AI news archive.
19,864 articles, newest first, from the outlets listed on the sources page.
- arXiv cs.AIresearchSENTRY: A Streaming Edge Network Trust Engine for Real-Time Audio Deepfake Detection
arXiv:2610.24468v1 Announce Type: cross Abstract: Real-time voice cloning has enabled large-scale streaming deepfake and vishing attacks, while existing Network Detection and Response (NDR) solutions rely on GPU-based po…
- arXiv cs.AIresearchWhich Long Documents Matter? A Controlled Study of Data Selection for Context Extension
arXiv:2610.24469v1 Announce Type: cross Abstract: Natural long documents are widely used for context extension, but which selection pipelines are effective remains unclear. We conduct a controlled comparison on Qwen2.5-3…
- arXiv cs.AIagentsWrite Once, Check Many: Reusable Ledgers for Post-Hoc Policy Compliance Auditing of Agent Trajectories
arXiv:2610.24483v1 Announce Type: cross Abstract: Auditing LLM agents against policies is critical to ensure safety but requires rereading long trajectories once per policy. Can we instead record each trajectory once and…
- arXiv cs.AIresearchGazeAct: A Human-Gaze-Annotated Manipulation Dataset for Attention-Regularized Policies
arXiv:2610.24507v1 Announce Type: cross Abstract: Vision-language-action (VLA) policies must ground language instructions in the right objects, contact points, and target locations for reliable manipulation. Human gaze p…
- arXiv cs.AIresearchContrastive Hypergraph Source-free Domain Adaptive Object Detection in Adverse Weather Conditions--Extended Version
arXiv:2610.24532v1 Announce Type: cross Abstract: Adverse weather conditions such as fog, rain, snow, and low illumination introduce structured visibility degradations that severely impair object detectors trained on cle…
- arXiv cs.AIagentsWhen Code Becomes an LLM Call: An Empirical Study of Call-Site Contracts in Agentic Systems
arXiv:2610.24545v1 Announce Type: cross Abstract: Software quality has long rested on specifications that state what code must do, and on testing and verification that check that the code does it. Agentic systems change…
- arXiv cs.AIagentsCARVS: A Congestion-Aware Algorithm for Online Multi-Agent Pickup-and-Delivery in Human-Collaborative Warehouses
arXiv:2610.24549v1 Announce Type: cross Abstract: Intelligent warehouse systems have transformed logistics by integrating robots with minimal infrastructure changes, boosting efficiency and optimizing workflows compared…
- arXiv cs.AIresearchFrom Stories to Features: Scaling Concept Vectors for AI Alignment & Interpretability
arXiv:2610.24556v1 Announce Type: cross Abstract: We study feature vectors: directions in a language model's activation space that correspond to human-interpretable concepts, such as honesty or deception. Existing unsupe…
- arXiv cs.AIresearchASR Personalization in Pathological Voice: Accuracy, Efficiency, and Duration Effects
arXiv:2610.24572v1 Announce Type: cross Abstract: Automatic Speech recognition (ASR) struggles with Pathological speech due to persistent speaker-specific mismatch. In clinical and accessibility scenarios, only limited t…
- arXiv cs.AIagentsScene-Adaptive VLA: Efficient Autonomous Driving via Dynamic Layer Routing
arXiv:2610.24590v1 Announce Type: cross Abstract: Vision-Language-Action (VLA) models offer a promising paradigm for autonomous driving. However, the massive parameter scale of VLAs strains onboard computational resource…
- arXiv cs.AIresearchAdamPM: Memory-Efficient LLM Optimization via Moment Pooling
arXiv:2610.24598v1 Announce Type: cross Abstract: Adam is widely used for training large language models (LLMs) owing to its strong optimization performance and training stability, but its element-wise estimation for the…
- arXiv cs.AIresearchSeverity-Channel Conditioning: An Injection-Level Study for Consumer-Device Deblurring
arXiv:2610.24599v1 Announce Type: cross Abstract: Motion-deblurring models lose substantial accuracy when transferred from professional cameras to smartphone-derived imagery. This paper studies whether a severity descrip…
- arXiv cs.AIresearchHow Much Do Activation Monitors Benefit from Original Model Computations?
arXiv:2610.24613v1 Announce Type: cross Abstract: One powerful way to safeguard AI systems is to monitor their internal computations--where signs of undesirable behavior might be more easily detectable than from models'…
- arXiv cs.AIagentsMuse Glimmer 30B: An On-Device Agentic Model
arXiv:2610.24628v3 Announce Type: replace-cross Abstract: We introduce Muse Glimmer, an open-source 30B parameter causal language model with perception encoder, purpose-built for autonomous agentic tasks on consumer hard…
- arXiv cs.AIresearchContrastive Adversarial Training for Robust Graph Neural Networks under Label Poisoning
arXiv:2610.24685v1 Announce Type: cross Abstract: Graph Neural Networks (GNNs) are effective for modeling relational data but are vulnerable to label poisoning, where a small number of corrupted training labels can propa…
- arXiv cs.AIagentsDiffuPlan: Editable Planning State for Diffusion Language Model Agents
arXiv:2610.24717v1 Announce Type: cross Abstract: Diffusion language models (dLLMs) are emerging as an alternative to autoregressive (AR) language models, yet dLLM agents largely inherit an interaction protocol designed…
- arXiv cs.AIresearchTensor Network Datamodels for Training Data Attribution
arXiv:2610.24721v1 Announce Type: cross Abstract: Datamodels predict how a model's behavior changes when different parts of its training data are included or removed. However, linear datamodels assign fixed contributions…
- arXiv cs.AIresearchGLOSS-MT: Controllable Low-Resource Machine Translation with an Editable Dictionary
arXiv:2610.24730v1 Announce Type: cross Abstract: Adapting a pretrained machine translation (MT) model to new terminology usually requires new parallel data and another round of fine-tuning, which is costly for low-resou…
- arXiv cs.AIresearchCorrFlow: Self-Correcting Flow Matching
arXiv:2610.24750v1 Announce Type: cross Abstract: Flow-matching models generate samples through iterative velocity predictions, but typically do not revisit these predictions using the intermediate representations that p…
- arXiv cs.AIresearchEvidence Field: Adaptive Covering Programs for Medical Imaging
arXiv:2610.24773v1 Announce Type: cross Abstract: Medical image classifiers typically return predictions without a native contract for independently reconstructing their spatial decision computation. Evidence Field is a…
- arXiv cs.AIresearchAI Rights with an Off-Switch: Rights-Balancing and Due Process Harmonize AI Rights with AI Safety
arXiv:2610.24782v1 Announce Type: cross Abstract: Several prominent voices in AI safety have recently opposed rights for AI on the grounds that such rights would make it harder for us to justify a mandatory off-switch fo…
- arXiv cs.AIresearchLLM Trojans that Increase Response Lengths and Cost
arXiv:2610.24784v1 Announce Type: cross Abstract: Management of the token-based costs of using LLMs has emerged as a significant problem. Some frontier-model providers charge five times per response token than per prompt…
- arXiv cs.AIresearchWhen LLM-Generated Refactorings Ripple: An Empirical Study of Repository Adoption Readiness
arXiv:2610.24790v1 Announce Type: cross Abstract: Large Language Models (LLMs) are increasingly used to refactor source files, but file-local evaluations do not reveal changes to contracts, dependencies, or caller assump…
- arXiv cs.AIagentsCooperation Without Shared Rewards via Reciprocal Q-Augmentation
arXiv:2610.24793v1 Announce Type: cross Abstract: General-sum games are more challenging than fully cooperative or adversarial settings because agents may deceive or exploit one another. Achieving high social welfare req…
- arXiv cs.AIresearchFirst-Order LoRA Training with Phone NPUs
arXiv:2610.24816v2 Announce Type: replace-cross Abstract: On-device fine-tuning lets a large language model (LLM) learn from its user's private data without uploading it. Low-rank adaptation (LoRA) reduces the trainable…
- arXiv cs.AIagentsPair-Aware Optimization: Coordinating Exploration and Refinement for Jailbreaking LLM Agents
arXiv:2610.24823v1 Announce Type: cross Abstract: Large Language Model (LLM) agents are vulnerable to adversarial inputs that induce attacker-specified malicious behaviors, commonly referred to as jailbreaking. Existing…
- arXiv cs.AIresearchSpriteStage: Long Horizon Animation Generation via Progressive Scene Programming and Replay
arXiv:2610.24869v1 Announce Type: cross Abstract: Video generation models synthesize visual sequences from text and image inputs. Extending video generation to long animations requires actions, dialogue, camera coverage,…
- arXiv cs.AIresearchRAFT: Redundancy-Aware Input Filtering for Temporal Graph Neural Network Training
arXiv:2610.24875v1 Announce Type: cross Abstract: Temporal graph neural networks (TGNNs) have shown strong performance on dynamic graph learning tasks by continuously updating node memories from evolving interactions (i.…
- arXiv cs.AIresearchLeveraging Mental Models for Human-Centered Explanations: A Systematic Design Approach Illustrated by Explainable Fake Review Identification
arXiv:2610.24903v1 Announce Type: cross Abstract: Explainable AI (XAI) often prioritizes model fidelity over user intelligibility, yielding explanations that satisfy technical transparency yet fail to support human sense…
- arXiv cs.AIagentsArctic-SWE: Revisiting the Long Horizon Agent Training by Modeling-System Co-Design
arXiv:2610.24914v1 Announce Type: cross Abstract: Long-horizon agent training, including software engineering, is advancing rapidly, but the recipe and infrastructure needed for a strong reinforcement-learning baseline r…
- arXiv cs.AIagentsSame Data, Different Bytes: Serialization-Invariant Integrity Checks for Agent-Published Datasets
arXiv:2610.24916v1 Announce Type: cross Abstract: Agent networks require reliable ways for requesting agents to verify where data is located, how it can be accessed, and whether the data received matches what the data ow…
- arXiv cs.AIresearchHow Well Can LLMs Verbalize Mathematical Formulas? A Multi-Domain Evaluation
arXiv:2610.24917v1 Announce Type: cross Abstract: Large Language Models (LLMs) have shown strong capabilities across natural language tasks. But their ability to generate accurate written verbalizations of mathematical f…
- arXiv cs.AIresearchStable Signer V3: 4D Deformable Primitive Splatting Is All You Need for Sign Language Production
arXiv:2610.24926v2 Announce Type: replace-cross Abstract: We present Stable Signer V3, an interactive high-resolution sign language avatar system built on 4D Deformable Primitive Splatting. It addresses three limitations…
- arXiv cs.AIagentsWhat Can't Jev Decide? Probing the Limits of One-Pass Decision Models
arXiv:2610.24929v1 Announce Type: cross Abstract: Jev and its open replicas choose among the options a caller supplies with a single forward pass, fast enough to decide inside an agent loop. We ask what such a model cann…
- arXiv cs.AIagentsTrustAgent-RFF: Agentic Diagnostic Planning for Reliable RF Fingerprinting under Domain Shift
arXiv:2610.24930v2 Announce Type: replace-cross Abstract: Radio frequency fingerprinting (RFF) models can achieve accuracy under source domain conditions but become unreliable when the receiver, distance, collection day,…
- arXiv cs.AIagentsEpi: Towards a Persistent, Self-Improving Agent for Autonomous Research
arXiv:2610.24944v1 Announce Type: cross Abstract: We present \'{E}pi, an autonomous research agent that sustains investigations across model sessions and evolves its methods through accumulated experience. \'{E}pi combin…
- arXiv cs.AIresearchRobust Direct Preference Optimization under Preference Label-Flip Attacks
arXiv:2610.24945v1 Announce Type: cross Abstract: Direct Preference Optimization (DPO) is widely used for offline Reinforcement Learning from Human Feedback. However, recent works have shown that DPO can be easily manipu…
- arXiv cs.AIresearchControlJEPA: Principled Trajectory Regularization via Lyapunov Tube Loss
arXiv:2610.24951v1 Announce Type: cross Abstract: Next-token prediction leaves hidden-state trajectories largely unconstrained, while existing geometric regularizers primarily control the direction rather than the magnit…
- arXiv cs.AIresearchCasePlay: Self-Play Reinforcement Learning from Case Reports for Medical Reasoning
arXiv:2610.24952v1 Announce Type: cross Abstract: Reinforcement learning (RL) is a promising way to improve the clinical reasoning abilities of large language models (LLMs), but current pipelines often rely on expert-lab…
- arXiv cs.AIresearchLabel-Space Mismatch Distorts Cross-Cohort Evaluation in Breast Cancer Molecular Subtyping
arXiv:2610.24962v1 Announce Type: cross Abstract: Cross-cohort evaluation of breast cancer subtype classifiers is unreliable when source and target cohorts use different annotation standards: METABRIC labels six classes,…
- arXiv cs.AIresearchPRECOCIAL: Pretraining with Code Curriculums via Iterative Search for Accelerated Learning
arXiv:2610.24970v1 Announce Type: cross Abstract: Fully synthetic pretraining data generated by symbolic programs can bootstrap downstream training on naturalistic tasks, such as language modeling, but the generating pro…
- arXiv cs.AIresearchUtoMe: Observation-Uncertainty-Guided Token Merging for Weather Foundation Models
arXiv:2610.25001v1 Announce Type: cross Abstract: Weather transformers process dense reanalysis fields whose reliability varies across variables, locations, and weather regimes. Token merging can reduce computation, but…
- arXiv cs.AIresearchUpLoop: Upcycling Large Language Models with Gated Loop
arXiv:2610.25004v1 Announce Type: cross Abstract: Looped large language models trade parameter storage for recurrent computation, but most are trained from scratch. In practice, pretraining with looped depth is expensive…
- arXiv cs.AIresearchReTrace: Visual Backtracking for Efficient Multimodal Large Language Models
arXiv:2610.25005v1 Announce Type: cross Abstract: Multimodal Large Language Models (MLLMs) encode images into dense visual token sequences, creating substantial attention and KV-cache overhead. Existing visual token comp…
- arXiv cs.AIresearchIECLA: Interpretable Emotion Contribution Learning for Affective Image Editing
arXiv:2610.25015v1 Announce Type: cross Abstract: Affective image editing (AIE) aims to evoke a target emotion while preserving the content and structure of a source image. Existing methods improve emotional expression o…
- arXiv cs.AIagentsLLM Agents as Suppliers of Physical System Models: Calibration and Acceptance in Modelica
arXiv:2610.25019v1 Announce Type: cross Abstract: To procure a model of a device, a client hands a supplier a description, sometimes with recorded data or a target response, and accepts the model against this handover. W…
- arXiv cs.AIresearchSynergy-Aware Residual Flow Matching for Single-Cell Perturbation Prediction
arXiv:2610.25021v1 Announce Type: cross Abstract: Predicting single-cell responses to genetic and chemical perturbations is important for understanding regulatory mechanisms and prioritizing therapeutic interventions. Ex…
- arXiv cs.AIresearchOne Head Away from Language Confusion: Single Attention Heads Across Model Families
arXiv:2610.25026v1 Announce Type: cross Abstract: Large language models sometimes reply in an unexpected language, a failure known as language confusion. We ablate individual attention heads in 12 model checkpoints spann…
- arXiv cs.AIresearchHCFM: Helmholtz Component Flow Matching for Time Series Anomaly Detection
arXiv:2610.25059v1 Announce Type: cross Abstract: Flow Matching (FM) is an efficient simulation-free approach for training flow-based generative models, making it a promising foundation for scalable time-series anomaly d…
- arXiv cs.AIresearchPolicy Is Not Capability: Some Safety Benchmarks Measure Which Definition of "Unsafe" You Trained On
arXiv:2610.25060v1 Announce Type: cross Abstract: A guardrail classifier is reported as if unsafe were a property of text. It is not: it is a property of a policy, and the policy enters the model through its labels. We e…