AI news archive.
19,864 articles, newest first, from the outlets listed on the sources page.
- arXiv cs.AIresearchMuon Dynamics as a Spectral Wasserstein Flow
arXiv:2604.04891v3 Announce Type: replace-cross Abstract: Gradient normalization can stabilize deep-learning optimization, and spectral normalizations are especially natural for matrix-shaped parameter blocks; Muon is th…
- arXiv cs.AIagentsFoundations for Investigations of Agentic AI Systems from the Forensic Analysis of OpenClaw
arXiv:2604.05589v2 Announce Type: replace-cross Abstract: Agentic AI systems are increasingly deployed as personal assistants and virtual employees, and are likely to become a common object of digital investigations and…
- arXiv cs.AIresearchFrom Scientific Crop Imagery to Agronomic Reasoning: A Multimodal LLM Benchmark for Plant Phenotyping
arXiv:2604.09907v2 Announce Type: replace-cross Abstract: High-throughput, effective and comprehensive phenotyping is a critical prerequisite for crop improvement. While phenotypic analysis was traditionally performed ma…
- arXiv cs.AIresearchICAT: Incident-Case-Grounded Adaptive Testing for Physical-Risk Prediction in Embodied World Models
arXiv:2604.16405v2 Announce Type: replace-cross Abstract: Reference-image-conditioned video generators are increasingly used as neural simulators for embodied planning and policy learning, yet their ability to anticipate…
- arXiv cs.AIagentsLLM as a Tool, Not an Agent: Code-Mined Tree Transformations for Neural Architecture Search
arXiv:2604.16555v2 Announce Type: replace-cross Abstract: Neural Architecture Search (NAS) aims to automatically discover high-performing deep neural network (DNN) architectures. However, conventional algorithm-driven NA…
- arXiv cs.AIresearchVoronoi-guided Bilateral 2D Gaussian Splatting for Arbitrary-Scale Hyperspectral Image Super-Resolution
arXiv:2604.17727v2 Announce Type: replace-cross Abstract: Most existing hyperspectral image super-resolution methods require modifications for different scales, limiting their flexibility in arbitrary-scale reconstructio…
- arXiv cs.AIresearchLatent Abstraction for Retrieval-Augmented Generation
arXiv:2604.17866v4 Announce Type: replace-cross Abstract: Retrieval-Augmented Generation (RAG) has become a standard approach for enhancing large language models (LLMs) with external knowledge, mitigating hallucinations,…
- arXiv cs.AIresearchA neural operator framework for data-driven discovery of stability and receptivity in physical systems
arXiv:2604.19465v4 Announce Type: replace-cross Abstract: Understanding how complex systems respond to perturbations, such as whether they will remain stable or what their most sensitive patterns are, is a fundamental ch…
- arXiv cs.AIresearchCyberCane: a privacy-bounded neuro-symbolic retrieval framework for phishing detection under distribution shift
arXiv:2604.23563v2 Announce Type: replace-cross Abstract: Organizations usually calibrate phishing detectors on public corpora, because privacy rules make their own labeled legitimate mail hard to collect. This practice…
- arXiv cs.AIresearchEfficient Training on Multiple Consumer GPUs with RoundPipe
arXiv:2604.27085v2 Announce Type: replace-cross Abstract: Fine-tuning Large Language Models (LLMs) on consumer-grade GPUs is highly cost-effective, yet constrained by limited GPU memory and slow PCIe interconnects. Pipel…
- arXiv cs.AIresearchForager: a lightweight testbed for continual learning with partial observability in RL
arXiv:2605.01131v2 Announce Type: replace-cross Abstract: In continual reinforcement learning (CRL), good performance requires never-ending learning, acting, and exploration in a big, partially observable world. Most CRL…
- arXiv cs.AIresearchThe Causal Description Gap: Information-Theoretic Separations Across Pearl's Hierarchy
arXiv:2605.02177v2 Announce Type: replace-cross Abstract: Pearl's causal hierarchy shows that observational, interventional, and counterfactual queries are qualitatively distinct. We ask a quantitative version of this qu…
- arXiv cs.AIresearchMultilingual Safety Alignment via Self-Distillation
arXiv:2605.02971v3 Announce Type: replace-cross Abstract: Large language models (LLMs) exhibit severe multilingual safety misalignment: they possess strong safeguards in high-resource languages but remain highly vulnerab…
- arXiv cs.AIresearchCoral: Cost-Efficient Multi-LLM Serving over Heterogeneous Cloud GPUs
arXiv:2605.04357v2 Announce Type: replace-cross Abstract: The landscape of large language models (LLMs) has become increasingly fragmented, with no single model dominating the field. Meanwhile, cloud providers offer a di…
- arXiv cs.AIresearchDiversity-Aware Active Learning Builds Materials Datasets for Current and Future Objectives
arXiv:2605.05104v2 Announce Type: replace-cross Abstract: Materials science data collection can be expensive, making dataset reuse and long-term utility important for future discovery. In practice, data collection often…
- arXiv cs.AIresearchBridging Generation and Training: A Systematic Review of Quality Issues in LLMs for Code
arXiv:2605.05267v2 Announce Type: replace-cross Abstract: Large language models (LLMs) frequently generate defective code, ranging from logical bugs to security vulnerabilities. Training-data quality is one contributor t…
- arXiv cs.AIresearchVisual Text Compression as Measure Transport
arXiv:2605.06708v2 Announce Type: replace-cross Abstract: Visual text compression (VTC) promises efficient long-context processing by rendering text into an image and re-encoding it with a vision-language model, often pr…
- arXiv cs.AIagentsBioProVLA-Agent: An Affordable, Protocol-Driven, Vision-Enhanced VLA-Enabled Embodied Multi-Agent System with Closed-Loop-Capable Reasoning for Biological Laboratory Manipulation
arXiv:2605.07306v4 Announce Type: replace-cross Abstract: Biological laboratory automation can reduce repetitive manual work and improve reproducibility, but reliable embodied execution in wet-lab environments remains ch…
- arXiv cs.AIagentsSafe, or Simply Incapable? Rethinking Safety Evaluation for Phone-Use Agents
arXiv:2605.07630v2 Announce Type: replace-cross Abstract: When a phone-use agent avoids harm, does that show safety, or simply inability to act? Existing evaluations often cannot tell. A harmful outcome may be avoided be…
- arXiv cs.AIresearchRuPLaR : Efficient Latent Compression of LLM Reasoning Chains with Rule-Based Priors From Multi-Step to One-Step
arXiv:2605.09346v2 Announce Type: replace-cross Abstract: The Chain-of-Thought (CoT) paradigm, while enhancing the interpretability of Large Language Models (LLMs), is constrained by the inefficiencies and expressive lim…
- arXiv cs.AIresearchContinuous Latent Contexts Enable Efficient Online Learning in Transformers
arXiv:2605.09867v2 Announce Type: replace-cross Abstract: Large language models (LLMs) exhibit a strong capacity for in-context learning: Given labeled examples, they can generate good predictions without parameter updat…
- arXiv cs.AIagentsSequential Behavioral Watermarking for LLM Agents
arXiv:2605.11036v2 Announce Type: replace-cross Abstract: LLM-based agents act through sequences of executable decisions, but their trajectories provide little evidence of which agent or policy produced them, making prov…
- arXiv cs.AIresearchGradient-Free Noise Optimization for Reward Alignment in Generative Models
arXiv:2605.11347v3 Announce Type: replace-cross Abstract: Existing reward alignment methods for diffusion and flow models rely on multi-step stochastic trajectories, making them difficult to extend to deterministic gener…
- arXiv cs.AIresearchHuman-AI Productivity Paradoxes: Modeling the Interplay of Skill, Effort, and AI Assistance
arXiv:2605.11350v2 Announce Type: replace-cross Abstract: Generative Artificial Intelligence (AI) tools are rapidly adopted in the workplace and in education, yet the empirical evidence on AI's impact remains mixed acros…
- arXiv cs.AIagentsMobius Injection: From One-Shot Prompt Injection to Sustained Resource Exhaustion in AI Agent Infrastructure
arXiv:2605.11442v2 Announce Type: replace-cross Abstract: Large Language Model (LLM) agents have emerged as key intermediaries, orchestrating complex interactions between human users and a wide range of digital services…
- arXiv cs.AIresearchLet the Batch Decide, On- or Off-Policy: Effective Sample Size for RL Post-Training
arXiv:2605.12380v2 Announce Type: replace-cross Abstract: Reinforcement learning (RL) is structurally harder than supervised learning because the policy changes the data distribution it learns from. The resulting fragili…
- arXiv cs.AIagentsAgentic Reverse Engineering: From I/O to Code with Discovery Agent
arXiv:2605.15334v2 Announce Type: replace-cross Abstract: The automatic synthesis of a program from any form of specification is regarded as a holy grail of computer science. Fueled by LLMs, NL2Code has achieved tremendo…
- arXiv cs.AIresearchA Measure-Theoretic Analysis of Reasoning in Transformers: Structural Generalization and Approximation Limits
arXiv:2605.19944v2 Announce Type: replace-cross Abstract: Scaling laws for reasoning in large language models (LLMs) are well documented, but little theory explains their out-of-distribution (OOD) generalization. We form…
- arXiv cs.AIresearchYour Embedding Model is SMARTer Than You Think
arXiv:2605.24938v2 Announce Type: replace-cross Abstract: Multimodal retrieval relies heavily on single-vector retrievers, which compress rich, sequential token sequences into one single global representation. While effi…
- arXiv cs.AIresearchAI estimation of partition functions with the PULSE method for the thermodynamic properties of disordered compounds
arXiv:2605.28594v2 Announce Type: replace-cross Abstract: Predicting the thermodynamic properties of chemically disordered materials is constrained by the combinatorial growth of possible atomic configurations, which mak…
- arXiv cs.AIresearchVLA-Pro: Cross-Task Procedural Memory Transfer for Vision-Language-Action Models
arXiv:2605.29562v2 Announce Type: replace-cross Abstract: Vision-Language-Action (VLA) models have shown strong potential for general-purpose robotic manipulation, yet they still struggle to generalize to unseen tasks th…
- arXiv cs.AIresearchDAMEL: Dual-Axis Multi-Expert Learning for Class-Imbalanced Learning
arXiv:2605.30135v2 Announce Type: replace-cross Abstract: Various algorithms have been proposed to address the challenges posed by class-imbalanced learning from real-world data with long-tailed distributions. While thes…
- arXiv cs.AIresearchSmart Picks in the Dark: Towards Efficient RLVR for Reasoning via Tracing Metacognitive Pivots
arXiv:2606.04503v2 Announce Type: replace-cross Abstract: Reinforcement learning with verifiable rewards (RLVR) has greatly advanced large reasoning models (LRMs), but it requires timely training on a huge fully-annotate…
- arXiv cs.AIresearch'Your AI Text is not Mine': Redefining and Evaluating AI-generated Text Detection under Realistic Assumptions
arXiv:2606.04906v2 Announce Type: replace-cross Abstract: Although it is generally agreed that AI-generated text poses a broad societal risk, there is no common understanding in the AI-generated text detection literature…
- arXiv cs.AIresearchBalancing Image Compression and Generation with Bootstrapped Tokenization
arXiv:2606.05552v2 Announce Type: replace-cross Abstract: Despite progress in image tokenization, standard methods encode redundant information by mixing all granularities within each token, thus redundancy persists betw…
- arXiv cs.AIresearchEnd-to-End Context Compression at Scale
arXiv:2606.09659v2 Announce Type: replace-cross Abstract: Long-context language model inference is bottlenecked by memory, as the KV cache grows with context length. Recent techniques to compress the KV cache fall short:…
- arXiv cs.AIresearchCANVAS: Captioning Art with Narrative Visual-Audio AI Systems
arXiv:2606.09846v2 Announce Type: replace-cross Abstract: For a person who is blind or has low vision (BLV), a painting is usually represented by a few words of alt-text, if anything at all. That text rarely conveys the…
- arXiv cs.AIresearchEDITH: Teaching Robot to Follow Nonverbal Human Intent from Egocentric Vision and Gaze
arXiv:2606.10276v2 Announce Type: replace-cross Abstract: For natural human-robot interaction, a robot must understand human intent expressed not only through language but also through nonverbal signals such as gestures…
- arXiv cs.AIresearchOptimal Post-Training Quantization Scales and Where to Find Them
arXiv:2606.10890v2 Announce Type: replace-cross Abstract: Post-training quantization (PTQ) compresses large language models by mapping weights to low-bit representations. While much work has focused on how weights are ro…
- arXiv cs.AIresearchIs LLM's Moral Decision Compositional?
arXiv:2606.11232v2 Announce Type: replace-cross Abstract: Moral evaluations of language models typically infer a model's values from its choices between single acts, yet in everyday life a person is judged on their histo…
- arXiv cs.AIresearchNon-Gaussianity Reveals Interpretable Directions in Language Models
arXiv:2606.11722v2 Announce Type: replace-cross Abstract: Finding human-interpretable directions in language-model activations is important for understanding and controlling model behavior. These directions are usually d…
- arXiv cs.AIresearchThe Signs Were Always There: Training-Free Detection and Control in Raw Transformer Dimensions
arXiv:2606.12629v4 Announce Type: replace-cross Abstract: Because of polysemanticity and superposition, it has been challenging to attribute token understanding and generation to specific neurons or dimensions. Yet the i…
- arXiv cs.AIresearchAn integrated interpretable control effectiveness learning and nonlinear control allocation methodology for overactuated aircraft
arXiv:2606.13794v3 Announce Type: replace-cross Abstract: Nonlinear dynamics and the strong couplings that arise between multiple effectors undermine the assumptions behind conventional, linear control allocation techniq…
- arXiv cs.AIresearchEvaluating the Robustness of Proof Autoformalization in Lean 4
arXiv:2606.14867v3 Announce Type: replace-cross Abstract: Proof autoformalization aims to translate a mathematical informal proof in natural language into a formal proof in a formal language such as Lean 4. Existing LLM-…
- arXiv cs.AIresearchService-Induced Congestion in Memory-Constrained LLM Serving
arXiv:2606.15555v3 Announce Type: replace-cross Abstract: In large language model (LLM) serving, each request accumulates persistent graphics processing unit (GPU) memory during service as its key-value cache grows with…
- arXiv cs.AIresearchEnd-to-End Radar and Communication Modulation Recognition with Neuromorphic Computing
arXiv:2606.24075v2 Announce Type: replace-cross Abstract: Although deep learning-based methods can achieve high accuracy in automatic modulation recognition (AMR) tasks, their high computational cost makes it difficult t…
- arXiv cs.AIagentsCan Trustless Agents Be Trusted? An Empirical Study of the ERC-8004 Decentralized AI Agent Ecosystem
arXiv:2606.26028v3 Announce Type: replace-cross Abstract: As autonomous AI agents increasingly transact across organizational boundaries, a fundamental trust challenge emerges: how can an agent assess whether an unknown…
- arXiv cs.AIagentsAutomating the Design of Embodied Agent Architectures
arXiv:2606.30111v3 Announce Type: replace-cross Abstract: Embodied agents are typically built as hand-designed compositions of perception, memory, planning, and action modules. This modularity exposes a large architectur…
- arXiv cs.AIresearchGROW$^2$: Grounding Which and Where for Robot Tool Use
arXiv:2606.30632v2 Announce Type: replace-cross Abstract: Can the robot use a plate to cut a cake if no knife is available? Tool use greatly expands robot capabilities, but to use tools creatively beyond their intended f…
- arXiv cs.AIresearchGemNav: Discrete-Token Visual Robot Navigation using a Multimodal Large Language Model
arXiv:2607.06882v3 Announce Type: replace-cross Abstract: Visual navigation policies built on large pretrained models increasingly rely on large cross-embodiment datasets and expressive action-generation mechanisms. In t…