AI news archive.
19,861 articles, newest first, from the outlets listed on the sources page.
- arXiv cs.AIresearchDiffWAM: A Fast and Efficient Navigation World Action Model
arXiv:2609.39763v1 Announce Type: cross Abstract: Pretrained video foundation models encode rich semantic and spatiotemporal priors for embodied navigation, yet converting these priors into UAV motion typically requires…
- arXiv cs.AIresearchHow Does Local Landscape Geometry Evolve in Language Model Pre-Training?
arXiv:2609.39767v1 Announce Type: cross Abstract: The scale and expense of pre-training language models make efficient hyperparameter tuning essential, yet a principled guidance is still missing. In this work, we analyze…
- arXiv cs.AIresearchPseudo-Label-Triggered Retraining from Forecast Errors for Online Time Series Forecasting
arXiv:2609.39789v1 Announce Type: cross Abstract: Real-world time series forecasting systems operate under non-stationary data streams, where forecasting performance may degrade over time. Although retraining can recover…
- arXiv cs.AIresearchProbabilistic Adversarial Training
arXiv:2609.39798v1 Announce Type: cross Abstract: Building on a probabilistic perspective in which adversarial examples arise from the overlap between a distance-based distribution $p_{\mathrm{dis}}$ and a victim-classif…
- arXiv cs.AIresearchStress-Testing LLM Lie Detectors: Role-Play Failures and Spurious Correlations
arXiv:2609.39807v1 Announce Type: cross Abstract: Lie detection probes aim to predict from a language model's internal states whether its output is truthful or dishonest. However, role-play complicates what "truth" means…
- arXiv cs.AIresearchLearning from Runtime Feedback through Failure-Bank Self-Evolution for Vision-Language-Action Models
arXiv:2609.39820v1 Announce Type: cross Abstract: Vision-language-action (VLA) models generalize broadly across robotic manipulation tasks, but complex environments require balancing task success with unintended contact.…
- arXiv cs.AIresearchSynthetic Pre-pretraining Survives Scale, but Not as a Grammatical Prior
arXiv:2609.39827v1 Announce Type: cross Abstract: Pre-pretraining (PPT) on synthetic non-natural language data improves token efficiency during language model pre-training (PT). Prior work attributes this gain to a gramm…
- arXiv cs.AIresearchBayesNDE: Bayesian Generative Modeling for Neural Density Estimation
arXiv:2609.39843v1 Announce Type: cross Abstract: Density estimation is a fundamental problem in statistics and machine learning. In this work, we introduce BayesNDE, a neural density estimator based on Bayesian generati…
- arXiv cs.AIresearchWhen a Kindergartener Solves Calculus: Measuring Capability Leakage in Role-Prompted Reasoning Models
arXiv:2609.39846v1 Announce Type: cross Abstract: We investigate the problem of role-capability leakage (RCL), in which a role-prompted reasoning model generates convincing in-role text while continuing to exhibit capabi…
- arXiv cs.AIresearchAlgorithmic Recourse Under Competition
arXiv:2609.39877v1 Announce Type: cross Abstract: Algorithmic recourse provides individuals who have received undesirable outcomes from machine learning models with suggestions for minimum-cost improvements to achieve th…
- arXiv cs.AIresearchOPSRD: On-Policy Self-Role Distillation
arXiv:2609.39884v1 Announce Type: cross Abstract: Role prompting elicits specialized behavior from large language models through an expert identity, offering a lightweight way to guide reasoning on demanding tasks. Howev…
- arXiv cs.AIresearchDo Better Goal Representations Improve Goal-Conditioned Reinforcement Learning?
arXiv:2609.39901v1 Announce Type: cross Abstract: Goal-conditioned reinforcement learning (GCRL) relies heavily on how target goals are represented to the policy. While recent methods encode goals via temporal distance,…
- arXiv cs.AIresearchCodeMimicry: Exploiting Safety Generalization Lag in Large Language Models via Structured Code Completion
arXiv:2609.39902v1 Announce Type: cross Abstract: Large language models have achieved remarkable capabilities across diverse domains, yet their safety alignment remains vulnerable to jailbreak attacks. In this work, we i…
- arXiv cs.AIresearchUnderstanding Parents' Complex Views of AI for Children's Pretend Play
arXiv:2609.39906v1 Announce Type: cross Abstract: AI could support children's pretend play, but it could also direct the play on behalf of children. Whether AI should have roles in children's lives is controversial becau…
- arXiv cs.AIagentsDoGBench: Can Agents Meet Expert Standards for User-Facing Documentation?
arXiv:2609.39909v1 Announce Type: cross Abstract: We introduce DoGBENCH (Documentation Generation Benchmark), to our knowledge, the first benchmark for generating and maintaining real user-facing software documentation.…
- arXiv cs.AIagentsTRACE: Trajectory Selection for Parallel Scaling of Search Agents
arXiv:2609.39912v1 Announce Type: cross Abstract: Parallel search may generate a correct answer that final-answer voting fails to select. We formulate this consolidation stage as trajectory selection and introduce TRACE…
- arXiv cs.AIresearchCluster Attention Neural Operators for Solving Parametric Partial Differential Equations
arXiv:2609.39914v1 Announce Type: cross Abstract: Traditional simulations of parametric partial differential equations (PDEs) rely on repetitive computations for each parameter, which makes high-fidelity design impractic…
- arXiv cs.AIresearchCoVisco: Codec-Native Vision Encoder with Native Token Compression for Unified Image-Video Understanding
arXiv:2609.39924v1 Announce Type: cross Abstract: Vision-language models face a fundamental scaling bottleneck: the number of visual tokens grows with both temporal duration and spatial resolution, making long-video unde…
- arXiv cs.AIresearchLEAP: Learned Block-wise Evidence Retrieval for Long Audio-Video Perception
arXiv:2609.39938v2 Announce Type: replace-cross Abstract: Hour-scale audio-visual question answering is constrained by a context dilemma: dense whole-recording encoding rapidly exhausts context limits, whereas uniform te…
- arXiv cs.AIagentsLearning When and How to Intervene: A Hindsight-Distilled Sentinel for Coding Agents
arXiv:2609.39957v1 Announce Type: cross Abstract: Coding agents solve repository-level tasks through sequences of actions, where a single erroneous action can misdirect subsequent decisions and increase recovery costs. E…
- arXiv cs.AIresearchWhat Limits Recursive Reasoning Models: Optimization, Architecture and Test-Time Scaling
arXiv:2609.39967v1 Announce Type: cross Abstract: Recursive reasoning models apply a small shared Transformer block many times to refine a latent state. This gives them large effective depth with few parameters and makes…
- arXiv cs.AIresearchTACTIC: Temporal and Context-Aware LLM Tactical Planning for Roadside LiDAR Attacks
arXiv:2609.39969v1 Announce Type: cross Abstract: Physical LiDAR attacks are often evaluated using fixed primitives and manually selected parameters, despite their strong dependence on surrounding traffic. We present TAC…
- arXiv cs.AIresearchOverview of BioASQ 2026: The fourteenth BioASQ Challenge on Large-Scale Biomedical Semantic Indexing and Question Answering
arXiv:2609.39975v1 Announce Type: cross Abstract: This paper presents an overview of the fourteenth edition of the BioASQ challenge, organized in the context of the Conference and Labs of the Evaluation Forum (CLEF) 2026…
- arXiv cs.AIresearchRichard: Voice-First Mobile Interaction for Persistent Tasks
arXiv:2609.39976v1 Announce Type: cross Abstract: Mobile terminals need to provide application and network services while supporting users' control over their attention. We explore voice-first interaction organized aroun…
- arXiv cs.AIagentsMid-Harness: Scaling Actions Between Model and Harness for Terminal Agents
arXiv:2609.39982v1 Announce Type: cross Abstract: Terminal agents act through stochastic model generations, yet the ability to generate a useful action does not ensure its reliable execution. A poor command (e.g., wrong…
- arXiv cs.AIresearchFenchel Tilting: Weighted Correction for Efficient Finetuning of Generative Models
arXiv:2609.40030v2 Announce Type: replace-cross Abstract: Adapting a pretrained generative model to an arbitrary preference expressed as a utility function underlies reward alignment, guided design, and constraint satisf…
- arXiv cs.AIresearchWARP: A Unified Benchmark for Invisible Image Watermarking -- Robustness and Protection Against Attacks
arXiv:2609.40031v1 Announce Type: cross Abstract: Digital image watermarking is increasingly critical in media contexts, as emerging regulations and industry practices require marking AI-generated content and ensuring tr…
- arXiv cs.AIresearchEfficient Active Auditing of Multi-Group Fairness with Bias Probes
arXiv:2609.40034v1 Announce Type: cross Abstract: Over the past decade, Machine Learning (ML) has been trained under dual objectives: minimizing prediction error via Empirical Risk Minimization (ERM) while controlling un…
- arXiv cs.AIresearchLess Data, Better Timing: Student-Curriculum Coupling for VLM On-Policy Distillation in Temporal Video Grounding
arXiv:2609.40055v1 Announce Type: cross Abstract: On-policy distillation (OPD) provides dense supervision directly on student-generated trajectories, making it an effective post-training strategy for vision-language mode…
- arXiv cs.AIresearchCommunity-Driven API and AI Writer Design for Openly Scaling Community Notes
arXiv:2609.40067v1 Announce Type: cross Abstract: Community Notes is a crowd-sourced approach for adding context to posts on X. Contributors propose and rate notes, forming the inputs to an open-source, open-data algorit…
- arXiv cs.AIresearchInference Auctions
arXiv:2609.40070v1 Announce Type: cross Abstract: When inference demand exceeds available compute capacity, model providers must decide which requests should be served first. Users have different tolerances for delay fro…
- arXiv cs.AIresearchGrounding Time-Series Foundation Models in Digital Twin Topology for Predictive Maintenance
arXiv:2609.40071v1 Announce Type: cross Abstract: Digital twins increasingly support downstream analytical tasks that depend on time-series data, motivating interest in time-series foundation models (TSFMs) as scalable b…
- arXiv cs.AIresearchLongEmo: Towards Emotion Understanding and Reasoning in Long Videos
arXiv:2609.40079v1 Announce Type: cross Abstract: While recent Multimodal Large Language Models (MLLMs) have shown promise in affective computing, their reasoning capabilities are largely confined to short video clips wi…
- arXiv cs.AIresearchBatSLAM 2.0: Sequence-Verified Sonar Place Recognition in a Robust Pose Graph
arXiv:2609.40085v1 Announce Type: cross Abstract: Echolocating bats can navigate dark and cluttered spaces using echolocation. Over a decade ago, BatSLAM showed that a robot with a biomimetic binaural sonar can build a t…
- arXiv cs.AIresearchMeanVoiceFlow2: Joint Optimization of Mean Flow and Content Encoder for Fast One-Step Zero-Shot Voice Conversion
arXiv:2609.40087v1 Announce Type: cross Abstract: Flow-matching approaches to voice conversion (VC) have gained attention owing to their high speech quality and strong speaker similarity. Among them, one-step models such…
- arXiv cs.AIresearchGateSPINE: Gated Cross-View Fusion for Lumbar Spine MRI Report Generation
arXiv:2609.40091v1 Announce Type: cross Abstract: Automated report generation can ease the burden radiolo gists face when interpreting multi-sequence MRI studies. Unlike CT, MRI examinations comprise multiple sequences a…
- arXiv cs.AIresearchOn the (In)effectiveness of AMR Augmentation for Large Language Models
arXiv:2609.40121v1 Announce Type: cross Abstract: While Abstract Meaning Representation (AMR) has historically improved performance on a range of NLP tasks, the benefit---or lack thereof---of AMR augmentation for modern…
- arXiv cs.AIresearchTactile Curiosity Drives Robot Interaction
arXiv:2609.40134v3 Announce Type: replace-cross Abstract: Mastering robot manipulation skills via reinforcement learning (RL) remains largely sample-inefficient. The most common RL algorithms rely on random action sampli…
- arXiv cs.AIagentsGame-Guided Skill Discovery through Self-Play for Playable Agent Control
arXiv:2609.40137v1 Announce Type: cross Abstract: We present Game-Guided Skill Discovery (GGSD), a framework that uses self-play in games to discover motor skills that are directly playable by humans. Playable skills pro…
- arXiv cs.AIresearchPrefPI: Preference-Guided Steering into Out-of-Distribution Behaviors
arXiv:2609.40165v1 Announce Type: cross Abstract: We present PrefPI (Preference-Guided Policy Iteration), an iterative framework for steering pretrained generative robot policies using only relative preferences over self…
- arXiv cs.AIagentsMemLife: Curating and Reasoning over Long-Term Egocentric Video Memories
arXiv:2609.40195v1 Announce Type: cross Abstract: Long-term egocentric video enables personalized AI assistants to reason about daily life. However, as video histories grow to hundreds of hours spanning months or years,…
- arXiv cs.AIresearchSCB: SpeechConversationBench for Evaluating Multi-Turn Reasoning in Speech-to-Speech Models
arXiv:2609.40198v1 Announce Type: cross Abstract: Speech-to-speech systems must solve tasks whose requirements emerge across conversational turns. We introduce SpeechConversationBench (SCB), a focused evaluation of spoke…
- arXiv cs.AIresearchLearning Skills from Historical Action Trajectories: Action Experience Dictionary for World Action Models
arXiv:2609.40219v2 Announce Type: replace-cross Abstract: World Action Models (WAMs) couple visual dynamics prediction with action generation, yet they do not explicitly support the reuse of action experience across mani…
- arXiv cs.AIagentsPhantomEnvironments: Training LLM Agents in Fictional Worlds
arXiv:2609.40221v1 Announce Type: cross Abstract: Training LLM agents with reinforcement learning (RL) is bottlenecked by environments, which must provide verifiable rewards, support long-horizon interaction, and scale c…
- arXiv cs.AIagentsEviRover: Reinforcing Agentic Perception Beyond a Glance
arXiv:2609.40230v1 Announce Type: cross Abstract: Visual perception is conventionally formulated as a one-shot prediction from a single glance at the image, under the assumption that the image content and the model's par…
- arXiv cs.AIagentsComputerSD: Online Self-Distillation from Real-Time Feedback for Computer-Use Agents
arXiv:2609.40253v2 Announce Type: replace-cross Abstract: Online training enables computer-use agents (CUAs) to improve through interaction with executable environments. However, existing methods primarily rely on sparse…
- arXiv cs.AIagentscua-speedrun: Standardized Benchmarking of the Speed of Computer-Use Agents
arXiv:2609.40284v1 Announce Type: cross Abstract: Computer use agents (CUAs), which use graphical user interfaces (GUIs) to complete tasks on a computer, have recently surpassed human performance on many standard benchma…
- arXiv cs.AIresearchLinguistic Loopholes in LLM Unlearning: From a 174-Language Benchmark to Coverage-Aware Unlearning
arXiv:2609.40286v1 Announce Type: cross Abstract: Unlearning a fact in one language does not guarantee its removal in others as changing the query or even the requested answer language can reopen seemingly forgotten know…
- arXiv cs.AIresearchCAS II: Orbits as Models: Kolmogorov's Structure Function under Symmetry
arXiv:2609.40290v2 Announce Type: replace-cross Abstract: In algorithmic statistics a string x is explained by a finite set containing it, and Kolmogorov's structure function records the smallest such model at each level…
- arXiv cs.AIagentsDynaHarness: A Dynamic Physical Harness for Self-Evolving Robot Agents
arXiv:2609.40306v1 Announce Type: cross Abstract: Pretrained robot policies provide useful action priors, but long-horizon manipulation still requires coordination between semantic reasoning and physical execution. Seman…