AI news archive.
19,864 articles, newest first, from the outlets listed on the sources page.
- arXiv cs.AIresearchPredicting Steering Vectors and Adapter Weights for Few-Shot Author-Style Transfer
arXiv:2610.03163v1 Announce Type: cross Abstract: Adapting large language models to an individual author's style from a few examples is challenging, and scientific writing sharpens the difficulty: formal conventions leav…
- arXiv cs.AIresearchLiBRA: Detection-Aware Image Watermark Removal via Bidirectional Latent Optimization
arXiv:2610.03166v1 Announce Type: cross Abstract: Digital watermarking supports source attribution for AI-generated images, but its reliability depends on resistance to removal attacks. Some attacks attempt to remove wat…
- arXiv cs.AIresearchNot Until the Evidence Says So: Teaching LLM Investigators When to Close a Case
arXiv:2610.03190v1 Announce Type: cross Abstract: Accident, defect and outage investigations end with a decision that ordinary question answering never faces: whether the evidence gathered so far is enough to close the c…
- arXiv cs.AIresearchContextual Flow Matching: Adaptive Step Selection in Flow Models for Efficient Visual Generation
arXiv:2610.03202v1 Announce Type: cross Abstract: Flow Matching enables high-quality visual generation via continuous-time dynamics, but inference remains costly due to multiple sequential function evaluations. Existing…
- arXiv cs.AIresearchEvolving Hybrid Quantum-Classical Architectures for Image Classification
arXiv:2610.03220v2 Announce Type: replace-cross Abstract: Hybrid quantum classical neural networks integrate parameterized quantum circuits (PQCs) with established deep learning architectures, but their performance depen…
- arXiv cs.AIresearchUncertainty as a Proxy for Semantic Correctness in Diffusion-Based Medical Image Synthesis
arXiv:2610.03224v1 Announce Type: cross Abstract: Diffusion models can synthesise contrast-enhanced CT (CECT) from non-contrast CT (NCCT), avoiding contrast administration and its environmental and patient-access costs.…
- arXiv cs.AIagentsD2K-Bench: Can LLM Agents Turn Expert Designs into Efficient GPU Kernels?
arXiv:2610.03226v1 Announce Type: cross Abstract: GPU kernels generated by large language model (LLM) agents can remain less efficient than expert implementations, but runtime alone does not reveal how the gap relates to…
- arXiv cs.AIresearchWAMpy: Efficient Synthesis of Prolog Programs in Python
arXiv:2610.03234v1 Announce Type: cross Abstract: We present WAMpy, a Python framework optimized for synthesizing Prolog programs. Unlike general-purpose Prolog systems, WAMpy targets workloads that repeatedly generate a…
- arXiv cs.AIresearchMapping and Advancing the Scalability-Accuracy Frontier of Nonlinear Causal Discovery
arXiv:2610.03258v1 Announce Type: cross Abstract: Scalable nonlinear causal discovery requires methods that combine flexible mechanism estimators with efficient search over large graph spaces. Several algorithmic familie…
- arXiv cs.AIresearchConsecutive Posterior Fusion for Diffusive Recovery of Unobservable Image Structures
arXiv:2610.03261v1 Announce Type: cross Abstract: Solving severely ill-posed imaging inverse problems requires recovering image structures that are unobservable or weakly constrained by the measurements. Diffusion models…
- arXiv cs.AIresearchSPEAR: A Spectral-Disentangled MoE Neural Operator with Knowledge-Guided Expert Aggregation for Large-Scale PDE Pretraining
arXiv:2610.03265v1 Announce Type: cross Abstract: Large-scale pre-training has improved the generalization of neural operators across diverse PDEs. However, existing PDE foundation models still struggle with heterogeneou…
- arXiv cs.AIresearchTraining-Loss Guarantees for Muon with Finite-Step Newton--Schulz Orthogonalization
arXiv:2610.03306v1 Announce Type: cross Abstract: Existing convergence analyses of Muon either assume exact orthogonalization or analyze classical Newton--Schulz polynomials, and guarantee only stationarity, so it is unr…
- arXiv cs.AIresearchInformation Limits of Low-Rank Approximation Certification
arXiv:2610.03321v1 Announce Type: cross Abstract: Low-rank approximation can require additional matrix--vector products to verify that its error meets a prescribed tolerance. We characterize this certification cost for b…
- arXiv cs.AIresearchSyntaxBench: A Statistical Diagnostic Framework for Character-Level Reasoning in Large Language Models
arXiv:2610.03329v1 Announce Type: cross Abstract: Large language models are increasingly used where small syntactic errors matter, yet character-level reasoning is still evaluated mostly through isolated probes and aggre…
- arXiv cs.AIagentsCordial Learning: Distributed Training with Correlated Data
arXiv:2610.03330v1 Announce Type: cross Abstract: We consider a distributed learning task with agents that have correlated data. Specifically, the label of an agent depends on the input of other agents for the same sampl…
- arXiv cs.AIresearchEquivariant Visual-Tactile Diffusion Policy for Contact-Rich Manipulation
arXiv:2610.03333v1 Announce Type: cross Abstract: Imitation learning for contact-rich manipulation requires high-quality expert data that is expensive to obtain. This makes learning a sample-efficient policy a key issue.…
- arXiv cs.AIagentsFollow the Winners: Conservative Policy Improvement with the Cross-Entropy Method for Critic-Free RFT
arXiv:2610.03361v1 Announce Type: cross Abstract: Critic-free reinforcement fine-tuning (RFT) for agentic large language models is often done through GRPO-style methods, which compute a group baseline over repeated rollo…
- arXiv cs.AIresearchDriftTTS: Few-Step Text-to-Speech Without Distillation via Distribution-Matching Drift
arXiv:2610.03390v1 Announce Type: cross Abstract: Few-step neural text-to-speech models often rely on short- ened diffusion or flow-matching schedules, or on distillation from pretrained multi-step teachers. To avoid the…
- arXiv cs.AIresearchForestQuery: Boundary-Aware and Spatially Anchored Query Learning for Unified Forest Point Cloud Segmentation
arXiv:2610.03403v1 Announce Type: cross Abstract: Forest point cloud segmentation is fundamental for fine-grained 3D forest scene understanding, yet remains challenging due to irregular tree structures, severe occlusions…
- arXiv cs.AIresearchRethinking Epistemic Uncertainty in Node Classification through Information Growth
arXiv:2610.03418v1 Announce Type: cross Abstract: Epistemic uncertainty should decrease as additional information about the data-generating process (DGP) becomes available to the predictor. Yet, existing graph evidential…
- arXiv cs.AIresearchOptiSelect: How does the Optimizer Shape Data Curriculum?
arXiv:2610.03432v1 Announce Type: cross Abstract: Online data selection has demonstrated substantial efficiency gains for LLM pretraining by training on the most valuable candidates within each batch. Since a candidate's…
- arXiv cs.AIresearchCorrupted but Correct: Why Vision-Language Models Lie to Themselves Internally
arXiv:2610.03445v2 Announce Type: replace-cross Abstract: A targeted adversarial perturbation can drive a vision-language model's (VLM's) teacher-forced training loss for a fixed target caption to near zero, yet the same…
- arXiv cs.AIresearchMeasure Less, Know More: Self-Supervised Test-Time Feature Acquisition
arXiv:2610.03454v1 Announce Type: cross Abstract: Recent progress in multimodal, high-dimensional learning has enabled foundation models to process heterogeneous, large-scale data. However, at test time, acquiring all fe…
- arXiv cs.AIresearchPreserving Anatomical Continuity: Three-Stage Pipeline for Colon Segmentation in 3D Abdominal CT Scans
arXiv:2610.03467v1 Announce Type: cross Abstract: Accurate colon segmentation from CT images is essential for colorectal disease analysis, yet deep learning based methods often produce disconnected predictions due to com…
- arXiv cs.AIresearchSingle or Multiple Policies for Phase-Structured Reinforcement Learning?
arXiv:2610.03475v1 Announce Type: cross Abstract: Many reinforcement-learning (RL) problems are non-stationary yet structured and can be decomposed into phases, each with its own transition probabilities and reward funct…
- arXiv cs.AIagentsMobiAgent: Dual-Loop Recursive Policy Self-Improvement for Long-Horizon Mobile Manipulation
arXiv:2610.03476v1 Announce Type: cross Abstract: Long-horizon mobile manipulation presents significant challenges due to compounding execution errors and capacity interference between locomotion and arm control. While r…
- arXiv cs.AIresearchAREX: Affine-Residual Exponential Integrator for Few-Step Sampling in Flow Matching
arXiv:2610.03483v1 Announce Type: cross Abstract: We introduce AREX, a training-free sampler for pretrained flow matching models that uses the target mean and covariance to capture an analytically tractable part of the s…
- arXiv cs.AIresearchDetect and Suppress: A Mechanistic Defense against Adversarial Patches in VLA Models
arXiv:2610.03498v2 Announce Type: replace-cross Abstract: Adversarial patches can disrupt Vision-Language-Action (VLA) models by manipulating visual observations, leading to failures in robot control. However, it remains…
- arXiv cs.AIresearchCertified Mechanistic Edits: Behavioral Guarantees for Skill Removal and Preservation
arXiv:2610.03502v1 Announce Type: cross Abstract: Mechanistic edits (ablations, weight edits, activation steering) are the standard tools for unlearning a harmful capability from a neural network while preserving useful…
- arXiv cs.AIresearchWeave Forcing: Compositional Memory Routing for Interactive Long Video Generation
arXiv:2610.03510v1 Announce Type: cross Abstract: Recent advances in autoregressive video generation have improved temporal consistency over extended durations, yet interactive storytelling requires more than continuous…
- arXiv cs.AIresearchBeyond Trained Models: Compiling GNNs for a Sound Explainer Benchmark
arXiv:2610.03526v1 Announce Type: cross Abstract: Explainers for Graph Neural Networks (GNNs) are commonly evaluated by their plausibility, i.e., how well their explanations recover a predefined ground truth, such as a m…
- arXiv cs.AIresearchCephalonauts One: A deep fMRI dataset for decoding naturalistic speech in the human brain
arXiv:2610.03558v1 Announce Type: cross Abstract: Cephalonauts One is a whole-brain 3 Tesla (3T) functional magnetic resonance imaging (fMRI) dataset recorded while subjects listened to audio podcasts. Three healthy subj…
- arXiv cs.AIresearchRethinking What to Cache in Few-Step Diffusion Transformers: Solver-Aware Target Selection
arXiv:2610.03577v1 Announce Type: cross Abstract: Diffusion Transformers (DiTs) can generate high-quality images and videos, but generating each sample requires multiple costly DiT forward passes. Two common ways to acce…
- arXiv cs.AIagentsThreat-Preserving Representation Sensitivity in Agent-Security Benchmarks
arXiv:2610.03585v1 Announce Type: cross Abstract: Security benchmarks for LLM-based agents often report the attack success rate (ASR) as a measure of model robustness and use these scores to compare different models and…
- arXiv cs.AIresearchWhen a Correct Reward Is Not Enough: Diagnosing and Guiding PPO in an Analytically Solved Broker-Trader Game
arXiv:2610.03598v1 Announce Type: cross Abstract: Reinforcement learning (RL) is increasingly used for financial optimal-control problems when complex dynamics make analytical strategies difficult to obtain. There are fi…
- arXiv cs.AIresearchLoGo: Local-Global Rewards for Consistent Long-Horizon Video Generation
arXiv:2610.03636v1 Announce Type: cross Abstract: Camera-controlled video models are rapidly advancing toward long generation horizons and complex camera control. A key failure mode is 3D inconsistency: as the camera mov…
- arXiv cs.AIresearchOn-Board Anomaly Detection for Efficient Marine Environmental Monitoring
arXiv:2610.03649v1 Announce Type: cross Abstract: Marine ecosystems are impacted by various threats such as oil spills, algal blooms, and sediment floods, which disrupt habitats, wildlife, and human activities. Advances…
- arXiv cs.AIresearchRevisiting Input Time-frequency Representations in Multi-pitch Estimation for Vocal Ensembles
arXiv:2610.03656v2 Announce Type: replace-cross Abstract: Multi-pitch estimation in vocal ensembles is challenging because singers occupy overlapping pitch ranges and often sing at closely spaced fundamental frequencies,…
- arXiv cs.AIresearchFrugalEvo: Towards Cost-Aware LLM-Guided Program Evolution
arXiv:2610.03675v1 Announce Type: cross Abstract: LLM-guided evolutionary methods, such as AlphaEvolve, have emerged as powerful approaches for challenging computational optimization problems, such as circle packing. How…
- arXiv cs.AIresearchEyeRobot 2.0: Active Gaze for Precise Manipulation without Wrist Cameras
arXiv:2610.03710v1 Announce Type: cross Abstract: Inspired by human vision, we introduce a framework using active gaze to enable fine-grained bimanual manipulation with only a single stereo camera. EyeRobot 2.0 physicall…
- arXiv cs.AIresearchWhat Should World Models Forget? Stratified Retention for Continual Adaptation
arXiv:2610.03713v1 Announce Type: cross Abstract: Continual learning treats degradation on previously seen data as evidence of failure, a convention inherited from settings with a stationary prediction target, where a co…
- arXiv cs.AIagents4DCodeBench: Benchmarking Agents on Inverse Graphics of Dynamic Scenes
arXiv:2610.03715v1 Announce Type: cross Abstract: We introduce 4DCodeBench, a benchmark for 4D inverse graphics through code generation, in which agents reconstruct dynamic scenes from video as executable graphics progra…
- arXiv cs.AIresearchLess Decoder is More Encoder: Geometric Representation Learning from Novel View Synthesis
arXiv:2610.03717v1 Announce Type: cross Abstract: This paper examines the role of Novel View Synthesis (NVS) in geometric representation learning. In principle, NVS should reason about 3D scene structure, thereby enablin…
- arXiv cs.AIresearchHeads, Tails, and AI Fails: LLMs, Randomness, and Human Judgments
arXiv:2406.00092v2 Announce Type: replace Abstract: Randomness is central to human cognition and to many applications in which large language models are deployed, yet probabilistic token generation does not imply that LL…
- arXiv cs.AIagentsLPS-Bench: Benchmarking Safety Awareness of Computer-Use Agents in Long-Horizon Planning under Benign and Adversarial Scenarios
arXiv:2602.03255v2 Announce Type: replace Abstract: Computer-use agents (CUAs) execute multi-stage tasks through tools, where an early unsafe decision can propagate to consequential actions. Evaluating only final outcome…
- arXiv cs.AIresearchOn the Tip of the Tongue: Why LLMs Hallucinate Answers They Can Decode
arXiv:2603.13911v2 Announce Type: replace Abstract: A language model can give the wrong answer even when the correct answer is decodable from its intermediate states. To study this gap between decodability and selection,…
- arXiv cs.AIresearchGISTBench: Evaluating LLM User Understanding via Evidence-Based Interest Verification
arXiv:2603.29112v2 Announce Type: replace Abstract: We introduce GISTBench, a benchmark for evaluating Large Language Models' (LLMs) ability to understand users from their interaction histories in recommendation systems.…
- arXiv cs.AIresearchWhat's Missing in Screen-to-Action? Towards a UI-in-the-Loop Paradigm for Multimodal GUI Reasoning
arXiv:2604.06995v3 Announce Type: replace Abstract: Existing Graphical User Interface (GUI) reasoning tasks remain challenging, particularly in UI understanding. Current methods typically rely on direct screen-based deci…
- arXiv cs.AIresearchWhat do your logits know?
arXiv:2604.09885v3 Announce Type: replace Abstract: Recent work has shown that probing model internals can reveal a wealth of information not apparent from the model generations. This poses a risk of unintentional or mal…
- arXiv cs.AIresearchOffline Policy Optimization with Posterior Sampling
arXiv:2605.07393v2 Announce Type: replace Abstract: A fundamental challenge in model-based offline reinforcement learning (RL) lies in the trade-off between generalization and robustness against exploitation errors in ou…