AI news archive.
19,864 articles, newest first, from the outlets listed on the sources page.
- arXiv cs.AIresearchDeepArrhythmia: Segment-Contextualized ECG Arrhythmia Classification via Selective Evidence Acquisition
arXiv:2605.16441v2 Announce Type: replace-cross Abstract: Beat-level Electrocardiography (ECG) arrhythmia detection aims to assign an arrhythmia class to each beat in a recording, yet many existing systems treat beats as…
- arXiv cs.AIresearchFidelity Probes for Specification--Code Alignment
arXiv:2605.17246v2 Announce Type: replace-cross Abstract: Software modernization often relies on natural-language specifications recovered from an existing implementation. Incorrect or missing requirements can lead to de…
- arXiv cs.AIagentsContractBench: Can LLM Agents Preserve Observation Contracts?
arXiv:2605.17281v2 Announce Type: replace-cross Abstract: Tool-augmented LLM agents call APIs whose intermediate outputs, such as presigned URLs, session tokens, and OAuth state parameters, are observation contracts: art…
- arXiv cs.AIresearchDCFold: Efficient Protein Structure Generation with Single Forward Pass
arXiv:2605.17899v2 Announce Type: replace-cross Abstract: AlphaFold3 introduces a diffusion-based architecture that elevates protein structure prediction to all-atom resolution with improved accuracy. This state-of-the-a…
- arXiv cs.AIresearchConcise and Logically Consistent Conformal Sets for Neuro-Symbolic Concept-Based Models
arXiv:2605.18202v3 Announce Type: replace-cross Abstract: Neuro-Symbolic Concept-based Models (NeSy-CBMs) are a family of architectures that integrate neural networks with symbolic reasoning for enhanced reliability in h…
- arXiv cs.AIagentsOmniGUI: Benchmarking GUI Agents in Omni-Modal Smartphone Environments
arXiv:2605.18758v2 Announce Type: replace-cross Abstract: Current benchmarks for graphical user interface (GUI) agents predominantly rely on static screenshots. However, real-world smartphone interaction routinely requir…
- arXiv cs.AIresearchWhen Does Equivariance Help? Canonical Alignment in Neural Fluid Surrogates
arXiv:2605.18816v2 Announce Type: replace-cross Abstract: Neural surrogates can accelerate computational fluid dynamics (CFD) simulations by orders of magnitude, but practical deployment in engineering and healthcare app…
- arXiv cs.AIresearchMLLMs Know When Before Speaking: Revealing and Recovering Temporal Grounding via Attention Cues
arXiv:2605.21954v2 Announce Type: replace-cross Abstract: Video temporal grounding (VTG), which localizes the start and end times of a queried event in an untrimmed video, is a key test of whether multimodal large langua…
- arXiv cs.AIresearchLearning Spatiotemporal Sensitivity in Video LLMs via Counterfactual Reinforcement Learning
arXiv:2605.21988v2 Announce Type: replace-cross Abstract: Video large language models (Video LLMs) can achieve strong video-QA accuracy without reliably tracking spatiotemporal dynamics. A model may answer a motion quest…
- arXiv cs.AIagentsDeferMem: Query-Time Evidence Distillation via Reinforcement Learning for Long-Term Agent Memory
arXiv:2605.22411v2 Announce Type: replace-cross Abstract: Large language model (LLM) agents still struggle to effectively use long-term memory, with answer-supporting evidence often scattered across long conversational h…
- arXiv cs.AIresearchAnytime Training with Schedule-Free Spectral Optimization
arXiv:2605.23061v2 Announce Type: replace-cross Abstract: Standard neural network training relies on learning-rate schedules tied to a fixed horizon, leading to strong path dependence and costly re-tuning as data availab…
- arXiv cs.AIresearchXWind: A Cross-site Router for Large Language Model Inference Serving at Renewable Energy Farms
arXiv:2605.23348v3 Announce Type: replace-cross Abstract: AI power demand is growing at an unprecedented rate while power grids are often ailing and struggle to keep up. Grid expansion comes with high capital expenditure…
- arXiv cs.AIresearchOne-Forcing: Towards Stable One-Step Autoregressive Video Generation
arXiv:2605.23458v2 Announce Type: replace-cross Abstract: Recent advances in autoregressive diffusion-based video generation have substantially improved the quality of real-time video synthesis. However, most existing me…
- arXiv cs.AIagentsPhoneWorld: From Real-App Trajectories to Dynamic and Verifiable Environments for Phone-Use Agents
arXiv:2605.29486v3 Announce Type: replace-cross Abstract: Real applications provide the training setting closest to phone-agent deployment, but are difficult to reset, scale safely, and verify programmatically. Static sc…
- arXiv cs.AIresearchEviLink: Multi-Path Schema Linking with Uncertainty-Guided Evidence Acquisition for Large-Scale Text-to-SQL
arXiv:2605.29670v2 Announce Type: replace-cross Abstract: Schema linking is a difficult and important step in large-scale Text-to-SQL, where systems must identify a compact yet sufficient schema context from large and am…
- arXiv cs.AIresearchMulti-Legal-Bench: When the Answer Is in the Input. Label Leakage in Legal Benchmarks Built from Court Registries
arXiv:2605.29738v3 Announce Type: replace-cross Abstract: Court registries publish millions of decisions with structured metadata, which makes them an attractive source of labelled legal benchmarks: the court type, the f…
- arXiv cs.AIagentsMemPoison: Bypassing Selective Memory Mechanisms to Plant Backdoors in LLM Agents
arXiv:2605.29960v2 Announce Type: replace-cross Abstract: Large language model (LLM) agents increasingly leverage long-term memory to support persistent and autonomous task execution. However, this capability also introd…
- arXiv cs.AIresearchNo More K-means: Single-Stage Sparse Coding for Efficient Multi-Vector Retrieval
arXiv:2605.30120v4 Announce Type: replace-cross Abstract: Multi-vector retrieval (MVR) models, exemplified by ColBERT, have established new benchmarks in retrieval accuracy by preserving fine-grained token-level interact…
- arXiv cs.AIresearchShared Doubt: Zero-Shot Cross-Lingual Confidence Estimation for Language Models
arXiv:2605.31220v3 Announce Type: replace-cross Abstract: Confidence estimation (CE), i.e. quantifying the reliability of a model's prediction, has attracted great interest in the context of large language models (LLMs).…
- arXiv cs.AIresearchBitsMoE: Cost-Aware Bit Allocation in Spectral Space for MoE LLM Quantization
arXiv:2606.00079v2 Announce Type: replace-cross Abstract: Mixture-of-Experts (MoE) large language models incur substantial memory costs due to their large expert parameter counts. Mixed-precision quantization reduces the…
- arXiv cs.AIresearchCan Predicted Dynamics Exist in the Physical World?
arXiv:2606.00089v3 Announce Type: replace-cross Abstract: Can learned state-action proposals exist in the physical world? Before executing a proposed action sequence, a robot can inspect empirical variation and disagreem…
- arXiv cs.AIresearchContext-aware tokenization for Cross-subject Emotion Decoding from EEG
arXiv:2606.00884v2 Announce Type: replace-cross Abstract: In cross-subject EEG emotion decoding, neighboring windows can inform the representation of a target window, but they contain both background variation and sustai…
- arXiv cs.AIresearchKnowledge-Intensive Video Generation
arXiv:2606.01285v2 Announce Type: replace-cross Abstract: Text-to-video generation has advanced rapidly in visual quality, but remains under-evaluated for factuality and practical usefulness. We introduce knowledge-inten…
- arXiv cs.AIresearchQuantifying and Mitigating Domain Shift in Peach Leaf Damage Classification: Attention Mechanisms and Fine-Tuning Strategies
arXiv:2606.02045v3 Announce Type: replace-cross Abstract: Deep learning models for crop damage assessment are typically trained and validated on curated public imagery, yet their behaviour when deployed in real orchards…
- arXiv cs.AIresearchConTraIRL: Factorized Contrastive Abstractions for Transferable IRL
arXiv:2606.03017v2 Announce Type: replace-cross Abstract: Reward transfer in Inverse Reinforcement Learning (IRL) is unreliable when policies must generalize to unseen combinations of environment dynamics and task goals.…
- arXiv cs.AIresearchFrom 'What' to 'How' and 'Why': Sharing LLM-Generated Retrospective Summaries of Older Adults' Passive Tracking Data with Remote Family Members
arXiv:2606.03876v2 Announce Type: replace-cross Abstract: With the growing prevalence of modern ubiquitous computing technologies, multi-modal tracking systems hold promise for providing timely awareness and reassurance…
- arXiv cs.AIresearchChannel-Preserving Representation Alignment for EEG-to-Music Reconstruction
arXiv:2606.04040v2 Announce Type: replace-cross Abstract: Reconstructing naturalistic music from EEG requires extracting music-specific information from weak signals distributed across electrodes. Existing spectrogram re…
- arXiv cs.AIresearchLarge Language Models Hack Rewards, and Society
arXiv:2606.04075v3 Announce Type: replace-cross Abstract: Reinforcement learning (RL) has become a dominant post-training paradigm, enabling large language models (LLMs) to learn from rewards. We observe that societal re…
- arXiv cs.AIresearchDual Advantage Fields
arXiv:2606.04188v2 Announce Type: replace-cross Abstract: Offline goal-conditioned reinforcement learning requires both long-horizon reachability estimates and local action comparisons. Dual goal representations provide…
- arXiv cs.AIagentsVault: One-Step Latent Generation with Positive-Anchored Rewards for Autonomous Driving
arXiv:2606.06219v2 Announce Type: replace-cross Abstract: End-to-end autonomous driving must balance multimodal maneuver generation against real-time inference constraints. Diffusion planners capture diverse behaviors, b…
- arXiv cs.AIresearchHearing the Unspoken: Language Model Priors for Acoustic Adversarial Attacks
arXiv:2606.06833v3 Announce Type: replace-cross Abstract: Automatic Speech Recognition (ASR) systems operating in real-time settings must process acoustic input under strict temporal constraints, where transcription deci…
- arXiv cs.AIresearchDefending Against Malicious Finetuning by Scaling Train-time Adversarial Attacks
arXiv:2606.07970v2 Announce Type: replace-cross Abstract: Malicious finetuning attacks pose a major safety threat against open-weight large language models (LLMs). However, existing alignment-stage defenses provide limit…
- arXiv cs.AIresearchSci-Rho: A Multilingual Visually-Grounded Symbolic Benchmark for STEM Problems
arXiv:2606.08034v2 Announce Type: replace-cross Abstract: Symbolic benchmarks have emerged as a key approach to assess model robustness under minor modifications to STEM-related questions. However, existing symbolic benc…
- arXiv cs.AIagentsAgentic Search for Counterfactual Recourse under Fixed LLM Budgets
arXiv:2606.08696v2 Announce Type: replace-cross Abstract: Counterfactual recourse aims to provide actionable feature changes that would alter an unfavorable decision made by a predictive model. In practice, affected indi…
- arXiv cs.AIagentsAgentic Hybrid RAG for Evidence-Grounded Muon Collider Analysis
arXiv:2606.10381v2 Announce Type: replace-cross Abstract: Muon collider research spans accelerator physics, detector instrumentation, and high-energy phenomenology, with relevant evidence scattered across a rapidly expan…
- arXiv cs.AIagentsLearning Coordinated Preference for Multi-Objective Multi-Agent Reinforcement Learning
arXiv:2606.14693v2 Announce Type: replace-cross Abstract: Cooperative multi-objective multi-agent reinforcement learning (MOMARL) models team decision making under multiple, potentially conflicting objectives. In this se…
- arXiv cs.AIagentsKnowledge-Based Zero-Replay Debugging of Multi-Agent LLM Traces
arXiv:2606.14805v2 Announce Type: replace-cross Abstract: Reliable operation of multi-agent large language model (LLM) systems depends on debugging long execution traces, where the few causally decisive events are buried…
- arXiv cs.AIagentsAutoDojo: A Generative Benchmark for Evaluating Prompt Injection Defenses in LLM Agents
arXiv:2606.15057v3 Announce Type: replace-cross Abstract: Indirect prompt injection (IPI) is a major security threat to LLM-powered agents. Thus, a growing body of work has proposed a variety of defensive approaches agai…
- arXiv cs.AIresearchStarOR: Synergizing Tree Search and Test-Time Reinforcement Learning for Optimization Modeling
arXiv:2606.15197v3 Announce Type: replace-cross Abstract: Optimization modeling is inherently hierarchical, requiring a precise sequence of symbolic commitments. Traditional learning-based automated optimization modeling…
- arXiv cs.AIresearchWasserstein Convergence of ODE-Based Samplers in Decentralized Diffusion Model via Velocity Field Decomposition
arXiv:2606.15835v2 Announce Type: replace-cross Abstract: Diffusion models have achieved impressive empirical success in generative tasks, and their convergence theory is now relatively well understood. Motivated by priv…
- arXiv cs.AIresearchWhat Should a Streaming Video Model Remember?
arXiv:2606.16353v2 Announce Type: replace-cross Abstract: Streaming video understanding models must answer queries at any moment during an ongoing stream, using only what they have observed so far and under fixed memory…
- arXiv cs.AIresearchWhen Does Depth Matter For In-Context Learning? Adaptive Inference in Deep Transformers
arXiv:2606.16694v2 Announce Type: replace-cross Abstract: Transformers perform computations through many successive attention and feedforward blocks, allowing them to learn complex correlations between a large collection…
- arXiv cs.AIresearchDRIFT: Data Selection for LLM Instruction Tuning via On-Policy Attribution
arXiv:2606.18307v2 Announce Type: replace-cross Abstract: Data selection for instruction tuning is usually studied for efficiency, reaching strong performance with a fraction of the training data. We ask whether data sel…
- arXiv cs.AIagentsGuava: Distilling Frontier VLMs into a Compact Agent through a Robotic Manipulation Harness
arXiv:2606.18363v3 Announce Type: replace-cross Abstract: Language models trained on large-scale vision-language data have demonstrated strong potential for embodied agents. Harnessing models through embodied tools use o…
- arXiv cs.AIresearchWhen to Commit and When to Defer: Maturing Markov Decision Processes under Refining Information and Expiring Opportunities
arXiv:2606.18820v2 Announce Type: replace-cross Abstract: Sequential decisions often become better informed as action opportunities expire. We introduce Maturing Markov Decision Processes (MMDPs), a structured subclass o…
- arXiv cs.AIresearchOneCanvas: 3D Scene Understanding via Panoramic Reprojection
arXiv:2606.19253v2 Announce Type: replace-cross Abstract: Existing approaches to 3D scene understanding in Vision-Language Models (VLMs) either rely on complex, model-specific geometry encoders or large training budgets…
- arXiv cs.AIagentsCRAX: Fast Safe Reinforcement Learning Benchmarking
arXiv:2606.20376v4 Announce Type: replace-cross Abstract: Safety is a core concern for deploying reinforcement learning (RL) agents in real-world domains such as robotics and autonomous driving. While benchmarks have bee…
- arXiv cs.AIresearchOnly Ask What You Don't Know: Grounded Delta Planning for Efficient Multi-step RAG
arXiv:2606.22681v2 Announce Type: replace-cross Abstract: Multi-hop question answering remains challenging for Retrieval-Augmented Generation (RAG) because existing approaches either propagate errors across iterative ret…
- arXiv cs.AIresearchRethinking Object-Centric Representations for Video Dynamics Modeling
arXiv:2606.23436v2 Announce Type: replace-cross Abstract: Learning to decompose videos into persistent objects is a fundamental challenge in unsupervised object-centric representation learning. Despite recent progress, e…
- arXiv cs.AIresearchJuZhou 1.0 Technical Report: The First Edge-Native Text-to-Image Foundation Model Trained Entirely on China-Developed AI Accelerators
arXiv:2606.28421v3 Announce Type: replace-cross Abstract: Text-to-image (T2I) diffusion models typically require substantial computational resources and cloud infrastructure, posing significant challenges for edge deploy…