AI news archive.
19,861 articles, newest first, from the outlets listed on the sources page.
- arXiv cs.AIresearchER-JEPA: Experience Replay Improves Joint-Embedding Predictive Learning in Language Models
arXiv:2609.36952v1 Announce Type: cross Abstract: Large language models (LLMs) excel at token-level generation but may learn undesirable abstract semantics and lack comprehensive perception. LLM-JEPA mitigates this by al…
- arXiv cs.AIresearchPurlin: Separating Orchestration from the Datapath of Collectives
arXiv:2609.36954v2 Announce Type: replace-cross Abstract: Distributed inference depends on GPU collective communication that must keep pace with evolving hardware and specialized workloads. However, existing works often…
- arXiv cs.AIresearchControlled Decoding Attacks on Black-Box LLMs
arXiv:2609.36956v2 Announce Type: replace-cross Abstract: Manipulating next-token probabilities during generation can bypass the safety alignment of large language models. Existing approaches, however, rely on access to…
- arXiv cs.AIresearchVStress: Correlation-Aware Auditing and Adaptive Budget Allocation for Repeated Verifiers
arXiv:2609.36958v2 Announce Type: replace-cross Abstract: Repeated verifier calls are useful only when they contribute conditional information. We introduce VStress, an auditable replay contract, and VStress-CA, a correl…
- arXiv cs.AIresearchJudgeCast: Time Series Forecasting with Experience-Informed Covariate Judgements
arXiv:2609.36966v2 Announce Type: replace-cross Abstract: Covariate effects vary across contexts and shift over time, requiring forecasters to assess how to use them for each forecasting context. As forecasting proceeds,…
- arXiv cs.AIresearchSRJudge: Empowering Large Language Models with Selective Reasoning for Fine-Grained Knowledge Concept Tagging
arXiv:2609.36982v1 Announce Type: cross Abstract: Knowledge concept tagging aims to assign specific concept or topic labels to educational content, which is essential for both educators and learners in traditional and on…
- arXiv cs.AIresearchAbductive World Modeling via Causal Representation Learning
arXiv:2609.36985v1 Announce Type: cross Abstract: The central challenge of world modeling is to learn representations that capture how the world evolves. However, existing world models predominantly represent future stat…
- arXiv cs.AIresearchSalt++: Context-Aligned Post-Training for Few-Step Streaming Multimodal Generation
arXiv:2609.36995v1 Announce Type: cross Abstract: Few-step streaming audio--video generation requires both causal modeling and step distillation, yet standard training recipes face two context-related challenges. Teacher…
- arXiv cs.AIresearchCross-Organizational SysML Model Integration: A Survey of Challenges and AI-Supported Tasks
arXiv:2609.37000v1 Announce Type: cross Abstract: Cross-organizational collaboration is widely regarded as a key promise of SysML-based Model-Based Systems Engineering (MBSE), yet practitioners still face persistent chal…
- arXiv cs.AIresearchParameterized Stripe Attention for Efficient Video Generation
arXiv:2609.37001v1 Announce Type: cross Abstract: Diffusion Transformers (DiTs) enable high-quality video generation but suffer from substantial inference latency, primarily attributable to the computationally expensive…
- arXiv cs.AIresearchVisual Parallel Search: Learning to Search High-Resolution Images with Parallel Tile Inspection and Adaptive Zoom
arXiv:2609.37002v2 Announce Type: replace-cross Abstract: High-resolution visual question answering often fails because a multimodal model does not acquire the small, spatially localized evidence needed to answer a quest…
- arXiv cs.AIresearchOPFL: Optimistic Verification of Federated Learning via Empirical Boundary
arXiv:2609.37011v1 Announce Type: cross Abstract: Federated learning enables multiple clients to collaboratively train models without sharing their private data. However, the lack of visibility into local training makes…
- arXiv cs.AIresearchEmbedded Bi-Temporal Building Damage Assessment for On-Board Data Reduction
arXiv:2609.37013v2 Announce Type: replace-cross Abstract: Rapid assessment of building damage after natural disasters is essential to support emergency response. Earth Observation satellites can acquire relevant imagery…
- arXiv cs.AIresearchLongSpark: Efficient speculative decoding with a fixed-cost parallel drafter
arXiv:2609.37029v2 Announce Type: replace-cross Abstract: Speculative decoding accelerates autoregressive inference by verifying multiple draft tokens in a single target forward pass. However, as the context grows, exist…
- arXiv cs.AIresearchMotionInsight: Diagnosing Object Motion Deficiencies in Generated Videos
arXiv:2609.37030v1 Announce Type: cross Abstract: Despite rapid progress in video generation models, they still exhibit obvious motion deficiencies, often manifested as incorrect object motion. However, most existing vid…
- arXiv cs.AIresearchNowcastDiT: Diffusion Transformers are Effective Precipitation Nowcasters
arXiv:2609.37038v1 Announce Type: cross Abstract: Precipitation nowcasting demands accurate short-term forecasts under strong spatiotemporal variability. Diffusion models are well suited to modeling complex precipitation…
- arXiv cs.AIresearchSelecting The Most Informative Tokens in Natural Language Autoencoders
arXiv:2609.37040v1 Announce Type: cross Abstract: Natural language autoencoders translate a language model's internal activations into readable explanations. Explaining every token position is costly. Which positions sho…
- arXiv cs.AIresearchBeam Search as Test-Time Self-Distillation via Counterfactual Contexts
arXiv:2609.37041v1 Announce Type: cross Abstract: Self-Distillation Fine-Tuning (SDFT) enables a language model to act as its own teacher: by conditioning on a demonstration, the model produces an implicit reward via poi…
- arXiv cs.AIresearchEvolving Towards Better Codes: LLM-Guided Search for High-Distance Binary Linear Codes
arXiv:2609.37056v1 Announce Type: cross Abstract: Evolutionary program search driven by large language models (LLMs) has produced record-breaking constructions for open problems in combinatorics and beyond. We apply this…
- arXiv cs.AIresearchA Comprehensive View of Fairness through Distributional Stability
arXiv:2609.37061v2 Announce Type: replace-cross Abstract: We view fairness as a property of distributional stability. Rather than assessing a predictor under a fixed data distribution, we study how its predictions change…
- arXiv cs.AIresearchBeyond Compression: Diagnosing How Post-Training Changes Mathematical Reasoning
arXiv:2609.37066v1 Announce Type: cross Abstract: Post-training is central to mathematical reasoning in modern large language models (LLMs), but endpoint pass@1 alone underidentifies what has changed. Gains may reflect n…
- arXiv cs.AIagentsFACT: Fidelity-Aware Construction of Articulated Twins
arXiv:2609.37067v2 Announce Type: replace-cross Abstract: Visually plausible articulated assets may still fail during contact interactions or exhibit inaccurate motion. We present FACT (Fidelity-Aware Construction of Art…
- arXiv cs.AIresearchPredictive Safety Curricula for Robust Legged Locomotion
arXiv:2609.37070v1 Announce Type: cross Abstract: Rare but consequential failures can persist in learned locomotion policies for legged robots even when average task performance is high, in part because standard curricul…
- arXiv cs.AIresearchIdentifying ODEs from Unstructured Data with Causal Representation Learning
arXiv:2609.37083v1 Announce Type: cross Abstract: We study the problem of recovering the governing ODE of a dynamical system from unstructured, high-dimensional observations such as images. Existing methods for ODE disco…
- arXiv cs.AIresearchARGOS: Reinforcement Learning-Driven Multidimensional Elasticity for Service Orchestration in the Computing Continuum
arXiv:2609.37085v2 Announce Type: replace-cross Abstract: Data-intensive services in the Computing Continuum must balance analytics quality, resource usage, and cost across heterogeneous nodes with limited and uneven cap…
- arXiv cs.AIresearchWhat Does Post-Training Change in Multilingual Reasoning?
arXiv:2609.37104v1 Announce Type: cross Abstract: Open-source reasoning models provide unequal access to reasoning capability across languages. When a model can solve a problem but cannot deliver a complete solution in t…
- arXiv cs.AIagentsVACE: Validation-Gated Alternating Co-Evolution of Agent Models and Harnesses
arXiv:2609.37105v1 Announce Type: cross Abstract: Language model agents can be improved by updating their model weights or refining the harness that guides task execution. These components are coupled: weight updates cha…
- arXiv cs.AIresearchDesigning a Boundary Negotiating Artifact for Collaborative Socio-Technical Sense-Making in AI Regulatory Sandboxes
arXiv:2609.37109v1 Announce Type: cross Abstract: The rapid, unpredictable advancements in AI system capabilities has seen regulators take adaptive and experimental approaches to policymaking. Established in other domain…
- arXiv cs.AIresearchMultichannel Audio Quality Assessment: Extending Pretrained Perceptual Models to Spatial Audio
arXiv:2609.37116v1 Announce Type: cross Abstract: Accurate perceptual quality assessment is essential for evaluating and optimizing spatial audio, where perceived quality depends on both signal fidelity and inter-channel…
- arXiv cs.AIresearchUnlocking the Critic: Reward-Free Policy Optimization for LLM Post-Training
arXiv:2609.37119v1 Announce Type: cross Abstract: Recent approaches to reinforcement learning (RL) post-training for large language models increasingly remove the critic to reduce training instability and memory overhead…
- arXiv cs.AIresearchSQUARE: Structured Quantum Representation Adapters as Compact Quadratic Feature Maps for Frozen Language Models
arXiv:2609.37134v1 Announce Type: cross Abstract: Frozen language models (LMs) are increasingly used as fixed feature extractors for downstream reranking, scoring, and preference modeling, raising a practical question: h…
- arXiv cs.AIagentsLucid Dreaming for World Models: Learning to Doubt Imagination and Decide by Trust
arXiv:2609.37156v1 Announce Type: cross Abstract: World models enable agents to learn and plan in imagination, but predictions beyond their experience can become unreliable and mislead decisions. Existing uncertainty est…
- arXiv cs.AIresearchTrajectory Soup: Pushing the Compute-Scaling Frontier of LLM Mid-training via Diverse Trajectories
arXiv:2609.37169v1 Announce Type: cross Abstract: Mid-training equips pretrained large language models with specialized and reasoning capabilities, but the returns of this stage are bounded since additional serial comput…
- arXiv cs.AIresearchInterpolated Policy Distillation: A Controllable Continuum Between Off-Policy and On-Policy Distillation
arXiv:2609.37170v1 Announce Type: cross Abstract: Off-policy and on-policy distillation have traditionally been formulated as separate paradigms, each favoring a different property of distillation trajectories. Teacher-g…
- arXiv cs.AIresearchEgoHumanoid-V2: Human-to-Humanoid Transfer of Coordinated Whole-Body Skills for Loco-Manipulation
arXiv:2609.37181v1 Announce Type: cross Abstract: Human demonstrations capture diverse scenes and rich whole-body skills without requiring robot teleoperation. Prior work on egocentric transfer has emphasized scene gener…
- arXiv cs.AIagentsToolFence: Fine-Grained Authorization for Secure Tool-Using LLM Agents
arXiv:2609.37196v1 Announce Type: cross Abstract: Tool-using LLM agents remain vulnerable to indirect prompt injection because trusted instructions and untrusted observations share one context, allowing malicious content…
- arXiv cs.AIresearchCRJudgeBench: Can AI Detect Plausible but Invalid Code Reviews?
arXiv:2609.37216v1 Announce Type: cross Abstract: Large language models can generate plausible code-review comments, but such comments may contain technically incorrect claims that mislead developers. We study technical…
- arXiv cs.AIresearchBeyond Semantic Narrowing: Robust and Efficient LLM Watermarking with Hamming Neighborhoods
arXiv:2609.37218v1 Announce Type: cross Abstract: Semantic watermarking improves robustness against watermark removal attacks by embedding detectable signals into sentence-level representations. However, existing waterma…
- arXiv cs.AIresearchResComEmb: Effective and Efficient Multimodal Embedding via Residual Homogeneity Compression
arXiv:2609.37225v1 Announce Type: cross Abstract: Multimodal large language models (MLLMs) have shown strong potential for universal multimodal representation learning. However, existing methods either compress each inpu…
- arXiv cs.AIagentsFollow the Entities: A Corpus Map for Agentic Search
arXiv:2609.37226v1 Announce Type: cross Abstract: Answering questions and completing tasks over large document collections often requires connecting evidence spread across multiple documents, such as a project's approval…
- arXiv cs.AIresearchDatalogBench: Evaluating Large Language Models on Text-to-Datalog Synthesis
arXiv:2609.37233v1 Announce Type: cross Abstract: Datalog underpins reasoning tasks such as program analysis, but its programs are hard to write. Existing synthesizers automate this task but require users to state their…
- arXiv cs.AIresearchCodebook-Guided Cross-Modal Knowledge Distillation for Structurally Heterogeneous Features
arXiv:2609.37243v2 Announce Type: replace-cross Abstract: Cross-modal knowledge distillation transfers knowledge from a teacher modality to a student modality. Existing feature-level alignment methods typically assume th…
- arXiv cs.AIresearchV-JEPA Policy: Building Effective World-Action Models on Predictive Visual Latents
arXiv:2609.37250v2 Announce Type: replace-cross Abstract: World-action models (WAMs) couple future visual-state prediction with action generation. By adapting video generators or image-editing models pretrained at scale,…
- arXiv cs.AIresearchLoss-Guided Pretraining Data Selection for Time-Series Foundation Models
arXiv:2609.37255v1 Announce Type: cross Abstract: Time series foundation models (TSFMs) are pretrained on heterogeneous collections containing billions of observations, yet their training windows are typically sampled wi…
- arXiv cs.AIresearchUniAfford: Token-Routed Multitask Learning for Generalizable 2D-3D Affordance Perception
arXiv:2609.37264v1 Announce Type: cross Abstract: Affordance perception aims to localize actionable regions supporting embodied interaction, yet 2D and 3D affordance grounding have evolved as separate problems, with diff…
- arXiv cs.AIresearchVISTA-Bench: Benchmarking Multilingual Image Translation with Image-Specific Rubrics
arXiv:2609.37287v1 Announce Type: cross Abstract: Image translation is a fundamental capability of multimodal models for multilingual applications, requiring visual understanding and meaning preservation across languages…
- arXiv cs.AIresearchHidden Reasoning Must Leak, but Need Not Be Readable: Fundamental Opportunities and Limits for Chain-of-Thought Monitoring
arXiv:2609.37312v1 Announce Type: cross Abstract: Can reasoning models trick chain of thought (CoT) monitors and perform hidden computation without revealing it in their thinking traces? We show that the answer depends o…
- arXiv cs.AIagentsDo Agent Benchmarks Do What They Say? An Executable-Contract Audit of Tool-Using Agent Environments
arXiv:2609.37315v1 Announce Type: cross Abstract: Tool-using agents are entering settings where a wrong action carries real cost, and the benchmarks certifying them grade what each simulated tool call reports having done…
- arXiv cs.AIagentsPowerMarketJax: A JAX Benchmark Suite for Multi-Agent Reinforcement Learning in Power Markets
arXiv:2609.37321v1 Announce Type: cross Abstract: Power markets are a natural testbed for multi-agent reinforcement learning (MARL), where multiple self-interested participants repeatedly submit bids. A market-clearing m…
- arXiv cs.AIresearchA Sharp Transition in Data Reconstruction under Differential Privacy
arXiv:2609.37344v1 Announce Type: cross Abstract: Data reconstruction attacks have empirically been successful in recovering training samples from learned models, raising privacy concerns and motivating defenses with gua…