AI news archive.
10,660 articles filed under Research, newest first, from the outlets listed on the sources page.
- arXiv cs.AIresearchFrom Geometry to Behavior: How Instruction Exposure Unlocks Latent Rhetorical Directions in LLMs
arXiv:2610.37685v1 Announce Type: cross Abstract: Language models do not merely memorize facts; they absorb rhetorical strategies from pretraining data, including the human tendency to reason by analogy. We ask: is this…
- arXiv cs.AIresearchWhere Planning Changes the Outcome of Orbital Games
arXiv:2610.37686v1 Announce Type: cross Abstract: This paper introduces OrbitalGym, a simulation environment for studying when planning algorithms or system design determine the outcome of adversarial orbital encounters.…
- arXiv cs.AIresearchOne Confidence Threshold, Unequal Coverage: Language Gaps in Typed Decision Interfaces and How Translating Inputs Reduces Them
arXiv:2610.37688v1 Announce Type: cross Abstract: Deployed classifiers often act on a prediction only when its confidence clears a threshold and pass the rest to a person. We ask whether one threshold serves all language…
- arXiv cs.AIresearchGenAI as an 'Invisible Hand' in Opinion Dynamics: Evidence from a Group-Level Simulation Study
arXiv:2610.37689v1 Announce Type: cross Abstract: Recent arguments suggest that genAI can act as an invisible hand that gradually shapes social structures, such as collective beliefs and norms. The argument is that if mi…
- arXiv cs.AIresearchBouba Beats Kiki, and Other Regularities in the Subjective Preferences of LLMs
arXiv:2610.37692v1 Announce Type: cross Abstract: Users engage with large language models on tasks that are purely objective ("When was Netflix founded?"), purely subjective ("What should I name my child?") or anywhere i…
- arXiv cs.AIresearchDuQUAD: A Dual-View Framework with Quality-Aware Evidence Pruning for Multi-Document Question Answering
arXiv:2610.37701v1 Announce Type: cross Abstract: Large language models with retrieval-augmented generation systematically underutilize evidence in the middle of multi-document contexts, a phenomenon known as Lost in the…
- arXiv cs.AIresearchSearch-Guided Reasoning Trace Curation for Verilog Generation
arXiv:2610.37706v1 Announce Type: cross Abstract: Recent advances in large language models (LLMs) have improved Verilog generation. However, most training pipelines distill natural-language reasoning traces whose interme…
- arXiv cs.AIresearchFVH-Bench: Evaluating Image Generator Safety Beyond Overtly Harmful Imagery
arXiv:2610.37722v1 Announce Type: cross Abstract: Modern image generators can produce complex visual artifacts, including diagrams, interfaces, and records that combine text, graphics, and layout to convey detailed infor…
- arXiv cs.AIresearchPredicate Neuron: Differentiable Quantization of Predicate Relations in Gradient-based Learning
arXiv:2610.37727v1 Announce Type: cross Abstract: In machine learning, symbolic reasoning approaches often rely on static architectures that hinder integration into deep neural networks and gradient-based optimization. T…
- arXiv cs.AIresearchBeyond Similarity Search: Knowledge Graph Metadata Enrichment for Enterprise Retrieval-Augmented Generation
arXiv:2610.37728v1 Announce Type: cross Abstract: A key challenge of RAG systems is retrieving information from enterprise documents created by multiple teams over time, where it is not possible to enrich the information…
- arXiv cs.AIresearchSelective Transfer Learning for Groundwater Level Anomaly Forecasting: Accuracy-Risk Trade-offs
arXiv:2610.37733v1 Announce Type: cross Abstract: This work studies context-aware selective transfer learning for multi-well groundwater anomaly forecasting in the Netherlands. Source-domain pretraining can raise average…
- arXiv cs.AIresearchEUReCA: End-to-End Unified CBCT Reconstruction Across Clinical Acquisitions
arXiv:2610.37740v1 Announce Type: cross Abstract: Cone-beam computed tomography (CBCT) is widely used for image-guided radiotherapy, but reducing the number of projections to lower dose and scan time makes reconstruction…
- arXiv cs.AIresearchSpokes, not a Ring: Revisiting the Weekday Manifold in Language Models
arXiv:2610.37796v1 Announce Type: cross Abstract: Recent work has hypothesised that large language models may represent some concepts as multi-dimensional manifolds instead of single directions. Using these manifolds to…
- arXiv cs.AIresearchResponsible Quantum Machine Learning for Medical Imaging: A Fairness Audit Across Sensitive Subgroups
arXiv:2610.37819v1 Announce Type: cross Abstract: Quantum machine learning (QML) is increasingly explored for medical classification, yet its behaviour under subgroup-aware fairness criteria remains understudied. We pres…
- arXiv cs.AIresearchDeFT-RAG: Decomposing Multi-Hop Questions into Self-Contained Sub-Questions with Reusable Answers
arXiv:2610.37826v2 Announce Type: replace-cross Abstract: Retrieval-augmented generation (RAG) lets a large language model (LLM) answer questions by retrieving relevant passages from a large corpus. However, RAG struggle…
- arXiv cs.AIresearchLearning Lotteries with Minimal Stakeholder Violations from Membership Queries
arXiv:2610.37828v1 Announce Type: cross Abstract: An AI developer often has several candidate versions of a system and can deploy a mixture of them, sending each request to a randomly chosen version, as in A/B testing. E…
- arXiv cs.AIresearchWhere the Error Lives: Spectral Representations of Learned Kohn-Sham Hamiltonians
arXiv:2610.37843v1 Announce Type: cross Abstract: Kohn-Sham density functional theory (DFT) is the standard method for computing the electronic structure of molecules and materials, but its self-consistent-field (SCF) it…
- arXiv cs.AIresearchEcho: Scaling Visual Reinforcement Learning with Off-policy Experience
arXiv:2610.37865v1 Announce Type: cross Abstract: Scaling visual reinforcement learning (RL) with GPU-accelerated simulation is computationally expensive due to rendering and visual-policy inference costs. Consequently,…
- arXiv cs.AIresearchPairCLIP-SWA: Similarity-Guided Balancing and Stochastic Weight Averaging for Generalized Deepfake Image Detection with OpenCLIP
arXiv:2610.37874v1 Announce Type: cross Abstract: Deepfake detectors are almost always deployed as the single checkpoint that scored best on a validation split, yet the reliability of that choice is rarely measured. We m…
- arXiv cs.AIresearchWhen More Planning Hurts: Learned Planners for World Models
arXiv:2610.37891v1 Announce Type: cross Abstract: On PushT, our fixed action updater (1,505 parameters) solves 8 of 16 scenes reserved from our configuration selection. The comparison planners perform as follows: Selecte…
- arXiv cs.AIresearchThink Twice: The Metis-1.6 Technical Report
arXiv:2610.37903v1 Announce Type: cross Abstract: Metis is a bet that better data, better training methods and new architectures can buy what a bigger parameter count cannot, at a fraction of the cost. Metis-1.6 is its l…
- arXiv cs.AIresearchTERRA: Task-Oriented Edge AI for Regional Fire Detection with Identity-Free Reporting
arXiv:2610.37909v1 Announce Type: cross Abstract: Distributed fire-monitoring systems may involve many sensing devices reporting over a shared uplink, even though the operational objective is often to identify regions ex…
- arXiv cs.AIresearchWhat Actually Matters? A Paired Evaluation of Inference Settings for $\pi_{0.5}$ on BEHAVIOR-1K
arXiv:2610.37917v1 Announce Type: cross Abstract: Vision-Language-Action (VLA) models offer a promising paradigm for general-purpose household robotics. However, inference and data-collection strategies that have been de…
- arXiv cs.AIresearchNLP-based Message Prioritisation for Opportunistic Routing: A Case Study of Nepal Earthquake Emergency Communication
arXiv:2610.37933v1 Announce Type: cross Abstract: This dissertation investigates whether Natural Language Processing (NLP) based semantic message prioritisation can improve the treatment of urgent disaster messages in op…
- arXiv cs.AIresearchSAG-Sep: Sparse Augmented Graphs and Onion-Guided Search for Rounded Capacity Cut Separation
arXiv:2610.37952v1 Announce Type: cross Abstract: Rounded capacity cuts (RCCs) are among the most effective cuts for capacitated vehicle-routing relaxations, but exact separation is computationally prohibitive at scale.…
- arXiv cs.AIresearchStatistical Detection of Positional Bias in LLM-Based Recommender Systems: Methodologies and Empirical Evidence
arXiv:2610.37962v1 Announce Type: cross Abstract: Large Language Models (LLMs) are increasingly used as recommendation generators in conversational recommender systems (RS) via retrieval-augmented generation (RAG). This…
- arXiv cs.AIresearchSelf-Supervised Latent Action-Conditioned World Modeling for Time Series
arXiv:2610.37963v1 Announce Type: cross Abstract: Time-series data play an important role in various tasks, such as weather forecasting, web traffic analysis, and speech recognition. Recently, pioneering studies have inc…
- arXiv cs.AIresearchMerge and Branch: Efficient Tree-Structured Supervised Fine-Tuning of LLMs for Recommendation
arXiv:2610.37973v1 Announce Type: cross Abstract: LLM-based generative recommendation reads long, text-rich interaction histories but generates only short semantic identifiers (SIDs). This asymmetry makes supervised fine…
- arXiv cs.AIresearchTowards Generalizing Pretrained All-Atom Representations to Unified Binder Design
arXiv:2610.37994v1 Announce Type: cross Abstract: PairFormer-based all-atom models demonstrate strong capabilities in biomolecular binder design. However, existing methods often use all-atom representations for modality-…
- arXiv cs.AIresearchAre Seismic Foundation Models More Than Glorified Feature Extractors?
arXiv:2610.38003v1 Announce Type: cross Abstract: Earthquake sequences are stochastic on two separated timescales: the seismic waves of any individual earthquake propagate over seconds to minutes, while the earthquakes t…
- arXiv cs.AIresearch"It Would Make a Geordie Feel at Home": Regional Accent Perceptions and Speech Accommodation in Voice AI
arXiv:2610.38005v1 Announce Type: cross Abstract: Automatic speech recognition (ASR) systems often perform less accurately for speakers of regional dialects, but less is known about how users respond to these limitations…
- arXiv cs.AIresearchMaking Smart Homes Fit for Autistic Children: Family Work and Monitored Independence
arXiv:2610.38008v1 Announce Type: cross Abstract: General-purpose smart-home technologies are increasingly present in family life, yet how they support or disrupt autistic children and families with autistic children rem…
- arXiv cs.AIresearchMaking Sense of Audience Change: Causal Attribution and Boundary Management on Xiaohongshu
arXiv:2610.38026v2 Announce Type: replace-cross Abstract: Recommendation-driven platforms can reshape not only what users see, but also who becomes visible and how community boundaries are negotiated. We examine Xiaohong…
- arXiv cs.AIresearchMETATRON: A Promptable Whole-Body Execution Layer for Humanoids
arXiv:2610.38027v1 Announce Type: cross Abstract: Humanoid controllers often require task-specific training despite sharing the need for balance and whole-body coordination. We present Metatron, a promptable whole-body e…
- arXiv cs.AIresearchMeasuring Deep Learning Performance - An Empirical Study of Performance Distributions Across Architectures and Tasks
arXiv:2610.38037v1 Announce Type: cross Abstract: Context: Non-determinism in deep learning algorithm design and implementation leads to performance variation, meaning model performance is not a single value, but rather…
- arXiv cs.AIresearchEARS-Info: Information-Aware Event-Driven Reallocation for Multi-Robot Exploration
arXiv:2610.38040v1 Announce Type: cross Abstract: We introduce EARS-Info, an information-aware extension of Event-Driven Ant Reallocation Search for multi-robot exploration on OpenStreetMap-derived grids. It combines mar…
- arXiv cs.AIresearchCan Event Detectors Leave the Broadcast Camera? Evidence from Tennis
arXiv:2610.38042v1 Announce Type: cross Abstract: Ball bounces and racket hits are the events from which tennis statistics are derived, and on monocular video the two are easy to confuse. We release a benchmark of 345 bo…
- arXiv cs.AIresearchFrom Error Prediction to Causal Influence: Auditing SAE Features in Multiple-Choice QA
arXiv:2610.38067v1 Announce Type: cross Abstract: Sparse autoencoders (SAEs) can predict internal features associated with model errors, but association alone does not establish causal influence. We study this distinctio…
- arXiv cs.AIresearchPrompt Lottery in LLM-as-a-Judge: Measuring and Mitigating Sensitivity to Syntactic Rephrasing
arXiv:2610.38076v1 Announce Type: cross Abstract: LLM-as-a-Judge has become a standard for evaluating large language models, yet most approaches implicitly assume that a single judge prompt functions as a stable evaluati…
- arXiv cs.AIresearchInterpretable Feature Discovery from Unstructured Data Using LLMs and Statistical Choice Models
arXiv:2610.38082v1 Announce Type: cross Abstract: Feature extraction from unstructured data typically relies on opaque embeddings unsuited to interpretable decision-making. Interpretable features, on the other hand, typi…
- arXiv cs.AIresearchWhat Can Firms Do in the Face of Model Distillation?
arXiv:2610.38088v1 Announce Type: cross Abstract: Model distillation has become a major concern in the rapidly growing generative AI discourse. In its simplest form, distillation is the phenomenon where smaller firms can…
- arXiv cs.AIresearchPredicting What Answer Engines Cite: Open Decision Models, Rerankers and a Distilled 4B Student on Ten Engines under Controlled Retrieval
arXiv:2610.38090v1 Announce Type: cross Abstract: Generative engine optimization needs a scorer that ranks candidate pages by the share of an answer they will receive as citations. We measure pretrained rerankers, a host…
- arXiv cs.AIresearchJailbreak Connectivity: Towards Diverse, Transferable, and Universal Multimodal Large Language Model Jailbreak
arXiv:2610.38091v1 Announce Type: cross Abstract: Multimodal large language models (MLLMs) are vulnerable to visual jailbreak attacks that bypass safety safeguards. Existing methods typically optimize isolated adversaria…
- arXiv cs.AIresearchCalculation and rejection diverge in language models tested at known mechanical limits
arXiv:2610.38096v1 Announce Type: cross Abstract: When a language model returns engineering quantities with the status "solved", software that trusts it passes them on, even when the requested design is physically imposs…
- arXiv cs.AIresearchThe Prestige: Benchmarking Cognitive Visual Reasoning using Magic Tricks
arXiv:2610.38103v1 Announce Type: cross Abstract: We introduce The Prestige, a video understanding benchmark that probes cognitive visual reasoning through professional magic performances, where deliberate misdirection c…
- arXiv cs.AIresearchFrom the Gettier Machine to Justified True Output: A Three-Step Account of Rational Trust in Generative AI
arXiv:2610.38112v1 Announce Type: cross Abstract: As generative artificial intelligence (AI) settles into everyday practices of inquiry, an old epistemological question returns in a new guise: when does a proposition a u…
- arXiv cs.AIresearchBeauty Is Human: When People Love AI-Generated Art, They Think a Human Made It
arXiv:2610.38113v1 Announce Type: cross Abstract: Generative AI now produces images and poems that people cannot reliably distinguish from human-made work, so people often judge for themselves who made a work. We examine…
- arXiv cs.AIresearchEstimating Implicit Expected Log Density Ratios
arXiv:2610.38151v1 Announce Type: cross Abstract: When exact probabilities cannot be computed, \emph{density ratio estimation (DRE)} is a key subroutine in the wide range of applications where density ratios appear, from…
- arXiv cs.AIresearchConvex-SKM-Net: Low-Latency Block Halfspace Corrections for Neural Convex Constraint Satisfaction
arXiv:2610.38197v1 Announce Type: cross Abstract: Fast inference and strict constraint satisfaction are essential for learning-based decision-making. Existing methods often rely on constraint-specific projections or feas…
- arXiv cs.AIresearchCuraEval: Evaluating Demonstration Curation on Mixed-Skill Robot Data
arXiv:2610.38221v1 Announce Type: cross Abstract: Robot imitation learning uses demonstrations from operators of varying skill, but selecting training data remains challenging. Existing methods score demonstrations using…