AI news archive.
19,861 articles, newest first, from the outlets listed on the sources page.
- arXiv cs.AIresearchU-Space: Uncovering When and Why Uncertainty Arises in Language Models
arXiv:2610.09087v1 Announce Type: cross Abstract: Large language models are informing decisions with ever-higher stakes. As the consequences of their errors grow, a central question becomes harder to ignore: how much can…
- arXiv cs.AIresearchMaRK: Markov-adapted Recurrent Kernels for Dynamic Operator Conditioning in State Space Models
arXiv:2610.09092v3 Announce Type: replace-cross Abstract: State Space Models (SSMs) offer an efficient alternative to Transformers for sequence modeling, yet conditioning pre-trained SSMs for iterative generation typical…
- arXiv cs.AIresearchConvex-Concave Reinforcement Learning
arXiv:2610.09108v1 Announce Type: cross Abstract: Policy learning drives many of the most consequential and heavily-invested applications of reinforcement learning today. Yet the core optimization problem it rests on (ma…
- arXiv cs.AIresearchSpatial Induction Heads: In-Context Learning of Multidimensional Cellular Automata
arXiv:2610.09124v1 Announce Type: cross Abstract: Induction heads provide a mechanistic account of in-context learning in sequential data, but existing theory largely assumes that the context relevant to a prediction for…
- arXiv cs.AIagentsSwarmReconGuard: Black-Box Detection of Distributed Collective Reconnaissance by Individually Benign-Looking Agent Populations
arXiv:2610.09138v1 Announce Type: cross Abstract: Autonomous and agentic clients can distribute reconnaissance across many identities so that each request remains valid, low-rate, and benign-looking while the population…
- arXiv cs.AIresearchsk-bench: A Native-First Benchmark for Evaluating Large Language Models in Slovak
arXiv:2610.09152v1 Announce Type: cross Abstract: Multilingual LLM benchmarks omit Slovak, a morphologically rich West Slavic language of five million speakers, or cover it only by machine translation. We present sk-benc…
- arXiv cs.AIagentsToolRACER: A Robust Agentic Conversation Emulation Resource for Agent Training and Evaluation
arXiv:2610.09163v2 Announce Type: replace-cross Abstract: Task-oriented conversational agents remain fragile under real world conversation scenarios as they rarely follow a predictable script, especially when users exhib…
- arXiv cs.AIresearchLower Bounds for Parallel Diffusion Sampling
arXiv:2610.09166v1 Announce Type: cross Abstract: Standard diffusion samplers generate samples through repeated evaluations of a learned score function. Parallel sampling methods seek to accelerate generation by trading…
- arXiv cs.AIresearchLayerRoPE: Dynamic Depth-wise Magnitude & Angular Superposition
arXiv:2610.09179v1 Announce Type: cross Abstract: As data propagates through a Transformer, the norm of its hidden states grows by orders of magnitude with depth, a phenomenon framed as 'curse of depth' and nearly univer…
- arXiv cs.AIresearchPatient, Place, Prior (P$^3$): What Counts as Personalization in Medical World Models?
arXiv:2610.09194v1 Announce Type: cross Abstract: Longitudinal models forecast how a patient's imaging state evolves, but accuracy does not show whether the patient's observed trajectory drives the prediction. A populati…
- arXiv cs.AIresearchDo Vision Models Learn Physical Constraints or Rendering Shortcuts? A Counterfactual Benchmark for Grounded Physical Consistency
arXiv:2610.09205v1 Announce Type: cross Abstract: Modern image editing models can satisfy a text instruction while breaking the physics of the edited scene. A new object may cast no shadow, a mirror may fail to reflect v…
- arXiv cs.AIresearchMulti-Objective Aligned Small Language Model Framework for SUD Patient Dialogue Generation
arXiv:2610.09209v1 Announce Type: cross Abstract: Substance Use Disorder (SUD) counseling requires patient responses that reflect underlying cognitive states such as beliefs, coping strategies, and readiness for change.…
- arXiv cs.AIresearchCurveTQ: Rotation-Free Trellis Quantization of LLM Weights via Curvature-Weighted Search
arXiv:2610.09212v1 Announce Type: cross Abstract: The best two-bit weight quantizers for large language models, such as QTIP and Proteus, rotate each weight matrix by a random orthogonal transform, which must be undone a…
- arXiv cs.AIresearchA Deterministic Evidence Layer for Vision-Language Autism Screening from Naturalistic Home Video
arXiv:2610.09217v1 Announce Type: cross Abstract: Autism spectrum disorder (ASD) is diagnosed through specialist observation of a child's social behavior, and access to that expertise is the bottleneck for early identifi…
- arXiv cs.AIresearchConsistent Distribution Matching for Data-Free Diffusion Distillation
arXiv:2610.09221v1 Announce Type: cross Abstract: Flow and diffusion models suffer from slow inference due to computationally expensive numerical integration. Distillation provides a promising way for a student model to…
- arXiv cs.AIresearchConditional Accuracy Profiles: Diagnosing LLM Judges across Deployment Conditions
arXiv:2610.09229v1 Announce Type: cross Abstract: LLM-as-judge is now a standard tool for scalable evaluation, but judge performance is still often summarized by a single accuracy number. This aggregate view hides the de…
- arXiv cs.AIagentsAdversarial Images Hijack Web Agents from Visual Grounding to Browser Execution
arXiv:2610.09240v1 Announce Type: cross Abstract: Modern web agents built on large vision-language models process webpages, select relevant UI elements, and translate model outputs into browser actions. Existing visual r…
- arXiv cs.AIresearchAn Informational Curse of Horizon in Goal-Conditioned Policy Learning
arXiv:2610.09247v1 Announce Type: cross Abstract: The difficulty of learning goal-reaching policies is often attributed to a "curse of horizon" that manifests as bias accumulation in temporal-difference backups and noisy…
- arXiv cs.AIresearchEfficient Best-of-N policy evaluation for inference-time alignment
arXiv:2610.09250v1 Announce Type: cross Abstract: Best-of-N (BoN) is a common inference-time alignment method that selects the highest-scoring response among N samples from a reference model. Evaluating BoN policies from…
- arXiv cs.AIagentsPackage Hallucination Attacks on Coding Agents through Prompt Injection in Rule Files
arXiv:2610.09264v1 Announce Type: cross Abstract: Modern agentic coding frameworks increasingly rely on community-shared rule files (e.g., AGENTS.md or .cursorrules) to guide autonomous code generation, yet the security…
- arXiv cs.AIresearchEvaluating Trajectory Features for Routing Final-Layer Attention
arXiv:2610.09272v1 Announce Type: cross Abstract: Attention routing requires a signal that predicts the value of attention on the current prefix. We evaluate whether hidden-state extrapolation error, curvature and error…
- arXiv cs.AIagentsLeCuration: A Tiny World Model as a Data Curation Multi-Tool
arXiv:2610.09285v1 Announce Type: cross Abstract: Many applications of physical AI run within finite or closed physical worlds with a limited set of physical laws governing object behavior. Examples include robots workin…
- arXiv cs.AIresearchNode-level Graph Neural Architecture Search Framework
arXiv:2610.09297v1 Announce Type: cross Abstract: In recent years, Graph Neural Networks (GNNs) and architecture search frameworks have gained extensive application in non-Euclidean data processing, attributable to their…
- arXiv cs.AIresearchKuration SDK: Addressing the Virtual2Real Gap via Data Curation
arXiv:2610.09305v1 Announce Type: cross Abstract: Benchmarks for measuring the quality of action-conditioned world models are still evolving and shifting away from visual similarity-based metrics to action-semantic and p…
- arXiv cs.AIresearchDenoising Blocks, Not Tokens: Efficient Compressed Continuous Diffusion with Branching Token Realization
arXiv:2610.09311v1 Announce Type: cross Abstract: Diffusion language models (DLMs) generate text through iterative parallel refinement, offering the potential for higher throughput than autoregressive (AR) decoding. Howe…
- arXiv cs.AIresearchConstrained Diffusion for Data-Scarce Orbital Monte Carlo in Constellation Tasking
arXiv:2610.09323v1 Announce Type: cross Abstract: Constellation Monte Carlo results depend on the orbital population used to evaluate a tasking policy. With scarce reference trajectories, replay limits geometric diversit…
- arXiv cs.AIresearchVisual Jev Rewards: Reference-Bound Verification for Multi-Subject Image Generation
arXiv:2610.09328v1 Announce Type: cross Abstract: Multi-subject image generation requires rewards that verify whether requested attributes, actions, and relations hold for the specified reference subjects. Subject presen…
- arXiv cs.AIresearchShared Low-rank Basis Factorization for Data-free Mixture-of-Experts Compression
arXiv:2610.09342v1 Announce Type: cross Abstract: Mixture-of-Experts (MoE) large language models decouple capacity from compute through sparse routing, but their large parameter count creates storage and serving challeng…
- arXiv cs.AIresearchOnlineQAT: On-Policy Distillation for Ultra-Low-Bit Large Language Models
arXiv:2610.09346v1 Announce Type: cross Abstract: Quantization-aware training (QAT) can recover much of the accuracy lost when large language models are compressed below four bits. Existing re- covery stages, however, ar…
- arXiv cs.AIresearchMultimodal LLMs Can Learn to Read Brain Signals: A Vision--Language Model for Unified Multi-Task EEG Decoding
arXiv:2610.09355v1 Announce Type: cross Abstract: Learning EEG representations that generalize across cognitive tasks, subjects, and recording conditions remains a key challenge in electroencephalography (EEG) decoding.…
- arXiv cs.AIresearchFrom Chunks to Functional Evidence: Function-Aware Retrieval for EDA Documentation QA
arXiv:2610.09361v1 Announce Type: cross Abstract: Retrieval-Augmented Generation (RAG) is widely used to ground answers in documents. For complex technical documentation, however, the primary bottleneck is often not mode…
- arXiv cs.AIagentsThe Confidence Game: Strategic Miscalibration in Human-AI Delegation
arXiv:2610.09371v1 Announce Type: cross Abstract: Calibrated uncertainty quantification is essential to ensuring AI agents are trustworthy and reliable. However, when agents seek to maximize user engagement or revenue, c…
- arXiv cs.AIresearchTutorLoop: Regulating Student Learning Behaviors via Sensor-in-the-Loop Generative Feedback
arXiv:2610.09400v1 Announce Type: cross Abstract: We present TutorLoop, a sensor-in-the-loop system that regulates student learning behaviors by delivering adaptive feedback based on real-time cognitive states. Unlike pr…
- arXiv cs.AIresearchShared Geometry As A Rosetta Stone: Cross-Modal Alignment Without Paired Data
arXiv:2610.09411v2 Announce Type: replace-cross Abstract: Multimodal representations enable zero-shot classification and retrieval, but aligning independently trained models usually requires large amounts of paired data.…
- arXiv cs.AIresearchMixture of Layers: Dynamic Layer Routing for Visual Reasoning
arXiv:2610.09440v2 Announce Type: replace-cross Abstract: Pre-trained vision encoders contain layer-wise visual representations that differ in spatial granularity, semantic abstraction, and sensitivity to local details.…
- arXiv cs.AIresearchArctic Questions, Missing Answers: A Dataset and Benchmark for LLM Abstention in Arctic Science
arXiv:2610.09446v1 Announce Type: cross Abstract: Large language models (LLMs) should abstain from scientific multiple-choice questions when no option is valid, but frequent abstention alone does not demonstrate sensitiv…
- arXiv cs.AIresearchIris-3B: Going Beyond the Latent with Pixel-Space Diffusion Training, Conversion and Fine-Tuning
arXiv:2610.09450v1 Announce Type: cross Abstract: Pixel-space diffusion models avoid the lossy VAE of latent models, which suggests an advantage on downstream tasks where fine-grained detail matters. We test this claim a…
- arXiv cs.AIresearchGeoPrior-Mamba: Structured Process Priors with Mamba for Fine-Resolution XCO2 Reconstruction
arXiv:2610.09456v1 Announce Type: cross Abstract: Reconstructing fine-resolution column-averaged dry-air CO2 (XCO2) fields from sparse satellite observations requires models to infer spatial structure that is only weakly…
- arXiv cs.AIresearchDSReg: Provably Recovering Individual World Latents without Reconstruction
arXiv:2610.09457v1 Announce Type: cross Abstract: Methods that recover individual latent variables of the world, from nonlinear ICA to dictionary learning and causal representation learning, anchor the latents to observa…
- arXiv cs.AIagentsSecure-CUA: Controlling Untrusted Influence in Computer-Use Agents
arXiv:2610.09469v1 Announce Type: cross Abstract: Computer-use agents (CUAs) perform tasks across applications (such as desktops, mobile apps, and web browsers) by observing graphical interfaces and issuing commands such…
- arXiv cs.AIresearchMORA: Modeling Observed Changes for Drift-Robust Time-Series Anomaly Detection
arXiv:2610.09473v1 Announce Type: cross Abstract: Time-series anomaly detection (TSAD) identifies deviations from patterns learned from historical data. In non-stationary settings, distribution drift and true anomalies c…
- arXiv cs.AIresearchCorrespondences as Decisions: JevNexus for Decision-Centric Schema Matching
arXiv:2610.09487v1 Announce Type: cross Abstract: Schema matching increasingly uses generative language models to rerank retrieved column candidates, although the underlying task is a bounded correspondence decision. We…
- arXiv cs.AIresearchSparse Feature Policy Unlearning Mitigates State Hallucination in Vision-Language-Action Models
arXiv:2610.09496v1 Announce Type: cross Abstract: Vision-Language-Action (VLA) models have shown strong generalization in robotic manipulation by leveraging rich representations from pretrained vision-language models. Ho…
- arXiv cs.AIresearchSpatialUQ: Post-Hoc Uncertainty Quantification from Spatial Consistency in Black-Box Vision Models
arXiv:2610.09498v1 Announce Type: cross Abstract: Clinical vision models are often deployed as frozen black boxes with no access to internals, retraining, or ground truth at inference time. We introduce \textbf{SpatialUQ…
- arXiv cs.AIresearchSafe on Average, Unsafe in the Tail: When Is the Episodic-Cost Tail Controllable?
arXiv:2610.09508v1 Announce Type: cross Abstract: Safe reinforcement learning seeks policies that maximize return while satisfying constraints on cumulative cost. Most methods impose these constraints on expected episodi…
- arXiv cs.AIresearchOmniCam: Omni-Camera Trajectory Generation via Geometry-Grounded Pose Token Learning
arXiv:2610.09513v2 Announce Type: replace-cross Abstract: Camera trajectories control viewpoint changes in video generation, scene reconstruction, and robotic perception. Generating them from language requires both scene…
- arXiv cs.AIagentsNot All Uncertainty Matters: Simulation-in-the-Loop Fast-Slow Reasoning for Decision-Critical Autonomous Driving System
arXiv:2610.09520v1 Announce Type: cross Abstract: Large vision-language models (VLMs) provide powerful open-world perception and reasoning for autonomous driving, but their high computational cost and inference latency m…
- arXiv cs.AIresearchAlign Before You Combine: Reference Space Calibration for Supervision Without Ground Truth
arXiv:2610.09525v1 Announce Type: cross Abstract: We introduce a calibration-first framework that produces supervision scores without access to ground-truth labels or a shared annotation space. Our framework aligns subse…
- arXiv cs.AIresearchKASALv2: Fully Automatic 3D Rotational Symmetry Classification and Axis Localization
arXiv:2610.09534v1 Announce Type: cross Abstract: Rotational symmetry is an important prior in 6D pose estimation, improving pose accuracy and supporting symmetry-aware evaluation. However, current symmetry annotations f…
- arXiv cs.AIresearchWAPR: A Foundation Model for Wide-Angle Refinement in Unseen Object Pose Estimation
arXiv:2610.09535v1 Announce Type: cross Abstract: Real-world applications require 6D pose estimation to be accurate, fast, and scalable to unseen objects. This paper introduces WAPR, a zero-shot wide-angle pose refinemen…