AI news archive.
10,661 articles filed under Research, newest first, from the outlets listed on the sources page.
- arXiv cs.AIresearchSupervising Sound Localization by In-the-wild Egomotion
arXiv:2610.01388v1 Announce Type: cross Abstract: We present a method for learning binaural sound localization using egomotion as a supervisory signal. Over the course of a video, the cameras direction to a sound source…
- arXiv cs.AIresearchLLM-Assisted Discovery of Typed Semantic Links for Ontology Network Construction
arXiv:2610.01393v1 Announce Type: cross Abstract: Constructing typed, justified semantic links between ontologies is essential for enabling interoperability across heterogeneous and interdisciplinary knowledge domains. H…
- arXiv cs.AIresearchOptimal Transport Meets Reinforcement Learning: A Survey
arXiv:2610.01413v1 Announce Type: cross Abstract: Reinforcement learning (RL) algorithms frequently compare probability distributions, such as state visitation distributions induced by policies and experts, action distri…
- arXiv cs.AIresearchGeneralization Is Stability, Not Accuracy: Multi-Axis Evaluation of LLMs
arXiv:2610.01428v1 Announce Type: cross Abstract: Generalization in large language models (LLMs) is the ability to produce consistent and semantically stable outputs when the same input is expressed in different ways. Ex…
- arXiv cs.AIresearchMWOP: Modality-aware Width-wise Operation Pruning for Efficient MLLMs
arXiv:2610.01434v1 Announce Type: cross Abstract: Multimodal large language models (MLLMs) incur substantial inference costs when processing long visual-textual sequences. While existing operation compression methods exp…
- arXiv cs.AIresearchWhen Does a Second Model Help? Cross-Model Review in LLM Verification
arXiv:2610.01471v2 Announce Type: replace-cross Abstract: Large language models now generate code, documentation, and analyses, and are increasingly used to review such output. We ask when a second review by a different…
- arXiv cs.AIresearchMulti-Party Backchannel Prediction: a Diagnosis, a Benchmark, and a Ceiling
arXiv:2610.01488v1 Announce Type: cross Abstract: Backchannel prediction has been studied almost entirely in dyadic conversation. We introduce a multi-party benchmark based on the AMI corpus, comprising 682 masked-listen…
- arXiv cs.AIresearchNo Model Required: Text Entropy Rate Filtering Mitigates Iterative Fine-Tuning Collapse
arXiv:2610.01493v1 Announce Type: cross Abstract: Iterative fine-tuning on synthetic data causes \emph{model collapse}: output diversity narrows as rare patterns are progressively lost, a signature most visible as phrase…
- arXiv cs.AIresearchFedMIX-P: Mixing Local and Global Preconditioners for Federated Vision and Language Model Training
arXiv:2610.01515v1 Announce Type: cross Abstract: Adaptive preconditioners accelerate model training, but heterogeneous client geometries can bias federated updates even when gradients are evaluated at the same model. Ro…
- arXiv cs.AIresearchAuto-Formalizing Neuro-Symbolic Predictors
arXiv:2610.01519v1 Announce Type: cross Abstract: Neuro-Symbolic (NeSy) predictors incorporate prior knowledge into the prediction process of neural networks, ensuring that outputs satisfy specified constraints, making t…
- arXiv cs.AIresearchExact Distinguishability in Non-Markovian Decision Processes
arXiv:2610.01527v1 Announce Type: cross Abstract: Non-Markovian environments are often modeled as Regular Decision Processes (RDPs), where dynamics depend on the interaction history through a finite automaton. Existing o…
- arXiv cs.AIresearchFalse Floors: LLM Safety Routing Evaluations Break Under Distribution Shift
arXiv:2610.01535v1 Announce Type: cross Abstract: Safety routers send each request to one of several models and are judged against the best single model. A major routing benchmark picks that comparator on the evaluation…
- arXiv cs.AIresearchReinforcement Learning to Accelerate Primal-Dual Hybrid Gradient for Linear Programming
arXiv:2610.01546v1 Announce Type: cross Abstract: Primal-dual hybrid gradient (PDHG) methods solve large-scale linear programs (LPs) using GPU-friendly matrix-vector products and projections, but their practical performa…
- arXiv cs.AIresearchCompletion Aware Guidance for World Action Models
arXiv:2610.01559v2 Announce Type: replace-cross Abstract: World Action Models (WAMs) predict visual futures and robot actions, yet they remain susceptible to task-incomplete imagination, where plausible, action-consisten…
- arXiv cs.AIresearchBeyond Pointwise Error: A Multi-Metric Evaluation of Spatial Climate Downscaling
arXiv:2610.01579v1 Announce Type: cross Abstract: Climate downscaling aims to reconstruct fine scale spatial fields from coarse resolution inputs. Evaluating the quality of these reconstructions is challenging: low point…
- arXiv cs.AIresearchBefore It Fades: Reinforcing Temporal Representations at Inference Time in VideoLLMs
arXiv:2610.01595v1 Announce Type: cross Abstract: Video Large Language Models (VideoLLMs) receive frames in sequential order and interpret how visual content evolves along the temporal axis, yet temporal reasoning remain…
- arXiv cs.AIresearchPermutation-Robust Decision Modeling with Candidate-Independent Block-Causal Attention
arXiv:2610.01601v1 Announce Type: cross Abstract: Decision models often score a variable-sized set of candidate actions encoded in a single sequence. This setting is increasingly relevant for System 1 components inside g…
- arXiv cs.AIresearchHob-VL: A Benchmark for Visually Grounded Boolean Reasoning
arXiv:2610.01605v1 Announce Type: cross Abstract: Reliable visual reasoning requires composing multiple visual observations and returning consistent answers to logically equivalent questions. We introduce Hob-VL, a bench…
- arXiv cs.AIresearchCan LLMs Reliably Annotate Bioassay Metadata to Improve Data Readiness?
arXiv:2610.01616v1 Announce Type: cross Abstract: The emergence of foundation models for molecular property prediction requires a high degree of AI data readiness, including reliable metadata annotation. However, both pu…
- arXiv cs.AIresearchExposing the Cost of Deep Learning Audio Development
arXiv:2610.01619v1 Announce Type: cross Abstract: The environmental impact of deep learning has attracted increasing attention over the past decade. Existing studies mainly focus on the energy and carbon emissions of mod…
- arXiv cs.AIresearchWhat Makes Something Hard(er)? Explaining Question Difficulty in Natural Language
arXiv:2610.01627v1 Announce Type: cross Abstract: Difficulty is one of the most fundamental properties of a question: it determines whether the question can meaningfully discriminate between models of differing ability.…
- arXiv cs.AIresearchNot All Error Yields to Scale: Where Scaling Stops in Vision-Language Inference
arXiv:2610.01640v1 Announce Type: cross Abstract: Vision-language models (VLMs) face a fixed-budget trade-off between processing more visual information for fine-grained perception and using a larger language backbone fo…
- arXiv cs.AIresearchMCIR: A Feature Dependence-Aware Explainability Method with Reliability Guarantees
arXiv:2610.01641v1 Announce Type: cross Abstract: Modern machine-learning models often contain strongly dependent or redundant features, making feature attribution difficult because shared predictive information can be d…
- arXiv cs.AIresearchIterative Policy Refinement through Semantic Rollout Analysis
arXiv:2610.01652v1 Announce Type: cross Abstract: Structured policies improve efficiency, robustness, and interpretability in imitation learning by introducing task-specific inductive bias, but existing structure generat…
- arXiv cs.AIresearchArchitectural Sampling: Test-Time Scaling via Computational Diversity in Frozen Vision-Language Models
arXiv:2610.01687v1 Announce Type: cross Abstract: Test-time scaling often seeks better answers by sampling multiple responses from a frozen model, yet conventional temperature sampling generates every candidate along the…
- arXiv cs.AIresearchArchitecture Without an Architect? Global Governance of Artificial Intelligence in a Divided World
arXiv:2610.01716v1 Announce Type: cross Abstract: Artificial intelligence presents an unusually difficult problem for global governance. The technology develops rapidly, crosses borders easily, and is shaped by actors wh…
- arXiv cs.AIresearchRemoving spurious minima for planar features by skip connections
arXiv:2610.01728v2 Announce Type: replace-cross Abstract: Understanding loss landscapes is central to explaining neural-network training, yet their structure remains only partially understood even in simple models. We st…
- arXiv cs.AIresearchCog-VADU: A Training-Free Cognitive Reasoning Framework for Video Anomaly Detection and Understanding
arXiv:2610.01754v1 Announce Type: cross Abstract: Video Anomaly Detection (VAD) aims to temporally localize abnormal events in videos. Most existing approaches rely on dataset-specific training and curated annotations, l…
- arXiv cs.AIresearchCODesign: Consistency from Data to Trajectory in All-Atom Protein Binder Co-Design
arXiv:2610.01773v1 Announce Type: cross Abstract: The central challenge in de novo protein design is generating plausible, mutually compatible structures and sequences, such that each designed sequence folds into its int…
- arXiv cs.AIresearchVETO: Video Efficient Token Optimization for Vision Language Models
arXiv:2610.01785v1 Announce Type: cross Abstract: Processing long videos with Vision-Language Models (VLMs) is bottlenecked by the quadratic cost of visual tokens, making long-form inference prohibitively expensive. Whil…
- arXiv cs.AIresearchiADD: Improving Alignment and Diversity in Diffusion Policy Optimization
arXiv:2610.01789v1 Announce Type: cross Abstract: Reinforcement learning based post training of diffusion models, such as Denoising Diffusion Policy Optimization (DDPO), optimizes a reverse diffusion process under a rewa…
- arXiv cs.AIresearchDetecting Inconsistencies in Model Specifications with LLM-as-Verifier Reasoning
arXiv:2610.01847v1 Announce Type: cross Abstract: Model specifications define how large language models (LLMs) should behave, guiding alignment training, inference-time behavior, and evaluation. Yet these specifications…
- arXiv cs.AIresearchFrom Isolated Feature to Orbits: Discovering Music Concepts via Multi-SAE Alignment
arXiv:2610.01864v1 Announce Type: cross Abstract: How can we understand what a music foundation model has learned \textit{internally}? Most interpretability approaches, such as probing and Sparse Autoencoders (SAEs), foc…
- arXiv cs.AIresearchWalking the Embedding Space: Datastore Extraction from Multimodal RAG
arXiv:2610.01871v1 Announce Type: cross Abstract: Multimodal Retrieval-Augmented Generation (MRAG) has emerged as a reliable and cost-effective technique of grounding the generative capabilities of Multimodal Large Langu…
- arXiv cs.AIresearchFrom Network Intrusion Detection to Blockchain-Backed Endpoint Detection and Response: Mapping the Landscape of Decentralized Detection-and-Response Architectures
arXiv:2610.01872v1 Announce Type: cross Abstract: While the literature on blockchain-assisted intrusion detection and prevention systems (IDS/IPS) for Internet of Things (IoT) and Industrial Internet of Things (IIoT) net…
- arXiv cs.AIresearchUnsupervised Domain Adaptation for Enhanced Radiometer Image Precipitation Estimation using Conditional Flow Matching
arXiv:2610.01890v1 Announce Type: cross Abstract: Deep generative networks have recently achieved unprecedented performance in precise image and video editing using sophisticated textual prompts. However, the effectivene…
- arXiv cs.AIresearchA Structured State Space Sequence Model for Multi-Class Classification of Malware
arXiv:2610.01893v1 Announce Type: cross Abstract: By 2030, Internet of Things (IoT) devices are projected to reach 40 billion, with fast-paced technological advancements in fields such as industry, healthcare, agricultur…
- arXiv cs.AIresearchAsynchronous LLM Post-Training: Group-Mass Capping and Convergence Analysis
arXiv:2610.01896v1 Announce Type: cross Abstract: Asynchronous reinforcement learning (RL) improves the efficiency of large language model post-training but introduces stale rollouts generated by earlier policies. Theore…
- arXiv cs.AIresearchMoLE: Mixture of Latent Experts for Complementary Visual Reasoning
arXiv:2610.01917v2 Announce Type: replace-cross Abstract: Latent visual reasoning equips vision--language models with continuous intermediate states that can process visual evidence without explicit textual reasoning tra…
- arXiv cs.AIresearchCross-Lingual Alignment for Decoder-Only Models using MoE Routers
arXiv:2610.01921v2 Announce Type: replace-cross Abstract: Cross-lingual contrastive learning has been a core component of multilingual encoder training, but the ability to explicitly align representations is not possible…
- arXiv cs.AIresearchA rubric landscape for evaluating clinical reasoning in large language models: what exists, what is missing, and what needs to be combined
arXiv:2610.01938v2 Announce Type: replace-cross Abstract: Exam-style accuracy does not establish whether large language models (LLMs) reason well over clinical records. We define clinical reasoning as integrating and upd…
- arXiv cs.AIresearchA Hybrid Approach to Malware Detection: Integrating Few-Shot Model-Agnostic Meta-Learning with Autoencoders
arXiv:2610.01949v1 Announce Type: cross Abstract: Ransomware has emerged as a major cybersecurity threat, with incidents increasing in frequency and impact across critical sectors. These attacks are typically launched th…
- arXiv cs.AIresearchExploring Weaknesses of Generative Image Watermarks against Latent Frequency Masking
arXiv:2610.02010v1 Announce Type: cross Abstract: Invisible watermarking has become a central tool for tracing AI-generated images, but its robustness against adaptive removal attacks remains an open security question. W…
- arXiv cs.AIresearchOn Language Drift during RLVR Post-Training
arXiv:2610.02015v1 Announce Type: cross Abstract: Recent advances in LLM reasoning models---driven primarily by the paradigm of post-training via reinforcement learning with verifiable reward (RLVR)---have enabled them t…
- arXiv cs.AIresearchTask-Adaptive Grounded 3D-Programmers Using 2D VLMs
arXiv:2610.02021v1 Announce Type: cross Abstract: Recent vision-language models (VLMs) exhibit remarkable generalization and reasoning abilities, yet 3D understanding in these models is limited by data scale, training di…
- arXiv cs.AIresearchCARM: Cancellation-Aware Response Masking for LLM Reinforcement Learning
arXiv:2610.02039v1 Announce Type: cross Abstract: Recent years have witnessed the rapid adoption of reinforcement learning (RL) in large language model (LLM) post-training, with substantial gains in mathematical reasonin…
- arXiv cs.AIresearchDistributionally Robust Schr\"odinger Bridge
arXiv:2610.02043v1 Announce Type: cross Abstract: Schr\"odinger bridge (SB) learns stochastic transport between prescribed initial and target distributions. When the initial distribution shifts at test time, the learned…
- arXiv cs.AIresearchHumanoidToolBench: Benchmarking Humanoid Tool Use from Selection to Mobile Execution
arXiv:2610.02089v1 Announce Type: cross Abstract: As robotic hardware and learning methods advance, humanoids need tools to perform tasks beyond their inherent physical limits. Successful tool use requires selecting a su…
- arXiv cs.AIresearchGeoLatent: Geometry-Guided Latent Structuring with Routed Optimization for 3D Reasoning
arXiv:2610.02091v1 Announce Type: cross Abstract: Despite progress in vision-language models, 3D spatial reasoning from 2D images remains challenging. Text-based methods describe intermediate geometry with discrete token…
- arXiv cs.AIresearchScalable, Transferable Meta-network for Data Selection Requires a Different Loss (and Why the Obvious Choice is Problematic)
arXiv:2610.02092v1 Announce Type: cross Abstract: Data selection is critical for training large language models on massive and heterogeneous corpora. Meta-learning for Training-data Selection offers a principled alternat…