AI news archive.
19,864 articles, newest first, from the outlets listed on the sources page.
- arXiv cs.AIresearchSAIL: Test-Time Scaling for In-Context Imitation Learning with VLM
arXiv:2603.08269v2 Announce Type: replace-cross Abstract: In-context imitation learning allows robots to acquire skills from demonstrations, yet one-shot trajectory generation remains fragile under environmental variatio…
- arXiv cs.AIresearchCCTU: A Benchmark for Tool Use under Complex Constraints
arXiv:2603.15309v2 Announce Type: replace-cross Abstract: Solving problems through tool use under explicit constraints constitutes a highly challenging yet unavoidable scenario for large language models (LLMs), requiring…
- arXiv cs.AIresearchFrom Noise to Signal: When Outliers Seed New Topics
arXiv:2603.18358v2 Announce Type: replace-cross Abstract: Outliers in dynamic topic modeling are typically treated as noise, yet we show that some can serve as early signals of emerging topics. We introduce a temporal ta…
- arXiv cs.AIresearchScaling Sim-to-Real VLA Reinforcement Learning with Generative 3D Worlds
arXiv:2603.18532v4 Announce Type: replace-cross Abstract: The strong performance of large vision-language models (VLMs) trained with reinforcement learning (RL) has motivated similar approaches for fine-tuning vision-lan…
- arXiv cs.AIresearchLearning Energy-Efficient Air--Ground Actuation for Hybrid Robots on Stair-Like Terrain
arXiv:2603.26687v2 Announce Type: replace-cross Abstract: Hybrid aerial--ground robots can use thrust to cross obstacles that impede wheel-driven motion, but deciding how much thrust to apply during contact remains chall…
- arXiv cs.AIresearchLG-HCC: Local Geometry-Aware Hierarchical Context Compression for 3D Gaussian Splatting
arXiv:2603.28431v4 Announce Type: replace-cross Abstract: Although 3D Gaussian Splatting (3DGS) enables high-fidelity real-time rendering, its prohibitive storage overhead severely hinders practical deployment. Recent an…
- arXiv cs.AIresearchWhat Makes Good Multilingual Reasoning? Disentangling Traces with Measurable Features
arXiv:2604.04720v2 Announce Type: replace-cross Abstract: Large Reasoning Models (LRMs) still exhibit large performance gaps between English and other languages, yet much current work assumes these gaps can be closed sim…
- arXiv cs.AIresearchNot All Forgetting Is Equal: Retention Dynamics in Fine-Tuned Image Classifiers
arXiv:2604.11508v3 Announce Type: replace-cross Abstract: Fine-tuning a pretrained classifier leaves some samples reliably learned and others cycling between correct and incorrect. Curriculum learning, data pruning and d…
- arXiv cs.AIresearchEnglish is Not All You Need: Systematically Exploring the Role of Multilinguality in LLM Post-Training
arXiv:2604.13286v2 Announce Type: replace-cross Abstract: Despite the widespread multilingual deployment of large language models, post-training pipelines remain predominantly English-centric, contributing to performance…
- arXiv cs.AIagentsRAT: RunAnyThing via Fully Automated Environment Configuration
arXiv:2604.23190v3 Announce Type: replace-cross Abstract: Automating repository-level software engineering tasks is a foundational challenge for autonomous code agents, largely due to the difficulty of configuring execut…
- arXiv cs.AIresearchLearning from Noisy Preferences: A Semi-Supervised Learning Approach to Direct Preference Optimization
arXiv:2604.24952v3 Announce Type: replace-cross Abstract: Human visual preferences are inherently multi-dimensional, encompassing aesthetics, detail fidelity, and semantic alignment. However, existing datasets provide on…
- arXiv cs.AIresearchUsing LLMs in Software Design: An Empirical Study of GitHub and A Practitioner Survey
arXiv:2605.01392v2 Announce Type: replace-cross Abstract: Recent advancements in Large Language Models (LLMs) have demonstrated significant potential across software engineering tasks, including software design, an area…
- arXiv cs.AIresearchProbe-Geometry Alignment: Erasing the Cross-Sequence Memorization Signature Below Chance
arXiv:2605.01699v4 Announce Type: replace-cross Abstract: Recent attacks show that behavioural unlearning of large language models leaves internal traces recoverable by adversarial probes. We characterise where this rete…
- arXiv cs.AIagentsAPIOT: Autonomous Vulnerability Management Across Bare-Metal Industrial OT Networks
arXiv:2605.02346v2 Announce Type: replace-cross Abstract: Operational technology (OT) devices run safety-critical physical processes, yet their security testing remains manual and expert-intensive. Autonomous security ag…
- arXiv cs.AIresearchRelational Retrieval: Leveraging Known-Novel Interactions for Generalized Category Discovery
arXiv:2605.09420v3 Announce Type: replace-cross Abstract: In this study, we tackle Generalized Category Discovery (GCD) via a Relational Retrieval perspective, explicitly coupling labeled and unlabeled data through bidir…
- arXiv cs.AIagentsTraining-Free Refusal of MCP Exploits via Retrieval-Augmented Generation
arXiv:2605.11217v2 Announce Type: replace-cross Abstract: The model context protocol (MCP) has been widely adopted as an open standard enabling the seamless integration of generative AI agents. However, while LLM guardra…
- arXiv cs.AIagentsgwBenchmarks: Stress-Testing LLM Agents on High-Precision Gravitational Wave Astronomy
arXiv:2605.11269v2 Announce Type: replace-cross Abstract: Modern gravitational wave astronomy relies on modeling tasks that often require months of graduate-level effort, including building fast waveform surrogates from…
- arXiv cs.AIagentsDiscovery of Interpretable Surrogates via Agentic AI: Application to Gravitational Waves
arXiv:2605.11280v2 Announce Type: replace-cross Abstract: Fast surrogate models for expensive simulations are now essential across the sciences, yet they typically operate as black boxes. We present \texttt{GWAgent}, a l…
- arXiv cs.AIresearchTASTE: A Designer-Annotated Multi-Dimensional Preference Dataset for AI-Generated Graphic Design
arXiv:2605.20731v3 Announce Type: replace-cross Abstract: Text-to-image models now generate graphic design at production scale, yet their supervision still comes primarily from photo-style preference datasets with a sing…
- arXiv cs.AIresearchAction with Visual Primitives
arXiv:2605.22183v4 Announce Type: replace-cross Abstract: Vision-Language-Action (VLA) models have emerged as a promising paradigm for generalist robotic manipulation. A common design in current architectures maps langua…
- arXiv cs.AIresearchFinite-Particle Convergence Rates for Conservative and Non-Conservative Drifting Models
arXiv:2605.22795v3 Announce Type: replace-cross Abstract: We analyze finite-particle drifting models for one-step generative modeling. For a conservative velocity given by the difference of the kernel-smoothed data and m…
- arXiv cs.AIresearchReflex: Reinforcement Learning with Reflection Symmetry Exploitation in State-Based Continuous Control
arXiv:2605.23415v3 Announce Type: replace-cross Abstract: Reinforcement learning has long struggled with poor sample efficiency. One promising approach to mitigate this problem is leveraging group-invariant Markov Decisi…
- arXiv cs.AIresearchSiST-GNN: Simultaneous Spatial-Temporal Message Passing for Dynamic Graph Representation Learning
arXiv:2605.25548v2 Announce Type: replace-cross Abstract: Dynamic graph neural networks (DGNNs) that operate on snapshot sequences typically fall into one of two categories. \emph{Temporal-first} approaches build per-nod…
- arXiv cs.AIagentsCan LLMs Time Travel? Enhancing Temporal Consistency in Legal Agentic Search through Reinforcement Learning
arXiv:2605.25920v2 Announce Type: replace-cross Abstract: While large language models (LLMs) augmented with agentic search capabilities show promise for legal reasoning, they overlook a fundamental constraint that applic…
- arXiv cs.AIresearchDDGAD: Disagreement-Driven Graph Anomaly Detection via Adapt-Then-Combine
arXiv:2605.26446v3 Announce Type: replace-cross Abstract: Graph anomaly detection (GAD) commonly relies on message passing to jointly encode node attributes and neighborhood context. However, once the two are mixed, an a…
- arXiv cs.AIresearchSUPREME: A Multi-GPU Framework for Reproducible Image Unlearning Method Evaluation
arXiv:2606.00380v3 Announce Type: replace-cross Abstract: Machine unlearning removes the influence of specific training data from a trained model without retraining it from scratch. Evaluating an unlearning method requir…
- arXiv cs.AIagentsA Taxonomy of Runtime Faults in Model Context Protocol Servers
arXiv:2606.05339v2 Announce Type: replace-cross Abstract: MCP (Model Context Protocol) enables LLMs (Large Language Models) to interact with external tools and data sources via a standardized protocol. Its rapid adoption…
- arXiv cs.AIresearchvla.cpp: A Unified Inference Runtime for Vision-Language-Action Models
arXiv:2606.08094v2 Announce Type: replace-cross Abstract: Deploying vision--language--action (VLA) models on robots requires adapting model-specific inference pipelines to heterogeneous processors and limited onboard mem…
- arXiv cs.AIresearchHiLo-Token: Input-Adaptive High-Low Frequency Token Compression for Efficient Image Editing
arXiv:2606.13898v3 Announce Type: replace-cross Abstract: Creative image editing tools, such as Adobe Photoshop's Remove and Generative Fill buttons, are central to everyday customer use and account for a major share of…
- arXiv cs.AIresearchAdaMame: A Training Recipe for Adaptive Multilingual Reasoning
arXiv:2606.15080v2 Announce Type: replace-cross Abstract: While Large Reasoning Models (LRMs) show strong performance in English, they often fail to reason in the language of the query, a phenomenon known as language col…
- arXiv cs.AIagentsTransformer-Based Warm-Starting for Feasible and Optimal Terminal Approach to Tumbling Objects with Space Manipulators
arXiv:2606.17317v2 Announce Type: replace-cross Abstract: Autonomous capture of a tumbling object with a space manipulator requires trajectory generation under real-time onboard constraints. However, coupled bus-arm dyna…
- arXiv cs.AIresearchA Red-Team Study of Anthropic Fable 5 & Opus 4.8 Models
arXiv:2606.18193v2 Announce Type: replace-cross Abstract: We evaluate the adversarial robustness of three frontier large language models (LLMs) developed by Anthropic, Opus 4.8, Fable 5 and its successor Fable 5.1, again…
- arXiv cs.AIagentsConnect the Dots: Training LLMs for Long-Lifecycle Agents with Cross-Domain Generalization Via Reinforcement Learning
arXiv:2606.20002v2 Announce Type: replace-cross Abstract: This work presents a general framework for training large language models (LLMs) to "Connect the Dots" (CoD), a meta-capability required by long-lifecycle agents:…
- arXiv cs.AIresearchThe Metanym Game: An LLM Benchmark Without Ground Truth That Rises With the Models It Measures
arXiv:2606.21008v4 Announce Type: replace-cross Abstract: We introduce a benchmark that is fully self-contained, needs no ground truth, and rises with the models it measures. Language models compete at making analogies a…
- arXiv cs.AIresearchAdaReP:Adaptive Re-Planning under Model Mismatch for Neural World-Model Predictive Control
arXiv:2606.23079v2 Announce Type: replace-cross Abstract: Neural world models coupled with model predictive control (MPC) replan at every environment step to bound accumulated prediction error, but this incurs substantia…
- arXiv cs.AIresearchInSight: Self-Guided Skill Acquisition via Steerable VLAs
arXiv:2606.24884v2 Announce Type: replace-cross Abstract: Vision-language-action (VLA) models excel at robot manipulation via imitation learning, but adapting them to new tasks often requires additional human demonstrati…
- arXiv cs.AIresearchLearning to Fold: prizewinning solution at LeHome Challenge 2026 (1st place online, 2nd offline)
arXiv:2606.27163v3 Announce Type: replace-cross Abstract: I describe my solution to the LeHome Challenge 2026, an ICRA 2026 competition on bimanual garment folding. The system placed 1st of 62 teams in the online (simula…
- arXiv cs.AIresearchHow Do LLMs Cite? A Mechanistic Interpretation of Attribution in Retrieval-Augmented Generation
arXiv:2606.28358v2 Announce Type: replace-cross Abstract: Retrieval-Augmented Generation (RAG) aims to enhance the trustworthiness of Large Language Models (LLMs) by grounding their outputs in external documents, often u…
- arXiv cs.AIresearchFew-class Fidelity: Evaluating Explanations of Real-conditions CNN classifiers with Optimized Perturbations
arXiv:2606.28391v2 Announce Type: replace-cross Abstract: The wide use of Convolutional Neural Networks (CNN) in numerous domains and real-world classification applications is justified by their high precision and automa…
- arXiv cs.AIresearchOut-of-Distribution Generalization of Risk Aversion in Language Models
arXiv:2607.02755v2 Announce Type: replace-cross Abstract: Training AIs to be risk-averse in resources could offer a failsafe in the event that AIs turn out misaligned. Misaligned but risk-averse AIs would tend to prefer…
- arXiv cs.AIresearchWhy3-py: A Tool for Formal Verification of Hypothesis Testing and Meta-Analysis in Python
arXiv:2607.03951v2 Announce Type: replace-cross Abstract: The reproducibility crisis in scientific research has received widespread recognition, thereby increasing the importance of meta-analyses that integrate statistic…
- arXiv cs.AIresearchHALO-WA: Hybrid-Attention Latent-Guided Online Reinforcement Learning for World-Action Models
arXiv:2607.04265v2 Announce Type: replace-cross Abstract: World-action (WA) models can generate long-horizon action chunks for general-purpose robotic manipulation, but they remain vulnerable to calibration, perception,…
- arXiv cs.AIresearchRiemannian Geometry for Pre-trained Language Model Embeddings
arXiv:2607.07047v3 Announce Type: replace-cross Abstract: Understanding the geometric structure of pre-trained language model embeddings matters for interpretability and safety. We ask whether sentence-level classificati…
- arXiv cs.AIresearchSee like a Robot: Robot-Centric Pointmaps for VLA Models
arXiv:2607.11498v2 Announce Type: replace-cross Abstract: Vision-language-action (VLA) models require 3D spatial reasoning, yet RGB observations encode robot-object geometry only implicitly. Lifting depth with camera int…
- arXiv cs.AIresearchGreedy Volume Maximization of Gradient Embeddings for Long-Tailed Frame-Level Bioacoustic Active Learning
arXiv:2607.13555v2 Announce Type: replace-cross Abstract: Bioacoustic call-type classification relies on costly expert annotation. Active learning can reduce this burden by selecting a small batch of segments for expert…
- arXiv cs.AIresearchInformation-Directed Sampling for Causal Bandits
arXiv:2607.15577v2 Announce Type: replace-cross Abstract: Causal bandits exploit structural relationships among variables to share information across interventions and accelerate the identification of high-reward decisio…
- arXiv cs.AIresearchCANDOR: Chance-Calibrated Neighborhood Discordance in Frozen Encoders for Medical Imaging
arXiv:2607.18451v4 Announce Type: replace-cross Abstract: In medical imaging, one frozen foundation encoder is often reused for many tasks. The encoder is usually chosen by the area under the receiver operating character…
- arXiv cs.AIresearchActive Inference as a Convex Markov Decision Process
arXiv:2607.20152v3 Announce Type: replace-cross Abstract: Active Inference (AIF) frames adaptive behavior as the minimization of expected free energy (EFE), combining epistemic and pragmatic objectives within a single va…
- arXiv cs.AIresearchFakeIDet3-DB: Refining Digital Attacks and Patch Extraction for Secure ID Benchmarking
arXiv:2607.26641v2 Announce Type: replace-cross Abstract: Identity document (ID) authentication relies on the structural integrity of complex, high-frequency security patterns. However, advanced Generative AI models can…
- arXiv cs.AIresearchGraRe: Grasp Candidate Re-Ranking for Frozen 6-DoF Grasp Detectors
arXiv:2608.00946v3 Announce Type: replace-cross Abstract: Existing 6-DoF grasp detectors typically rank grasp candidates by detector confidence. However, our analysis on GraspNet-1Billion shows that detector confidence i…