AI news archive.
10,661 articles filed under Research, newest first, from the outlets listed on the sources page.
- arXiv cs.AIresearchSecond-Moment Stochastic Approximation Methods
arXiv:2609.36600v1 Announce Type: cross Abstract: Classical stochastic approximation methods rely on estimators of the first moment (mean) of a random regression function. We study methods that employ estimators of both…
- arXiv cs.AIresearchInducing Process Supervision from Outcome-Only Reinforcement Learning
arXiv:2609.36641v1 Announce Type: cross Abstract: Process reward models (PRMs) have become a key component for LLMs, as their step-level feedback supports both post-training and test-time reasoning. However, training str…
- arXiv cs.AIresearchWhere Predictive Supervision Goes Shapes What VLA Policies Learn
arXiv:2609.36645v2 Announce Type: replace-cross Abstract: Future prediction is increasingly used to improve vision-language-action (VLA) policies, based on the premise that anticipating scene evolution encourages represe…
- arXiv cs.AIresearchFocusVTC: Efficient and High-Performance Visual Text Compression with Adaptive Resolution
arXiv:2609.36651v1 Announce Type: cross Abstract: Long-context reasoning in large language models incurs substantial computation and memory costs. Visual text compression (VTC) reduces input length by rendering text as i…
- arXiv cs.AIresearchConstitutional adapters: Inference-time interventions for misalignment and misuse
arXiv:2609.36657v1 Announce Type: cross Abstract: Training models to act in accordance with an explicitly defined set of principles, or "constitution," has shown promise as a robust and transparent mechanism for AI align…
- arXiv cs.AIresearchAutoLoCo: Communication Efficient Distributed LLM Training via Adaptive Synchronization
arXiv:2609.36662v1 Announce Type: cross Abstract: The pre-training of Large Language Models (LLMs) is increasingly conducted across multiple data centers. As training scales to a larger number of accelerators, the fracti…
- arXiv cs.AIresearchMyoCodec: A Streaming Neural Codec for Electromyography
arXiv:2609.36687v1 Announce Type: cross Abstract: Neural codecs encode continuous signals into compact sequences of discrete tokens, providing an interface for efficient transmission, storage, and token-based sequence mo…
- arXiv cs.AIresearchNormalize-Then-Precondition: A Hierarchical Approach to Marginal Scale and Interaction Geometry for LLM Training
arXiv:2609.36692v1 Announce Type: cross Abstract: Matrix optimizers have emerged as a promising direction, with Muon standing out as a prominent design. Revisiting Muon through its full-Gram representation, we observe th…
- arXiv cs.AIresearchLost in Conversation or Lost in Translation? Diagnosing Multi-Turn Degradation in RAG
arXiv:2609.36700v1 Announce Type: cross Abstract: When conversing with large language models (LLMs), users often begin with a simple question and build towards a multi-hop question through follow-up turns. Retrieval-augm…
- arXiv cs.AIresearchGroup-Marginalized Self-Rewarding RL Drives Zero-Label Self-Evolving
arXiv:2609.36750v1 Announce Type: cross Abstract: Self-rewarding reinforcement learning (RL) enables large language models (LLMs) to self-evolve without human labels. Existing ensemble-based methods construct reward refe…
- arXiv cs.AIresearchNesTok: Nested Self-Aligned 1D Tokenizer for Autoregressive Image Generation
arXiv:2609.36756v3 Announce Type: replace-cross Abstract: One-dimensional (1D) variable-length visual tokenizers enable adaptive compression by varying the number of tokens, allowing downstream autoregressive (AR) models…
- arXiv cs.AIresearchDual-Mode Low-Rank Learner with Bridge-Prototype Ensemble for Vision-Language Class-Incremental Learning
arXiv:2609.36759v1 Announce Type: cross Abstract: Benefiting from transferable visual-textual alignment, CLIP has been widely adopted for class-incremental learning (CIL). However, existing learners either repeatedly upd…
- arXiv cs.AIresearchBeyond Conditional Independence: Root Cause Analysis with Deep Causal Models
arXiv:2609.36771v1 Announce Type: cross Abstract: Root cause analysis (RCA) is a critical problem in many real-world scenarios. RCA enables the identification of faulty or failing mechanisms in a system by comparing anom…
- arXiv cs.AIresearchVAA-CSEC: Vote-guided Advantage Allocation for Chinese Semantic Error Correction
arXiv:2609.36804v1 Announce Type: cross Abstract: Chinese Semantic Error Correction (CSEC) targets semantic errors in Chinese text, which are typically more subtle and complex than spelling and grammatical errors but rem…
- arXiv cs.AIresearchSpotter: Let the Embodied Model Lead, and the VLM Reflect for It
arXiv:2609.36808v1 Announce Type: cross Abstract: Current embodied models do not respond to their own failures, although what just went wrong could inform a small adjustment on the next attempt, the kind of reflection be…
- arXiv cs.AIresearchDiffusion Policy Improvement with Proposal-Conditioned Refinement Flows
arXiv:2609.36812v2 Announce Type: replace-cross Abstract: Diffusion and flow policies can model complex behaviors in offline reinforcement learning (RL). However, penalizing their KL divergence from the behavior policy c…
- arXiv cs.AIresearchDSWM: Decomposed Spatio-Temporal World Model for Demand-Driven UAV Base Station Repositioning
arXiv:2609.36845v1 Announce Type: cross Abstract: Uncrewed aerial vehicle base stations (UAV-BSs) are expected to cover traffic demand that shifts across space and time, yet most repositioning schemes either re-solve an…
- arXiv cs.AIresearchSafer Content or Firmer Refusals? A Hybrid Perturbation Defense for Alignment under Harmful Fine-tuning
arXiv:2609.36862v1 Announce Type: cross Abstract: Fine-tuning-as-a-service lets users adapt a safety-aligned language model to their own data, but it also creates a harmful fine-tuning attack surface: a small amount of h…
- arXiv cs.AIresearchDigital Twin Modeling of Quantum Dynamical Systems: Dissipative Quantum Reservoir Computing
arXiv:2609.36901v1 Announce Type: cross Abstract: Modeling the response of driven many-body quantum systems from input--output data is difficult: the dynamics are nonlinear, history dependent, and expensive to simulate a…
- arXiv cs.AIresearchMultiTalk: Scaling Full-Duplex Speech Models to Long, Multi-Party, Bilingual Conversation
arXiv:2609.36903v1 Announce Type: cross Abstract: End-to-end full-duplex speech models have brought open-source machine conversation closer to human-like interaction, yet existing systems remain limited in two intertwine…
- arXiv cs.AIresearchBaLEEN: Biasing with Latent Encoded Entities for Context-Aware ASR
arXiv:2609.36913v1 Announce Type: cross Abstract: Transcribing domain-specific entities and rare proper nouns remains a major challenge in automatic speech recognition (ASR). In this paper, we propose BaLEEN (Biasing wit…
- arXiv cs.AIresearchAeroManip-VLA: Scalable Vision-Language-Action Learning for Aerial Manipulation with RL-Generated Demonstrations
arXiv:2609.36915v1 Announce Type: cross Abstract: Aerial manipulators extend robotic manipulation into 3D workspaces that are difficult for ground-based robots to access, creating new opportunities for general-purpose ma…
- arXiv cs.AIresearchState Transport Routing for Short-horizon Adaptation in Multi-horizon Photovoltaic Forecasting
arXiv:2609.36926v1 Announce Type: cross Abstract: Recent power measurements provide valuable information for photovoltaic(PV) power forecasting, but directly extrapolating short-term trends can introduce substantial erro…
- arXiv cs.AIresearchWeLike2Party! In-Context Motion Transfer for Multi-Human Image Animation
arXiv:2609.36937v3 Announce Type: replace-cross Abstract: Human image animation aims to transfer motion from a driving video to subjects in a reference image. Despite remarkable progress in video generation, achieving hi…
- arXiv cs.AIresearchSafe-by-Design Learning via Energy-based Neural Networks
arXiv:2609.36942v2 Announce Type: replace-cross Abstract: Learning neural-network models of dynamical systems with safety guarantees is a fundamental requirement for their deployment in safety-critical settings. Safety i…
- 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.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…