for robots. However, specialized domains remain a challenge for…
- arXiv cs.AIresearchTowards a Unified Framework of Optimal Input-Side Dimensional Configuration for Deep CTR Prediction
arXiv:2610.35695v1 Announce Type: cross Abstract: Deep click-through rate (CTR) prediction has achieved substantial success through increasingly expressive feature interaction architectures. However, predictive performan…
- arXiv cs.AIagentsMiRL: Error-Targeted Reinforcement Learning for Correcting Terminal Agent Misbehaviors
arXiv:2610.35697v1 Announce Type: cross Abstract: Error-targeted learning gives a legible way to improve a model: identify specific weaknesses of the model, train the model to fix these weaknesses, and check whether the…
- arXiv cs.AIresearchQuantitative Generalization Bounds for Multi-Layer Transformers: A Few Long Strings can Beat Many Short Ones
arXiv:2610.35715v2 Announce Type: replace-cross Abstract: Transformer-based language models exhibit an astonishing capacity to generalize to longer and more difficult problem instances than those seen in training. Howeve…
- arXiv cs.AIresearchAudit Where Hacks Pay: Budgeted Strong-Verifier Audits Against Reward Hacking in GRPO
arXiv:2610.35716v1 Announce Type: cross Abstract: Reinforcement learning with verifiable rewards trains on cheap checks, such as unit tests, that a policy can learn to game, while a stronger check is too expensive to run…