AI news archive.
10,660 articles filed under Research, newest first, from the outlets listed on the sources page.
- arXiv cs.AIresearchGeospatial Vector Geometry as a Native Spatial Modality for Vision-Language Models
arXiv:2610.16769v1 Announce Type: new Abstract: Geospatial reasoning links VLMs to real-world action and decision making. Reliable reasoning requires accurate spatial information and effective spatial representations. Ho…
- arXiv cs.AIresearchLIBERO-Industry: Benchmarking Robotic Manipulation under Industrial Process Constraints
arXiv:2610.16782v2 Announce Type: replace Abstract: Industrial manipulation in flexible manufacturing, e.g., high-mix, low-volume (HMLV) electronics assembly, requires robot policies to adapt to changing products and pro…
- arXiv cs.AIresearchCLIVO: Differentiable Cluster-Based Instruction Mixing with Learned Validation Objectives
arXiv:2610.16876v2 Announce Type: replace Abstract: Data selection turns large multimodal instruction pools into compact training subsets tailored to a vision-language model's target capabilities. Effective selection req…
- arXiv cs.AIresearchTransparency as Answerability: Role-Dependent Information Flow Modeling
arXiv:2610.16887v1 Announce Type: new Abstract: Transparency in AI-supported decision systems is widely required but poorly defined. Existing approaches treat transparency as a property of systems or components, producin…
- arXiv cs.AIresearchTransparent Information Flow Modeling for Role-Aware AI Act Assessment
arXiv:2610.16916v1 Announce Type: new Abstract: The European Union's Artificial Intelligence Act introduces a structured framework for governing high-risk AI systems, emphasizing transparency, risk management, and role-s…
- arXiv cs.AIresearchWeFair: Fidelity-Aware Alignment from Human Feedback for Personalized Query Rewriting in Short-Video Search
arXiv:2610.16927v2 Announce Type: replace Abstract: Short-video search needs compact query rewriters that recover users' personalized intent from ambiguous queries under strict latency constraints. Existing LLM-based met…
- arXiv cs.AIresearchUnderstanding Personalization Gains in Whisper ASR
arXiv:2610.17019v2 Announce Type: replace Abstract: Whisper-style ASR models provide strong zero-shot transcription, but their residual errors are not evenly distributed across datasets, recording conditions, and metadat…
- arXiv cs.AIresearchBenchmarking Quantum Kernel SVMs for Credit Card Fraud Detection: Performance Realities Under NISQ Constraints
arXiv:2610.17027v1 Announce Type: new Abstract: Detecting credit card fraud is notoriously difficult because fraudulent charges make up less than 0.2% of total transactions. Quantum Machine Learning (QML), particularly Q…
- arXiv cs.AIresearchVL-DocIR: A Benchmark for Vision-Based Long Document Information Retrieval
arXiv:2610.17057v1 Announce Type: new Abstract: Vision-based document retrieval has improved rapidly, but current evaluation settings still emphasize short documents and single relevant pages. This leaves an important ga…
- arXiv cs.AIresearchPatientWM: Towards Generalizable Clinical World Models via Unified Patient States
arXiv:2610.17059v1 Announce Type: new Abstract: Clinical decisions depend on anticipating how a patient's condition will evolve as treatment is adjusted and new evidence becomes available. Existing medical world models c…
- arXiv cs.AIresearchSFT Leaves a Reproducible Signature in Activation Geometry: Calibrating Post-Training Interpretability Against Run-to-Run Noise
arXiv:2610.17093v2 Announce Type: replace Abstract: A model diff credits post-training with whatever separates a base checkpoint from one post-trained descendant, presuming a rerun would land close by. On the sparse co-a…
- arXiv cs.AIresearchThe Format is the Filter: Scoring Format Fixes What an LLM Judge Can Express
arXiv:2610.17158v1 Announce Type: new Abstract: When an LLM judge filters instruction-tuning data, its scoring format (binary verdict, 1--5 rating, 0--100 score, or comparison) is rarely justified or ablated. Holding the…
- arXiv cs.AIresearchLearning Perceptual Geometry of Natural Odor Mixtures from LLM-Derived Descriptors
arXiv:2610.17164v1 Announce Type: new Abstract: The relationship between odor chemistry and perception remains incompletely understood. Many existing studies focus on the perception of single molecules, whereas natural o…
- arXiv cs.AIresearchChemExplain: A Multimodal Benchmark for Explanatory Chemical Reasoning
arXiv:2610.17183v1 Announce Type: new Abstract: Current chemistry benchmarks primarily evaluate outcome prediction or reaction pathway generation, but rarely test whether a model can explain why an observed chemical effe…
- arXiv cs.AIresearchSize Generalization for Diffusion Routing Solvers
arXiv:2610.17192v1 Announce Type: new Abstract: Routing problems, like the Traveling Salesman Problem (TSP) and the Capacitated Vehicle Routing Problem (CVRP), are NP-hard and slow to solve for large instances. Diffusion…
- arXiv cs.AIresearchReleasing the Inner Jev: A Simple Recipe for Open Decision Models
arXiv:2610.17205v1 Announce Type: new Abstract: LLM-based decision-making systems, also called System One models, have recently gained popularity, most notably through Jev (Almeida, 2026). Given a typed input state, a qu…
- arXiv cs.AIresearchIsoVRBench: Video Reward Modeling Without Human Feedback
arXiv:2610.17234v1 Announce Type: new Abstract: Video reward models are trained and evaluated on human preferences between videos that often differ simultaneously on properties such as prompt alignment, visual fidelity,…
- arXiv cs.AIresearchDoes a Governed Confidence Score Know When a Text-to-SQL Answer Is Right? An Exploratory Study on BIRD and a Pre-registered Confirmation on Spider
arXiv:2610.17256v2 Announce Type: replace Abstract: Conversational analytics lets people ask questions of records spread across many systems and get answers in plain language; it is useful only if each answer can be trus…
- arXiv cs.AIresearchRL Post-Training Diffusion Language Models Along Their Own Generation Paths
arXiv:2610.17266v1 Announce Type: new Abstract: Diffusion language models are a promising and more efficient alternative to autoregressive models. However, most RL post-training techniques are not easily adapted to these…
- arXiv cs.AIresearchReasoning for Propaganda Detection via Label-Guided CoT Optimisation
arXiv:2610.17271v1 Announce Type: new Abstract: Propaganda detection systems usually operate as black boxes, lacking explanations. To address this, we hypothesise that persuasive techniques contain definitional character…
- arXiv cs.AIresearchTowards Resilience: Slice-Driven Orchestration of Mobile IoMT in 6G-Edge-Continuum
arXiv:2610.17296v1 Announce Type: new Abstract: Emerging healthcare services, such as real-time diagnostics, remote health monitoring and computer-assisted surgery, require stringent Quality of Service (QoS) guarantees w…
- arXiv cs.AIresearchWhat Makes a Latent Space Shared? Direct and Recoverable Compatibility in Motion VAEs
arXiv:2610.17376v1 Announce Type: new Abstract: A shared latent space is often assumed to make representations from different schemas directly interchangeable, yet sharing parameters, dimensionality, or a prior does not…
- arXiv cs.AIresearchEPOCH: Coverage-Aware Evolution with Experiential Preference Optimization for LLM-based Automated Heuristic Design
arXiv:2610.17379v1 Announce Type: new Abstract: LLM-based automated heuristic design (AHD) discovers heuristics for combinatorial optimization problems (COPs), where an LLM generates candidates in an evolutionary search.…
- arXiv cs.AIresearchLearning to Play: Reinforcement Learning and Games
arXiv:2610.17391v1 Announce Type: new Abstract: Amazing breakthroughs in reinforcement learning have taken place. Computers teach themselves to play Chess and Go and beat world champions. There is talk about expanding ap…
- arXiv cs.AIresearchGeneralizable field of view extension for diffusion MRI via conditional flow matching
arXiv:2610.17401v1 Announce Type: new Abstract: Incomplete field-of-view (FOV) diffusion MRI (dMRI) acquisitions compromise whole-brain white matter analysis by excluding brain regions from tractography and connectivity…
- arXiv cs.AIresearchAn FPGA-Based Spiking Neural Network for Spatiotemporal Pattern Learning and Classification
arXiv:2610.17463v1 Announce Type: new Abstract: Spiking Neural Networks (SNNs) are promising for energy-efficient spatiotemporal pattern recognition at the edge, but efficient deployment and on-device adaptation require…
- arXiv cs.AIresearchREA: From Correct LLM Judgments to Safe Decision Delivery
arXiv:2610.17473v1 Announce Type: new Abstract: Generative safety guards must classify requests correctly and return outputs that applications can parse. Reasoning guards can improve classification accuracy while produci…
- arXiv cs.AIresearchTacitVLA: Reasoning Vision-Language-Action Models Without Reasoning Latency
arXiv:2610.17540v1 Announce Type: new Abstract: Textual reasoning before acting has improved vision-language-action (VLA) models, but at the cost of latency: every action conditioned on the reasoning text must wait for a…
- arXiv cs.AIresearchReference Wording Shapes Retrieval of Robot Task Instructions
arXiv:2610.17549v1 Announce Type: new Abstract: Identifying a robot task from a short instruction is sensitive to which descriptions are available for retrieval. We investigate this effect in the natural-language instruc…
- arXiv cs.AIresearchRAN-JEPA: An Action-Conditioned World Model for Energy-efficient Mobile Network Control
arXiv:2610.17584v1 Announce Type: new Abstract: Operational mobile networks are rich in observations but poor in interventions: they continuously generate large volumes of passive telemetry, while controlled action--resp…
- arXiv cs.AIresearchOpenDepth: Repurposing Image Editing Priors for Robust Open-World Monocular Depth Estimation
arXiv:2610.17610v2 Announce Type: replace Abstract: Recently, the integration of generative priors has revolutionized Monocular Depth Estimation (MDE), achieving state-of-the-art (SOTA) performance with remarkably high d…
- arXiv cs.AIresearchBeyond Bias Scores: Answerability Confounds in Activation Steering with Gradient-Constrained Direction Design (GCD)
arXiv:2610.17641v1 Announce Type: new Abstract: Bias scores in language-model evaluations often conflate what a model prefers with whether it answers at all. We identify this confound in \textsc{BBQ}, whose ambiguous sco…
- arXiv cs.AIresearchRoTA-Bench: Evaluating 3D Spatial Reasoning through Interactive Projection Alignment
arXiv:2610.17665v3 Announce Type: replace Abstract: Can vision-language models turn 2D observations into 3D understanding that supports precise action? This requires inferring object geometry, anticipating the effects of…
- arXiv cs.AIresearchEncounter-Driven City-Scale Human Mobility Generation with Large Language Models
arXiv:2610.17672v2 Announce Type: replace Abstract: Large language models (LLMs) have shown strong potential for human mobility generation by modeling individual routines, activities, and mobility preferences. However, e…
- arXiv cs.AIresearchStable Token-level Scheduling for Serverless LLM Inference
arXiv:2610.17689v1 Announce Type: new Abstract: Serverless inference is emerging as an efficient deployment model for Large Language Models (LLMs) due to its ability to elastically scale resources, improve GPU utilizatio…
- arXiv cs.AIresearchMedEvo: Medical Reasoning Evolution through Knowledge Navigation
arXiv:2610.17690v2 Announce Type: replace Abstract: Medical multimodal reasoning models are typically trained on teacher-generated rationales, discarding the valid reasoning in students' own failed trajectories, while ge…
- arXiv cs.AIresearchUnderstanding Gene Expression-to-Image Learning: Spatial Structure and Information Fidelity
arXiv:2610.17699v1 Announce Type: new Abstract: Single-cell RNA sequencing (scRNA-seq) enables cell-level analysis of biological heterogeneity, but learning effective representations from high-dimensional, unordered gene…
- arXiv cs.AIresearchA Node Embedding Framework for Model-Centric Conformance Checking in Process Mining
arXiv:2610.17702v1 Announce Type: new Abstract: Evaluating the quality of process models discovered from event logs is a fundamental challenge in process mining. Traditional evaluation relies on conformance metrics such…
- arXiv cs.AIresearchECG-RSI: Recursive Self-Improvement through Targeted Electrocardiogram Waveform Evolution
arXiv:2610.17718v2 Announce Type: replace Abstract: Electrocardiogram (ECG) models need supervision that targets evolving weaknesses and remains faithful to waveform evidence. We introduce ECG-RSI, a recursive self-impro…
- arXiv cs.AIresearchDuplexAct: How Interactive Are Frontier Full-Duplex Spoken Language Models?
arXiv:2610.17738v1 Announce Type: new Abstract: End-to-end (E2E) full-duplex spoken language models (FD-SLMs) enable simutanous listening and speaking continously, requiring models to take appropriate interaction actions…
- arXiv cs.AIresearchCoupled Harness--Model Evolution for Scientific Equation Discovery
arXiv:2610.17740v1 Announce Type: new Abstract: Large language models (LLMs) are increasingly used to discover scientific equations from experimental data. Such a discovery system has two parts that must work together: a…
- arXiv cs.AIresearchPaceReasoner: Label-Free Learning to Answer Briefly from Long Reasoning
arXiv:2610.17900v1 Announce Type: new Abstract: Extended chain-of-thought reasoning improves problem-solving performance but increases inference cost and latency, motivating more accurate answers with shorter reasoning.…
- arXiv cs.AIresearchSeeing Depth but Choosing Cues in Vision-Language Models
arXiv:2610.17976v1 Announce Type: new Abstract: Do vision-language models use depth information to judge which object is closer, or rely on image-plane cues? We investigate this question through controlled depth--cue con…
- arXiv cs.AIresearchSHELDON: Reasoning through Dual Search over Hypothesis and Observation Spaces
arXiv:2610.18025v1 Announce Type: new Abstract: Test-time scaling has enabled LLMs to solve increasingly complex reasoning, discovery, and optimization tasks. However, existing approaches often gather observations while…
- arXiv cs.AIresearchBeyond Black Boxes: Visual Grounding for Text Embeddings
arXiv:2610.18047v1 Announce Type: new Abstract: In this paper, our goal is to represent text embeddings as sketches for three main reasons. First, to visualize text representation and to explore their potential their pot…
- arXiv cs.AIresearchOne-Sided Verification Under Limited Expert Review
arXiv:2610.18089v2 Announce Type: replace Abstract: AI has become increasingly helpful in scientific discovery, yet human expert review remains essential for those problems without reliable automated evaluation, posing a…
- arXiv cs.AIresearchCompanionSafe: From Multi-turn Safety Evaluation to Guardrails for AI Companions
arXiv:2610.18095v1 Announce Type: new Abstract: AI companions provide users with emotional support and ongoing companionship, but their sustained relational interactions also introduce distinct safety risks. Prior work l…
- arXiv cs.AIresearchChain of Thought Monitoring Can Fail Even When CoT Is Necessary
arXiv:2610.18105v1 Announce Type: new Abstract: Chain of Thought (CoT) monitoring is used by frontier labs to detect misbehaviour of AI systems. Yet, its reliability remains poorly understood. We attribute this to the la…
- arXiv cs.AIresearchFresh at Decision, Stale at Action: Routing New Information to LLM Decisions Already Made
arXiv:2610.18126v1 Announce Type: new Abstract: Freshness shapes an LLM decision at the moment it is made; the action it commits to is latent, carried out later, in a changing world. We therefore introduce a timestamp th…
- arXiv cs.AIresearchMonitoring latent reasoning in looped language models
arXiv:2610.18127v1 Announce Type: new Abstract: Looped language models (LMs) reuse one block of layers several times per token generation, promising more latent computation at no additional storage cost. Despite their ri…