AI news archive.
19,861 articles, newest first, from the outlets listed on the sources page.
- arXiv cs.AIresearchGRASP: Group-Adaptive Hybrid RL-SFT Post-Training for Medical VQA without Reasoning Annotations
arXiv:2610.34561v1 Announce Type: cross Abstract: Adapting general-purpose vision-language models (VLMs) to medical visual question answering (VQA) is valuable for helping clinicians read images and make diagnoses, but a…
- arXiv cs.AIresearchRecursive CLIP: Vision-Language Distillation with Looped Transformer Blocks
arXiv:2610.34563v1 Announce Type: cross Abstract: Contrastive vision-language models such as CLIP typically rely on independently parameterized transformer blocks across depth. We investigate the extent to which these bl…
- arXiv cs.AIresearchLarge Language Models: A Plain-Language Overview for Engineers
arXiv:2610.34585v1 Announce Type: cross Abstract: Large language models (LLMs) are neural networks trained on huge text collections to generate text by predicting what comes next. Engineers using ChatGPT and other genera…
- arXiv cs.AIresearchHARP-LoRA: Hierarchy-Conditioned Rank Projection for Low-Rank Adaptation in Scientific Table Understanding
arXiv:2610.34589v1 Announce Type: cross Abstract: Tabular data is widely used in scientific applications, where complex layouts, including multi-level headers, merged cells, captions, and footnotes, make information extr…
- arXiv cs.AIresearchAudio-R1: Audio Reasoning through Reinforcement Learning on Self-Supervised Tasks
arXiv:2610.34609v1 Announce Type: cross Abstract: Reasoning is increasingly important for large audio-language models (LALMs), yet remains relatively underexplored compared with text-only and vision-language models. We i…
- arXiv cs.AIresearchEntity Matching using Decision Models
arXiv:2610.34626v1 Announce Type: cross Abstract: Entity matching is the task of deciding whether two records describe the same real-world entity. Current entity matching methods rely on pre-trained language models (PLMs…
- arXiv cs.AIresearchRIDE-Splat: Reflection Removal for In-the-Wild Driving Environments
arXiv:2610.34632v1 Announce Type: cross Abstract: Driving video captured through a windshield violates the world-space consistency assumed by 3D Gaussian Splatting (3DGS): the road scene exhibits parallax while cabin ref…
- arXiv cs.AIagentsCodeMeepo: A Multi-Agent Workflow for Repository-Level Code Migration and Optimization
arXiv:2610.34633v1 Announce Type: cross Abstract: Repository-level code migration rewrites an entire project in a new programming language while preserving its observable behavior. It is challenging because behavior span…
- arXiv cs.AIagentsAgentProofBench: Benchmarking Reusable Verifiers for Web Agents
arXiv:2610.34634v1 Announce Type: cross Abstract: Reusable Web-agent verification requires a rule to follow changing requirements and support subsequent execution. We introduce AgentProofBench, which connects paired test…
- arXiv cs.AIagentsIntrinsic Goals for Autonomous Agents: Hierarchical Exploration Captures Future Volitional Action in Drosophila
arXiv:2610.34638v1 Announce Type: cross Abstract: Animals have a remarkable capacity for autonomy---driven by intrinsic motivation---without external sensory cues or extrinsic objectives, yet the computational mechanisms…
- arXiv cs.AIagentsRobotAgentBench: Towards Open-world Robot Autonomy
arXiv:2610.34649v1 Announce Type: cross Abstract: Recent advances in vision-language-action (VLA) and world-action models (WAMs) have significantly improved robotic manipulation, yet deploying robots in the open world de…
- arXiv cs.AIagentsThinking-in-Bets at Test Time Reduces Sycophantic Revisions in LLM Agents
arXiv:2610.34654v1 Announce Type: cross Abstract: Language model agents often abandon correct work when a user challenges it, yet simply telling them to stand firm makes them ignore real mistakes. Once an agent reads a c…
- arXiv cs.AIresearchVideo World Models Need Predictable Latents
arXiv:2610.34663v1 Announce Type: cross Abstract: Video world models trained on large-scale robot data promise a safe and scalable approach for learning and evaluating policies that act in the physical world. However, th…
- arXiv cs.AIagentsAgent Memory as Recommendation: Recommender-System Design for Long-Term Memory of LLM Agents
arXiv:2610.34673v1 Announce Type: cross Abstract: Large language model (LLM) agents that serve users across many sessions must choose, for every request, the few stored memories that enter a limited context window. This…
- arXiv cs.AIresearchBenchmarking Obstacle-Conditioned Safety in Household Robot Navigation
arXiv:2610.34674v1 Announce Type: cross Abstract: Safe household navigation requires robots to regulate clearance and speed according to what an obstacle is and how close it is, without unnecessary conservatism. Yet exis…
- arXiv cs.AIresearchKnowing When the Evidence Is Enough: Requirement-Directed Search with Horn-Closure Certificates
arXiv:2610.34684v1 Announce Type: cross Abstract: After each Web search, a search-augmented model must decide whether its evidence suffices: answer, search again, or abstain. Prevailing systems leave this to holistic mod…
- arXiv cs.AIresearchFrom Speech Tokens to Stolen Voices: Attacker-Chosen-Text Speaker Impersonation via Representation Inversion
arXiv:2610.34688v1 Announce Type: cross Abstract: Speech interaction systems have gradually evolved from traditional cascaded systems that use text as intermediate information to end-to-end speech language models that di…
- arXiv cs.AIresearchGangqinpu: A Multi-Genre, Multi-Task Piano Dataset with Aligned Audio, MIDI, and Musical Scores
arXiv:2610.34694v1 Announce Type: cross Abstract: Aligned audio, performance MIDI, and musical scores provide valuable supervision for music analysis and performance modeling, yet datasets that jointly align all three mo…
- arXiv cs.AIresearchVLA-HWBench: Where the Time Goes When VLA Models Run on Edge Hardware
arXiv:2610.34717v2 Announce Type: replace-cross Abstract: Vision-language-action (VLA) models increasingly run on edge devices aboard robots, where inference latency constrains closed-loop robot control. However, it rema…
- arXiv cs.AIagentsSceneAgent: An Agentic Pipeline from 3D and 4D Captures to Simulation Environments
arXiv:2610.34745v1 Announce Type: cross Abstract: Visual captures provide detailed scene appearance, but converting them into interactive simulation environments requires object reconstruction, physical modeling, and cor…
- arXiv cs.AIagentsBabysitting AI Agents: A User-Centered Taxonomy and Study of Agentic Delegation Failures
arXiv:2610.34748v1 Announce Type: cross Abstract: Users are increasingly delegating tasks to AI agents, allowing agents to perform long-running, multi-step workflows on their behalf. However, agents may perform these tas…
- arXiv cs.AIagentsThe Physical Cost of Context: Quality-Constrained Resource Accounting for Coding Agents
arXiv:2610.34763v1 Announce Type: cross Abstract: Coding agents resend a growing context on every model call, and context policies are usually judged by the prompt tokens they save. Executed work also depends on call cou…
- arXiv cs.AIresearchDynEdit: Dynamic Entropy-Guided Sequential Editing for Large Language Models
arXiv:2610.34768v1 Announce Type: cross Abstract: Knowledge editing aims to update outdated or incorrect knowledge in large language models without full retraining. Existing parameter-editing methods remain limited for l…
- arXiv cs.AIresearchThe Impact of Personalized AI Response Suggestions on Content Creators' Direct Messaging
arXiv:2610.34770v1 Announce Type: cross Abstract: Direct messaging is often employed by social media content creators to directly interact with followers. Those creators attempt to engage with followers in private commun…
- arXiv cs.AIresearchToDoPro: Faster and Better Reference-Based Generation: Early Token Reduction via Downsampled Self-Probing
arXiv:2610.34782v1 Announce Type: cross Abstract: Recent generic reference-based image generation models natively support multiple conditions by concatenating all reference image and text tokens into a joint sequence pro…
- arXiv cs.AIresearchPrecedence-Aware Resource Allocation: Extending the AUTOC Framework to Multi-Level Treatments
arXiv:2610.34812v1 Announce Type: cross Abstract: Many real-world decision problems require allocating limited resources across individuals to maximize total benefit often through interventions that vary in intensity rat…
- arXiv cs.AIagentsSilent and Costly: Characterizing and Detecting Prompt-Caching Mis-Integration in LLM Agents
arXiv:2610.34817v2 Announce Type: replace-cross Abstract: Large language model (LLM) services process massive volumes of user requests, resulting in substantial inference costs. To reduce both cost and latency, providers…
- arXiv cs.AIresearchSPARTA: A Sparse Ternary LLM Accelerator with Adaptive Attention and Unified Datapath for Long-Context Edge Inference
arXiv:2610.34824v1 Announce Type: cross Abstract: LLMs on edge devices are constrained by limited memory and bandwidth. Although 1.58-bit ternary weights greatly reduce model storage, long-context inference is increasing…
- arXiv cs.AIresearchStreaming Recurrent Memory
arXiv:2610.34833v1 Announce Type: cross Abstract: Natural intelligence learns from a continuous stream of sensorimotor experience: data can arrive at high bandwidth, and behavior adapts to feedback as soon as it arrives,…
- arXiv cs.AIresearchRecovering Black-Box Point Cloud Models from Pose Shifts via Derivative-Free Optimization
arXiv:2610.34850v1 Announce Type: cross Abstract: Point cloud models are increasingly deployed through score-only black-box interfaces. Under this access model, test-time rotations outside the training distribution can s…
- arXiv cs.AIagentsAdaptive Retrieval, Selective Answers: Evaluating Conformal Factuality in Agentic RAG
arXiv:2610.34872v1 Announce Type: cross Abstract: Retrieval-augmented generation (RAG) can improve factual grounding without guaranteeing that every generated claim is supported. Previous work has studied claim-level con…
- arXiv cs.AIresearchCoDeRNet: Selective Cross-Task Routing under Heterogeneous Supervision for Change Detection and Captioning
arXiv:2610.34876v1 Announce Type: cross Abstract: Change Detection & Captioning (CDC) aims to jointly localize changed regions and describe their semantic content from bi-temporal remote sensing images. While recent appr…
- arXiv cs.AIagentsNumTrace: Auditing the Number Provenance of Financial Analyst Agents
arXiv:2610.34887v1 Announce Type: cross Abstract: A numerical claim generated by a financial analyst agent can match a number in a company filing but refer to the wrong entity, concept, period, unit or scope. A check bas…
- arXiv cs.AIagentsAIPC: Evidence-Guided Agent Workflows for PyTorch Project Deployment
arXiv:2610.34890v1 Announce Type: cross Abstract: Deploying and optimizing a PyTorch inference project on a dedicated accelerator, especially an on-device NPU, requires more than using a framework device API as with CUDA…
- arXiv cs.AIresearchLE-GDA: Layer Ensemble Gaussian Discriminant Analysis for Training-Free Few-Shot CLIP Adaptation
arXiv:2610.34901v1 Announce Type: cross Abstract: Training-free few-shot adaptation of vision-language models typically constructs a classifier from CLIP's final projected image representation, leaving intermediate repre…
- arXiv cs.AIresearchWaypoint: Analytically Modeling GEMM for CPUs
arXiv:2610.34914v2 Announce Type: replace-cross Abstract: High-performance General Matrix Multiplication (GEMM) implementations rely on breaking down GEMM into carefully selected tiles to achieve peak performance. We pre…
- arXiv cs.AIagentsHow Do Coding-Agent Harnesses Self-Evolve? An Empirical Study of Retrospective Adaptation
arXiv:2610.34938v1 Announce Type: cross Abstract: Coding agents can adapt their harnesses, the software, configuration, and instructions used to run them, based on experience from earlier tasks, but whether these adaptat…
- arXiv cs.AIresearchReasoning Patterns for Efficient AI Coding: An Empirical Study
arXiv:2610.34943v1 Announce Type: cross Abstract: Large Reasoning Models (LRMs) generate long reasoning traces that expose intermediate inference behavior, offering opportunities to study and control reasoning in AI codi…
- arXiv cs.AIresearchRelational Composition as Parallel Transport: What Per-Entity Frames Force in Attention
arXiv:2610.34945v1 Announce Type: cross Abstract: A dot product means something only when both vectors share a coordinate system. Content words have one; a fresh entity does not: rotating its coordinates alone changes no…
- arXiv cs.AIresearchCorrelation-Aware Exploration for Long-Trace Reasoning
arXiv:2610.34949v1 Announce Type: cross Abstract: Reasoning models trained with Group Relative Policy Optimization (GRPO) now produce chains of thought thousands of tokens long, and recent studies reveal that such traini…
- arXiv cs.AIagentsGUIFlow: Temporal Redundancy-Aware Incremental Inference for GUI Agents
arXiv:2610.34959v1 Announce Type: cross Abstract: GUI agents built on vision-language models interact with continuously evolving interfaces, yet conventional inference repeatedly recomputes representations of largely ove…
- arXiv cs.AIagentsThe Target Agent Is Its Own Best Critic but a Poor Proposer: Self-Improved Red Teaming
arXiv:2610.34965v1 Announce Type: cross Abstract: Automatic red teaming increasingly relies on large language models (LLMs) to iteratively diagnose failed attacks and propose improved adversarial prompts or injections. A…
- arXiv cs.AIresearchSVD-Attention: Efficiently Analyzing Attention Blocks in Transformers
arXiv:2610.34971v1 Announce Type: cross Abstract: Pretrained transformers spend a large share of their inference compute inside self-attention, yet the per-head query-key interaction is structurally low-rank by construct…
- arXiv cs.AIresearchSparse Recovery Bird's-Eye View Model Soup for Robust Camera-Based 3D Object Detection
arXiv:2610.34976v1 Announce Type: cross Abstract: Camera-based bird's-eye view (BEV) perception methods such as Fast-BEV have demonstrated promising results with fast inference speed and competitive accuracy. However, th…
- arXiv cs.AIagentsAskGLP1: A Knowledge Graph LLM Agent for Exploring GLP-1 Experience from Online Patient Narratives
arXiv:2610.34987v1 Announce Type: cross Abstract: GLP-1 medications are increasingly used for weight management, and many people share their experiences online. These narratives show why people take the drugs and what th…
- arXiv cs.AIresearchFrom Single Spins to Ensembles: A Calibrated Symbolic Regression Pipeline for NV Spectroscopy
arXiv:2610.35016v1 Announce Type: cross Abstract: Characterizing nitrogen-vacancy (NV) ensembles requires connecting their collective spectra to individual centers that experience different local environments. We develop…
- arXiv cs.AIresearchAutoPRL: Automated Path Representation Learning via a Learnable View Generator
arXiv:2610.35032v1 Announce Type: cross Abstract: Self-supervised learning has emerged as a powerful paradigm for Path Representation Learning (PRL) in road networks. PRL aims to learn informative representations of path…
- arXiv cs.AIresearchCA-HNM: Constraint-Aware Hard Negative Mining for Dense Retrieval with Structured Domain Models
arXiv:2610.35045v1 Announce Type: cross Abstract: Dense retrievers are commonly trained with hard negatives selected from lexical or dense retrieval results. Retrieval proximity, however, does not indicate whether a cand…
- arXiv cs.AIresearchJoint Dynamic Lane Reversal and Variable Speed Limit Control: A Graphormer-Based Approach
arXiv:2610.35070v1 Announce Type: cross Abstract: Connected and automated vehicles could allow reassigning lane directions and speed limits on every road frequently, but the benefit hinges on how traffic reroutes, and on…
- arXiv cs.AIagentsCoSA: The Conflict of Skills Attack in Real-World LLM Agent Ecosystems
arXiv:2610.35082v1 Announce Type: cross Abstract: Agent Skills allow LLM agents to combine reusable capabilities, but checking each Skill in isolation cannot rule out policy violations when they are composed. We term suc…