AI news archive.
19,864 articles, newest first, from the outlets listed on the sources page.
- arXiv cs.AIresearchDo VLAs Understand and Adapt to the Objects They Handle, or Simply Replay Learned Behaviors?
arXiv:2610.06078v1 Announce Type: cross Abstract: This paper asks whether VLA generalization is grounded in a global understanding of objects' physical properties that enables policies to adapt their motion to unseen set…
- arXiv cs.AIresearchBoosting Transferable Adversarial Attacks against Deep Reinforcement Learning
arXiv:2610.06083v3 Announce Type: replace-cross Abstract: Most adversarial attacks on deep reinforcement learning (DRL) assume white-box access to the victim policy, which rarely holds in practice. This paper studies tra…
- arXiv cs.AIresearchAdaptive Mean Flow for Responsive Closed-Loop Robot Control
arXiv:2610.06089v1 Announce Type: cross Abstract: Diffusion- and flow-based robot policies have recently become widespread in robotic Imitation Learning (IL) due to their high performance and ability to model continuous…
- arXiv cs.AIresearchCross-Lingual Transferability of Training Data Extraction Attacks to Recover Memorized PII
arXiv:2610.06093v1 Announce Type: cross Abstract: The robustness of Personally Identifiable Information (PII) protection in Large Language Models (LLMs) is a critical concern, yet the risks associated with cross-lingual…
- arXiv cs.AIresearchOn the Geometry of Multimodal Saturation: Riemannian VICReg
arXiv:2610.06096v1 Announce Type: cross Abstract: In self-supervised learning, a third modality should improve, or at least preserve, performance. Across nine image-text-tabular datasets, we show that it instead harms pe…
- arXiv cs.AIresearchMachine learning for journal entry testing: A type-aware evaluation of anomaly detectors under a review budget
arXiv:2610.06133v1 Announce Type: cross Abstract: Journal entry anomaly detectors are commonly evaluated on the full population with ROC-AUC, precision and recall, ignoring the review budget and which anomaly types are f…
- arXiv cs.AIagentsWhere Did the Repair First Go Wrong? Localizing the Origins of Silent Failures in Agentic Vulnerability Repair
arXiv:2610.06163v1 Announce Type: cross Abstract: Localizing where an LLM-based agent first fails to uphold security during a repair can show which stage of its workflow needs an additional safeguard. This is difficult f…
- arXiv cs.AIresearchAnosognosia in LLMs: Probing Self-Awareness of Quantized Computational Substrate
arXiv:2610.06174v1 Announce Type: cross Abstract: Can LLMs recognize degradation in their own computational substrate? Inspired by anosognosia, a neurological condition in which patients fail to recognize impairments in…
- arXiv cs.AIresearchAnlu: Enabling In-Context Time Series Anomaly Detection in Foundation Models via Counterfactual Supervision
arXiv:2610.06180v1 Announce Type: cross Abstract: Whether a time-series pattern is anomalous often depends on the operating regime of the monitored process. A missing event can signal a fault in one regime and be routine…
- arXiv cs.AIagentsCorrect Code, Broken Contributions? SWE-CC: Benchmarking Repository Policy Compliance for Coding Agents
arXiv:2610.06193v1 Announce Type: cross Abstract: Autonomous coding agents now resolve a substantial share of real-world GitHub issues. However, passing functional tests differs fundamentally from producing a high-qualit…
- arXiv cs.AIresearchCross-lingual Calibration of Pre-Generation Success Probes for Multilingual LLM Routing
arXiv:2610.06216v1 Announce Type: cross Abstract: Pre-generation success probes estimate response correctness from a language model's hidden activations before decoding, enabling cost-aware routing. While prior work has…
- arXiv cs.AIagentsAPOD: reasoning-guided agentic population ordinary differential equation discovery for pharmacological digital twins
arXiv:2610.06227v1 Announce Type: cross Abstract: Establishing ordinary differential equations (ODEs) describing population data is a fundamental part of mathematical modeling in pharmacology, crucial to developing digit…
- arXiv cs.AIresearchSO(3)-RoPE for Spherical Transformers
arXiv:2610.06229v1 Announce Type: cross Abstract: Spherical data arise in many scientific applications. Often spherical transformers disregard the geometry of the underlying spherical domain, causing distortions and coor…
- arXiv cs.AIresearchJoint Class-Time Learning for Video Classification with Multi-Instance Partial-Label Learning
arXiv:2610.06234v1 Announce Type: cross Abstract: Multi-instance partial-label learning (MIPL) addresses inexact supervision in both the instance and label spaces, which can be applied to video classification. However, b…
- arXiv cs.AIresearchArtificial Intelligence and the New Science of Culture
arXiv:2610.06240v1 Announce Type: cross Abstract: Cognition and culture have long been treated as parallel objects of study, joined more by metaphor than by mechanism. We argue they are co-constituted in a manner now emp…
- arXiv cs.AIresearchFew-Shot Prototype Head Adaptation for On-Device ECG Personalization on PSoC~6
arXiv:2610.06241v1 Announce Type: cross Abstract: Wearable and bedside electrocardiogram (ECG) monitors must adapt to patient-specific morphology to maintain arrhythmia detection accuracy across users, yet personalizatio…
- arXiv cs.AIresearchCentriQ: Calibration-Free Quantization of Diffusion Transformers via Exact Mean Centering
arXiv:2610.06260v1 Announce Type: cross Abstract: Diffusion transformers (DiTs) achieve state-of-the-art image generation, but their sampling cost limits deployment. Quantizing both weights and activations to 4 bits redu…
- arXiv cs.AIresearchRamp Metering Control via Hybrid State Deep Reinforcement Learning in Partially Observable Connected Vehicle Environments
arXiv:2610.06266v1 Announce Type: cross Abstract: Freeway on-ramp merges are major sources of congestion, causing significant economic and environmental costs. While Deep Reinforcement Learning (DRL) offers a promising s…
- arXiv cs.AIresearchVLA-ZO: Fast Zeroth-Order Adaptation for Vision-Language-Action Models
arXiv:2610.06271v1 Announce Type: cross Abstract: Adapting vision-language-action (VLA) models to deployment-time distribution shifts is important for reliable robotic operation, but conventional first-order adaptation c…
- arXiv cs.AIresearchFuture Anchored Verification and Online Recovery for World Action Models
arXiv:2610.06280v1 Announce Type: cross Abstract: World action models (WAMs) have emerged as a promising paradigm for robotic manipulation. They act by first predicting how a task should be performed and then decoding th…
- arXiv cs.AIresearchWhen Are Concept Bottleneck Model Explanations Faithful and Compact?
arXiv:2610.06285v1 Announce Type: cross Abstract: Concept bottleneck models (CBMs) are neural classifiers that allow to explain their decisions via high-level concepts, potentially enabling understanding, steering and de…
- arXiv cs.AIresearchGAMBIT: Learning to Plan Continuous Multi-Robot Trajectories
arXiv:2610.06290v1 Announce Type: cross Abstract: GAMBIT is an opening chess move in which a player sacrifices a piece, typically a pawn, to gain a positional advantage later in the game. Analogously, in multi-robot coor…
- arXiv cs.AIresearchDialectSentEval 2026: Arabic Dialect Sentiment Analysis and Swapping Shared Task
arXiv:2610.06298v1 Announce Type: cross Abstract: Sentiment analysis is a fundamental problem in Natural Language Processing (NLP). Standard sentiment classification for the Arabic language remains challenging due to the…
- arXiv cs.AIresearchWiring Matters: Injection Topology and Initialization of Affordance Heads in Vision-Language-Action Policies
arXiv:2610.06318v1 Announce Type: cross Abstract: Dense affordance supervision is an appealing auxiliary signal for vision-language-action (VLA) policies, yet naively co-training an affordance head can severely damage in…
- arXiv cs.AIagentsAgentic schema-guided extraction of materials process knowledge from scientific literature
arXiv:2610.06322v1 Announce Type: cross Abstract: Materials literature contains detailed experimental knowledge, but procedures, chemical entities and measurements remain difficult to aggregate because they are reported…
- arXiv cs.AIresearchFine-Tuning a 3B-Parameter LLM on a Smartphone: Characterizing Sustained Training
arXiv:2610.06325v1 Announce Type: cross Abstract: Multi-billion-parameter LLMs now run on phones for inference, and training them on the device would personalize them without user data leaving the phone. Prior work has m…
- arXiv cs.AIresearchMeSD: Multi-Evidence Self-Distillation for VideoLLM
arXiv:2610.06342v1 Announce Type: cross Abstract: While reinforcement learning with verifiable rewards provides reliable outcome supervision for VideoLLMs, sequence-level rewards offer limited token-level guidance. On-po…
- arXiv cs.AIresearchSteering by Influence: Curvature Aware Data Weighting for Activation Steering
arXiv:2610.06383v1 Announce Type: cross Abstract: Inference-time steering offers cheap, fine-grained control over a language model's outputs by estimating a concept's representation in activation space and shifting activ…
- arXiv cs.AIresearchScaling Down the Scaling Laws: Parameter Efficiency and Compute-Optimal Training in Resource-Constrained Large Language Models
arXiv:2610.06387v2 Announce Type: replace-cross Abstract: Large language models (LLMs) have achieved substantial performance gains through increases in model size, training data, and computational resources. However, tra…
- arXiv cs.AIagentsRAISED: Self-Distillation for Robustness to Prompt Injection in LLM Agents
arXiv:2610.06401v2 Announce Type: replace-cross Abstract: Tool-using language-model agents are vulnerable to indirect prompt injection because they must act on untrusted external content. Existing training-time defenses…
- arXiv cs.AIresearchQuantifying the Stability of Multi-Step Reasoning via Error Amplification
arXiv:2610.06404v1 Announce Type: cross Abstract: We consider the stability of multi-step reasoning processes, which have extensive applications in language models, including chain-of-thought and algorithmic reasoning. W…
- arXiv cs.AIresearchSpatialChain: A Benchmark for Auditing Spatial Reasoning Faithfulness in VLMs
arXiv:2610.06413v1 Announce Type: cross Abstract: Thinking-enabled vision-language models (VLMs) report ever-higher accuracy on spatial benchmarks, yet final-answer scores cannot reveal whether a correct prediction refle…
- arXiv cs.AIresearchToward Reliable Infant Pose Estimation: A Training-Dynamics Approach to Noisy Annotation Detection
arXiv:2610.06423v1 Announce Type: cross Abstract: Spontaneous movement analysis in preterm infants relies increasingly on markerless pose estimation (PE) to derive clinically relevant motion biomarkers directly from vide…
- arXiv cs.AIresearchSoK: Semantic Decision Engines in Network Control Loops
arXiv:2610.06425v1 Announce Type: cross Abstract: A semantic decision engine such as Jev can return a valid answer and still miss a network deadline, select an infeasible action or leave the service unverified. We system…
- arXiv cs.AIagentsValid Stopping in Adaptive Generator-Verifier Loops
arXiv:2610.06432v1 Announce Type: cross Abstract: Numerous agentic workflows are based on a generator-verifier loop: a generator proposes candidates, a cheap verifier scores them, and the workflow terminates when a propo…
- arXiv cs.AIresearchBetter Call Reward: Reward Hacking as Strategic Abstention in Legal Reasoning Models
arXiv:2610.06439v1 Announce Type: cross Abstract: What happens when a legal AI model learns to look like a lawyer instead of reasoning like one? We fine tune Qwen3-8B with Group Relative Policy Optimisation (GRPO) agains…
- arXiv cs.AIresearchARO: Aligned Representation learning for multi-Omics data
arXiv:2610.06443v1 Announce Type: cross Abstract: The high cost of functional molecular assays, and prevalence of missing modalities and unmatched samples in computational biology, create significant barriers to comprehe…
- arXiv cs.AIresearchChoosing an energy-efficient software architecture for building system diagnostic support
arXiv:2610.06444v1 Announce Type: cross Abstract: Around 30\% of global energy expenditure can be attributed to the building sector, where a large portion of energy-consumption could be avoided by repairing existing faul…
- arXiv cs.AIresearchThe Assistance Dilemma: Learning to Teach via Multi-Turn Reinforcement Learning
arXiv:2610.06446v1 Announce Type: cross Abstract: Large language models (LLMs) trained to answer questions are natively poor at teaching. Reinforcement Learning (RL) against a simulated student is a promising approach to…
- arXiv cs.AIresearchA Physics-Guided Transformer Framework for Electromigration Analysis in Multi-Segment Interconnects
arXiv:2610.06464v1 Announce Type: cross Abstract: As technology scales to smaller nodes, increasing current densities make electromigration (EM) one of the dominant reliability challenges in on-chip interconnects. Accura…
- arXiv cs.AIresearchLatent Flow Matching for Molecular Graph Generation
arXiv:2610.06468v1 Announce Type: cross Abstract: Modern graph generative models typically operate directly in the discrete graph space, explicitly generating node and edge variables, which can become costly as graphs gr…
- arXiv cs.AIresearchOdyssey: A Closed-Loop Benchmark for Long-Horizon Real-World Driving with Explicit Navigation Routes
arXiv:2610.06469v1 Announce Type: cross Abstract: Closed-loop evaluation of end-to-end driving requires continuous rollouts that reveal how earlier decisions affect subsequent driving. However, existing benchmarks evalua…
- arXiv cs.AIresearchTopology-Informed Prompt-Conditioned Universal Segmentation of Uterine Structures from Ultrasound and MRI
arXiv:2610.06494v1 Announce Type: cross Abstract: Multi-structure segmentation of the uterus is important for computer-assisted screening, diagnosis, and treatment planning of uterine diseases, where ultrasound and MRI p…
- arXiv cs.AIresearchHarmful Content Generation in Text-to-Image Models: Capabilities and Moderation Limitations
arXiv:2610.06503v1 Announce Type: cross Abstract: Text-to-image generative models can produce highly realistic imagery but also raise concerns about harmful misuse. While safety mechanisms exist, systematic evaluations o…
- arXiv cs.AIresearchArtifactArena: Evaluating Models by What They Build in the Physical World
arXiv:2610.06511v2 Announce Type: replace-cross Abstract: To evaluate the frontier, we must measure models not by what they say, but by what they can engineer and build in grounded physical environments. We introduce Art…
- arXiv cs.AIagentsGCTAuto-encoder: A Cross modal Framework for Security Flaw Detection in IoT Networks
arXiv:2610.06517v1 Announce Type: cross Abstract: IoT encompasses diverse physical entities, from smart home devices to autonomous vehicles, creating a complex environment with heterogeneous security models. This heterog…
- arXiv cs.AIresearchAnatomy of LLM Sycophancy: What a Flip Rate Hides
arXiv:2610.06522v1 Announce Type: cross Abstract: A model under pushback can correct itself, capitulate, or hold, and one flip rate counts a correction and a capitulation alike. Using SycoLens, a modular replay protocol,…
- arXiv cs.AIresearchSymmetry and AI-assisted discovery of magic-state factories
arXiv:2610.06535v1 Announce Type: cross Abstract: Magic-state distillation is a major resource cost in fault-tolerant quantum computing. The cost of a magic-state factory depends strongly on its failure rate, which grows…
- arXiv cs.AIresearchBrainTRACE: Tracing Longitudinal, Multimodal, and Volumetric Evidence in Brain MRI Clinical Reasoning
arXiv:2610.06571v1 Announce Type: cross Abstract: Brain MRI interpretation is a longitudinal clinical reasoning problem: radiologists compare serial studies, integrate information across MRI sequences, localize findings…
- arXiv cs.AIagentsDoes AI Help Cyber Attackers or Defenders? Evidence from Nonpublic Vulnerabilities and Subsequent Attacks
arXiv:2610.06584v1 Announce Type: cross Abstract: The release decision for frontier AI systems increasingly relies on cyber capability benchmarks, yet public vulnerability benchmarks can expose agents to previously publi…