AI news archive.
19,861 articles, newest first, from the outlets listed on the sources page.
- arXiv cs.AIresearchRadar-Based 3D Human Pose Estimation via Motion-Aware Pose Initialization and Observation-Guided Refinement
arXiv:2610.27774v1 Announce Type: cross Abstract: 3D Human Pose Estimation (3D HPE) is used in indoor environments, such as smart homes, to analyze human movement and monitor human states. Millimeter-wave (mmWave) radar…
- arXiv cs.AIagentsRELAY: Scaling Historical Build Restoration through Rule Reuse and Agentic Repair
arXiv:2610.27784v1 Announce Type: cross Abstract: Vulnerability benchmarks and software engineering research depend on rebuilding historical software. Yet builds rely on external resources, such as base images and packag…
- arXiv cs.AIresearchSLM-SS: Token-Based Speech Separation with Speech Language Models
arXiv:2610.27785v1 Announce Type: cross Abstract: Speech separation (SS) has witnessed substantial progress in recent years with the advent of neural network-based methods, achieving notable improvements on signal-level…
- arXiv cs.AIresearchRAG-NIMBF: A Non-Invasive, Modular Benchmarking Framework for Automated RAG Configuration Analysis
arXiv:2610.27816v1 Announce Type: cross Abstract: Retrieval-Augmented Generation (RAG) has become the dominant paradigm for grounding the outputs of large language models (LLM) in external knowledge. However, practitione…
- arXiv cs.AIresearchSMART: Semantic Segment Mapping and Assessment of Recognition Transcripts with Contextual Rubrics
arXiv:2610.27820v1 Announce Type: cross Abstract: Word error rate (WER) assigns equal cost to lexical edits despite their different semantic consequences, while overall semantic scores cannot identify which individual er…
- arXiv cs.AIresearchVISH-ASR: Viterbi-Guided Selection of Hotwords for Speech-LLM Contextual ASR
arXiv:2610.27867v1 Announce Type: cross Abstract: Prompt-based contextual ASR requires selecting a compact hotword subset from large dynamic inventories, yet existing pre-selection methods rely either on discrete ASR hyp…
- arXiv cs.AIresearchHallucinations of Large Language Models in Cross-Language Code Translation: Phenomena and Mitigation
arXiv:2610.27868v1 Announce Type: cross Abstract: Code translation converts source code from one programming language to another while preserving its functionality. Although Large Language Models (LLMs) have improved cod…
- arXiv cs.AIresearchPhysical-Variable-Informed Deep Learning for Robust Diagnosis in Industrial Fluid Transport Systems
arXiv:2610.27891v1 Announce Type: cross Abstract: Industrial fluid transport systems are monitored through heterogeneous sensing streams, but robust fault diagnosis remains difficult because response signals vary with op…
- arXiv cs.AIresearchThe Shape of the DPO Hyperparameter Landscape: What to Measure, How It Moves with Scale, and When Not to Transfer It
arXiv:2610.27895v2 Announce Type: replace-cross Abstract: Direct preference optimisation (DPO) is widely used for language model post-training, but its performance depends strongly on the choice of its hyperparameters, s…
- arXiv cs.AIresearchCollabSciReM: Aligning Language Models for Scientific Conversations via Science-Aware Reward Decomposition
arXiv:2610.27901v1 Announce Type: cross Abstract: Large Language Models (LLMs) are increasingly used as research collaborators for hypothesis refinement, methodological planning, and technical analysis across multi-turn…
- arXiv cs.AIresearchPolarity Blindness in LLM Safety: A Systematic Study of Negation, Antonym Substitution, and Adversarial Framing
arXiv:2610.27908v1 Announce Type: cross Abstract: Negation remains a persistent challenge for language models across NLP tasks and modalities. We show that this weakness can undermine LLM safety guardrails through a stru…
- arXiv cs.AIresearchAPRIL: Ambiguity-Aware Expert Routing for Respiratory Sound Domain-Incremental Learning
arXiv:2610.27942v1 Announce Type: cross Abstract: Automated respiratory sound classification enables continuous, non-invasive respiratory assessment, yet long-term deployment remains challenging due to domain shifts from…
- arXiv cs.AIresearchRecast the Past: Stable Long Video Generation with Full Context Memory
arXiv:2610.27986v1 Announce Type: cross Abstract: Long-horizon video generation requires retaining an ever-expanding history, but conditioning on its growing token sequence is costly. Existing methods restrict or compres…
- arXiv cs.AIresearchLearning Tactile-Aware Hand Representations from Human Hand-Object Interaction Data
arXiv:2610.27995v1 Announce Type: cross Abstract: Tactile representation learning for dexterous manipulation often requires substantial robot-side data collection, limiting its scalability across different hands and sens…
- arXiv cs.AIresearchOn-Policy Transition Distillation
arXiv:2610.28048v1 Announce Type: cross Abstract: On-policy distillation (OPD) consolidates expert capabilities into a single student by matching teacher and student final-layer distributions on student-generated rollout…
- arXiv cs.AIresearchAssessing Representation Semantics Under Language Pretraining in Fine-Grained Classification
arXiv:2610.28051v1 Announce Type: cross Abstract: Understanding how supervision signals shape semantic visual representations remains challenging, particularly in fine-grained, low-data settings. Standard evaluations of…
- arXiv cs.AIresearchSlots Are Not Speakers: Training-Free Speaker Linking for Frozen Streaming Diarizers
arXiv:2610.28053v1 Announce Type: cross Abstract: This paper presents a causal, training-free linker that allows a frozen streaming diarizer to track more speakers than it has output slots. Streaming end-to-end diarizers…
- arXiv cs.AIresearchAuditing Where Concept Bottleneck Accuracy Comes From on CUB
arXiv:2610.28059v1 Announce Type: cross Abstract: Concept Bottleneck Models (CBMs) promise predictions that humans can inspect and correct through concepts such as "curved beak". Yet on CUB-200-2011, their standard bench…
- arXiv cs.AIresearchQuantifying the Threat: A Bayesian Probabilistic Framework for Heavy Metal Health Risks among Children in the Densu Basin, Ghana
arXiv:2610.28064v1 Announce Type: cross Abstract: Groundwater in Ghana's Densu River Basin remains a key domestic water source, but multi-metal contamination threatens children's health. Previous deterministic hazard ind…
- arXiv cs.AIresearchSame Judgment, Different Yes: Measuring Multilingual Judgment Profiles in Language Models
arXiv:2610.28066v1 Announce Type: cross Abstract: Multilingual evaluations often score a model's opening yes or no, a token that also carries model and language answering conventions. We ask when different ways of elicit…
- arXiv cs.AIresearchPULSE: Personalized Opportunistic Learning for Wearable Devices
arXiv:2610.28081v1 Announce Type: cross Abstract: Wearable devices increasingly support personalized health and well-being applications, but post-deployment data can differ substantially from those used for training, whi…
- arXiv cs.AIresearchMoDDiT: Simple Token Routing in Diffusion Transformers
arXiv:2610.28086v1 Announce Type: cross Abstract: Real-time video generation, interactive world models, and on-device image synthesis are almost a reality. Diffusion Transformers (DiT) achieve excellent sample quality, s…
- arXiv cs.AIresearchFrom Complex Histories to Simple Predictors: Predictive Dimension in Dynamic Graph Learning
arXiv:2610.28090v1 Announce Type: cross Abstract: Existing continuous-time graph learning methods rely heavily on complex neural architectures to encode ever-expanding interaction histories. However, the future condition…
- arXiv cs.AIresearchBAIT: Can LLMs Find What Biases a Reader? A Benchmark for Cognitive Bias Triggers in News
arXiv:2610.28092v1 Announce Type: cross Abstract: Persuasive writing exploits cognitive biases, recruiting a reader's mental shortcuts to shape belief, often without the reader noticing. We call the linguistic features e…
- arXiv cs.AIagentsClawMMU: Protection-Coherent Virtual Memory for Stateful LLM Agents
arXiv:2610.28093v2 Announce Type: replace-cross Abstract: AI agents keep long-term memory, much of which comes from web pages and tool results. Agent harnesses, the software that runs the model, do not record who may act…
- arXiv cs.AIresearchDe-Diffusing WAMs: Action-Sufficient Direct Prediction for Robot Control
arXiv:2610.28122v1 Announce Type: cross Abstract: Cascade world-action models (WAMs) use predicted visual futures to condition robot actions, but inherit costly iterative inference from diffusion-pretrained experts. We a…
- arXiv cs.AIresearchCausal Discovery for Linear Models with Latent Confounding via Multi-domain Identifiable Representation Learning
arXiv:2610.28134v1 Announce Type: cross Abstract: Causal discovery with latent confounding is particularly challenging, but a common setting in real-world data. In this work, we focus on linear causal models with latent…
- arXiv cs.AIagentsFrom Code Generator to Engineering Companion: A Plant-aware Agent for PLC Programming
arXiv:2610.28160v2 Announce Type: replace-cross Abstract: Programmable Logic Controller (PLC) coding remains a manual, IDE-centric task that demands constant context switching between documentation, project files, and co…
- arXiv cs.AIresearchAfrica-Papers: A 10-Billion-Token Multi-Domain Academic Corpus for African Foundation Language Models
arXiv:2610.28173v1 Announce Type: cross Abstract: Large Language Models (LLMs) depend fundamentally on the diversity, depth, and factual rigor of their pre-training corpora. However, contemporary foundational pre-trainin…
- arXiv cs.AIresearchTemporal Evidence-Parameter Co-Alignment for LLM Reasoning over Temporal Knowledge Graphs
arXiv:2610.28176v2 Announce Type: replace-cross Abstract: Large Language Models (LLMs) often struggle with temporally grounded reasoning because their static parametric memory is misaligned with the dynamic evolution of…
- arXiv cs.AIresearchPerceives but Doesn't Brake: A Perception-Action Binding Gap in Reasoning Driving VLAs
arXiv:2610.28184v1 Announce Type: cross Abstract: Reasoning-augmented vision-language-action (VLA) driving models can perceive and reason about safety-critical hazards yet fail to translate that evidence into safe action…
- arXiv cs.AIresearchOffline Makes Online Better: Calibrated Cache Compression for Video Generation
arXiv:2610.28192v1 Announce Type: cross Abstract: Token merging is an effective approach to reducing KV-cache memory consumption in autoregressive video generation by clustering temporally redundant tokens and retaining…
- arXiv cs.AIresearchAdaptive Pullback: Reweighting Supervision at Penalty Jumps in On-Policy Distillation
arXiv:2610.28194v1 Announce Type: cross Abstract: On-policy distillation (OPD) supervises student-generated responses using sampled-token student-teacher log-ratios. A positive log-ratio penalizes a token that the studen…
- arXiv cs.AIagentsReframing Object-Centric Reinforcement Learning: From Absolute to Relative Representations
arXiv:2610.28197v1 Announce Type: cross Abstract: Object-centric reinforcement learning agents typically receive each object's position in a fixed global frame, even though their decisions usually depend on where objects…
- arXiv cs.AIresearchParameter-Efficient Adaptation of Time Series Foundation Models for Electrical Load Forecasting
arXiv:2610.28200v2 Announce Type: replace-cross Abstract: Accurate electrical load forecasting supports power-system operation across countries, regions, cities, and buildings, but repeated development of target-specific…
- arXiv cs.AIresearchJAXbounce: A Continuous-Control Pong-Like Benchmark for Active Inference Beyond Low Dimensional Environments
arXiv:2610.28203v1 Announce Type: cross Abstract: We introduce JAXbounce, a continuous control pong-like benchmark designed to evaluate active inference beyond discrete, low dimensional environments. JAXbounce combines c…
- arXiv cs.AIresearchRegion-Guided Food-Package Evidence Extraction and Abstention-Aware Draft R3337 Screening with Selective VLM Review
arXiv:2610.28211v1 Announce Type: cross Abstract: Applying South Africa's draft R3337 warning criteria to food-package photographs requires nutrition, ingredient and product-form evidence. This study presents a region-gu…
- arXiv cs.AIresearchLocal Inference of LLMs on Long Contexts: A Data Systems Perspective
arXiv:2610.28223v1 Announce Type: cross Abstract: Large language models can solve complex problems across a variety of subjects, such as mathematics and coding. For such complex analytical tasks, models with a long conte…
- arXiv cs.AIresearchTPO: Tri-level Distributionally Robust Learning for OOD Direct Preference Optimization
arXiv:2610.28229v1 Announce Type: cross Abstract: Direct Preference Optimization (DPO) minimizes empirical risk over observed preference comparisons, implicitly assuming that the training preference distribution matches…
- arXiv cs.AIresearchPI-MLLM: Psychophysics-Inspired Multimodal Large Language Model for Oddly Satisfying Video Emotion Analysis
arXiv:2610.28264v1 Announce Type: cross Abstract: Oddly Satisfying Videos (OSVs) can evoke strong viewer responses through repetitive motion, visual tactility, and ASMR-like sounds despite containing few explicit semanti…
- arXiv cs.AIresearchVGL-stGen: Learning a shared multimodal model for lung histology and spatial transcriptomics
arXiv:2610.28266v1 Announce Type: cross Abstract: VGL-stGen is a multimodal large language model adapted from a pretrained medical vision-language model using paired lung H&E and spatial transcriptomics with single-cell…
- arXiv cs.AIresearchGALA: Geometry-Aware Language Model for Controllable Object Arrangement
arXiv:2610.28280v1 Announce Type: cross Abstract: Reasoning about fine-grained placement constraints, such as support and containment, is essential for realistic 3D scene creation. It remains a significant challenge for…
- arXiv cs.AIagentsLocal Work, Global Progress: A Convergence Theory of AI Agent Collaboration
arXiv:2610.28286v1 Announce Type: cross Abstract: Teams of large language model (LLM) agents are increasingly applied to complex tasks, but their collaboration protocols are mostly designed empirically, without convergen…
- arXiv cs.AIresearchABACUS: A Benchmark for Image Editing Models to Assess Object Category and Counting Under Scene Conservation
arXiv:2610.28316v1 Announce Type: cross Abstract: Instruction-based image editing models can now add, remove a specified number of objects or change their category while preserving the scene. Yet these models often fail…
- arXiv cs.AIresearchIdentifying Dependent Components from Multi-domain Linear Mixtures
arXiv:2610.28330v1 Announce Type: cross Abstract: We study a linear mixing model with dependent latent components, assuming multiple data domains. Most existing models assume that the components are independent or at lea…
- arXiv cs.AIresearchBeyond a Single Sentiment Score: Topical and Affective Dimensions of Emoji Meaning on Twitter
arXiv:2610.28337v1 Announce Type: cross Abstract: Emoji are widely treated as compact affective tokens whose meaning is summarised by a single sentiment score. We argue that this picture is incomplete. From a corpus of 1…
- arXiv cs.AIresearchGated Prototype Transfer for Zero-Support Medical Vision Language Model
arXiv:2610.28350v1 Announce Type: cross Abstract: Realistic few-shot adaptation of medical vision-language models (VLMs) can leave low-prevalence classes without any labeled support. The training-free SS- Text+ solver re…
- arXiv cs.AIresearchRayCo4D: Ray-Conditioned Continuous Motion Model for Monocular 4D Dynamic Reconstruction
arXiv:2610.28351v2 Announce Type: replace-cross Abstract: Reconstructing dynamic 3D scenes from monocular video requires inferring motion from noisy and intermittently visible observations. Long-range tracks provide valu…
- arXiv cs.AIresearchCountVideoBench: A Benchmark to Evaluate Prediction Biases on the Object Counting task by Video-Language Models
arXiv:2610.28356v3 Announce Type: replace-cross Abstract: Object counting in videos remains a poorly characterized capability of multimodal large language models. Counting questions are included in many existing VideoQA…
- arXiv cs.AIresearchContext-Aware Prompt Injection Detection via Small Language Models in RAG Pipelines: nokast-secureRAG
arXiv:2610.28364v1 Announce Type: cross Abstract: Local Retrieval-Augmented Generation (RAG) systems are vulnerable to indirect prompt injection and retrieval poisoning, where malicious instructions in retrieved content…