AI news archive.
19,864 articles, newest first, from the outlets listed on the sources page.
- arXiv cs.AIresearchM$^2$RNN: Non-Linear RNNs with Matrix-Valued States for Scalable Language Modeling
arXiv:2603.14360v3 Announce Type: replace-cross Abstract: Transformers are highly parallel but are limited to computations in the TC$^0$ complexity class, excluding tasks such as entity tracking and code execution that p…
- arXiv cs.AIresearchUnderstanding and Defending VLM Jailbreaks via Jailbreak-Related Representation Shift
arXiv:2603.17372v3 Announce Type: replace-cross Abstract: Large vision-language models (VLMs) often exhibit weakened safety alignment with the integration of the visual modality. Even when text prompts contain explicit h…
- arXiv cs.AIresearchSuppression of $^{14}\mathrm{C}$ photon hits in large liquid scintillator detectors via spatiotemporal deep learning
arXiv:2603.27727v2 Announce Type: replace-cross Abstract: Liquid scintillator detectors are widely used in neutrino experiments due to their low energy threshold and high energy resolution. Despite the tiny abundance of…
- arXiv cs.AIresearchWorst-Case Optimal $\sqrt{\epsilon}$-Rate Stability of KL Divergence under Perturbations of Gaussian Distributions
arXiv:2604.11026v4 Announce Type: replace-cross Abstract: We establish a stability bound for the Kullback-Leibler (KL) divergence when its Gaussian reference distribution is perturbed. Existing relaxed triangle inequalit…
- arXiv cs.AIresearchOmniTrace: A Unified Framework for Generation-Time Source Attribution in Omni-Modal LLMs
arXiv:2604.13073v2 Announce Type: replace-cross Abstract: An omni-modal language model can answer a question about a multimodal document, a recording, or a video, but it cannot show which part of the input the answer cam…
- arXiv cs.AIresearchAlgorithmic Primitives of Theory of Mind Benchmarks
arXiv:2604.17819v2 Announce Type: replace-cross Abstract: Do Theory of Mind (ToM) benchmarks really test theory of mind, or are they actually testing parsing and algorithmic state tracking? While benchmarks vary modality…
- arXiv cs.AIresearchActivation-Efficient Fine-Tuning via Sequence-Compressed Low-Rank Subspaces
arXiv:2604.22783v2 Announce Type: replace-cross Abstract: Parameter-Efficient Fine-Tuning (PEFT) has become the standard approach for adapting large language models (LLMs). However, despite reducing trainable parameter c…
- arXiv cs.AIagentsCastFlow: Bridging Evidence Acquisition and Accurate Prediction in Agentic Time Series Forecasting
arXiv:2604.27840v3 Announce Type: replace-cross Abstract: Time series forecasting is a fundamental task in temporal data analytics, and large language model (LLM)-based agents offer a promising paradigm through autonomou…
- arXiv cs.AIresearchInterpretable experiential learning based on state history and global feedback
arXiv:2605.00940v2 Announce Type: replace-cross Abstract: A new interpretable experiential learning model based on state history and global feedback is presented. It is capable of learning a behavioral model represented…
- arXiv cs.AIresearchLearning reveals invisible structure in low-rank RNNs
arXiv:2605.04115v2 Announce Type: replace-cross Abstract: Learning in neural systems arises from synaptic changes that reshape the representations underlying behavior. While low-rank recurrent neural networks (RNNs) have…
- arXiv cs.AIresearchFaithfulFaces: Pose-Faithful Facial Identity Preservation for Text-to-Video Generation
arXiv:2605.04702v2 Announce Type: replace-cross Abstract: Identity-preserving text-to-video generation (IPT2V) empowers users to produce diverse and imaginative videos with consistent human facial identity. Despite recen…
- arXiv cs.AIresearchMOSAIC: Module Discovery via Sparse Additive Identifiable Causal Learning for Scientific Time Series
arXiv:2605.05524v2 Announce Type: replace-cross Abstract: Causal representation learning (CRL) seeks to recover latent variables with identifiability guarantees, typically up to permutation and component-wise reparameter…
- arXiv cs.AIagentsCoordination Matters: Process-Aware Evaluation of Cooperative Multi-Agent Reinforcement Learning
arXiv:2605.06557v2 Announce Type: replace-cross Abstract: Cooperative multi-agent reinforcement learning (MARL) benchmarks commonly emphasize aggregate outcomes such as return, success rate, or completion time. While ess…
- arXiv cs.AIresearchSTRIDE: Reasoning-Aware Training for Time Series Forecasting
arXiv:2605.08625v2 Announce Type: replace-cross Abstract: Time Series Foundation Models (TSFMs) excel at numerical forecasting but operate as black boxes lacking qualitative reasoning. Conversely, applying LLMs directly…
- arXiv cs.AIresearchCIDR: A Large-Scale Industrial Source Code Dataset for Software Engineering Research
arXiv:2605.12153v3 Announce Type: replace-cross Abstract: We present the Curated Industrial Developer Repository (CIDR), a large-scale dataset of real-world software repositories collected from industrial partners. The d…
- arXiv cs.AIresearchRaPD: Resolution-Agnostic Pixel Diffusion via Semantics-Enriched Implicit Representations
arXiv:2605.15908v2 Announce Type: replace-cross Abstract: Natural images are continuous, yet most generative models synthesize them on discrete grids, limiting resolution-flexible generation. Continuous neural fields ena…
- arXiv cs.AIresearchHuman-Centered Learning Mechanics: Observable Entropy Control under Protected-Risk Constraints
arXiv:2605.22940v2 Announce Type: replace-cross Abstract: Entropy reduction is not a safety criterion: it can leave predictions unchanged or accompany increasing risk for a protected group. We study entropy-regulated lea…
- arXiv cs.AIresearchFormInv: A Measurement Protocol for Semantic Invariance in Mathematical Reasoning Benchmarks
arXiv:2605.29001v2 Announce Type: replace-cross Abstract: A paraphrase-quality audit of MathCheck (ICLR 2025) detected 4 semantically incorrect paraphrases in 129 groups (3.1%); removing them drops GPT-4o from rank 2 to…
- arXiv cs.AIresearchSciIntBench: Measuring LLM Compliance with Research Integrity Norms Under Adversarial Framing
arXiv:2605.29468v2 Announce Type: replace-cross Abstract: Large language models (LLMs) are increasingly used to support scientific work, but it is unclear whether they uphold responsible conduct of research (RCR) norms o…
- arXiv cs.AIresearchCauTion: Knowing When to Trust LLMs for Ensemble Causal Discovery
arXiv:2606.03602v2 Announce Type: replace-cross Abstract: Causal discovery from observational data remains challenging due to the fundamental limitations of purely statistical methods, such as statistical distinguishabil…
- arXiv cs.AIresearchTimpaTeks: Automatic In-place Text Sequence Modification via Diffusion Language Model Steering
arXiv:2606.08408v2 Announce Type: replace-cross Abstract: We extend activation steering to diffusion language models (DLMs) and study a novel problem that arose due to the inference mechanism of DLMs: Modifying a text in…
- arXiv cs.AIresearchAccounting for Purchased Artificial Intelligence Inference in Corporate Greenhouse Gas Inventories: A Token-Based Method
arXiv:2606.10660v2 Announce Type: replace-cross Abstract: Purchased artificial intelligence (AI) inference belongs in Scope 3 Category 1 of a corporate greenhouse gas inventory, yet practice omits it or applies a spend-b…
- arXiv cs.AIagentsAgentRivet: an automated system for producing Rivet routines from journal publications
arXiv:2606.13535v5 Announce Type: replace-cross Abstract: Particle physics collider experiments provide Rivet routines as part of the analysis preservation strategy for model-independent measurements. Rivet is a C++ tool…
- arXiv cs.AIresearchBeyond Tokenization: Direct Timestep Embedding and Contrastive Alignment for Time-Series Question Answering
arXiv:2606.18986v2 Announce Type: replace-cross Abstract: Recent advances in large language models (LLMs) have given rise to time-series question answering (TSQA), which formulates time-series analysis as natural-languag…
- arXiv cs.AIagentsGroup-Graph Policy Optimization for Long-Horizon Agentic Reinforcement Learning
arXiv:2606.22995v2 Announce Type: replace-cross Abstract: Group-based Reinforcement Learning (RL) has significantly enhanced Large Language Models (LLMs) in agentic scenarios. To achieve finer-grained policy updates, rec…
- arXiv cs.AIresearchPruneGround: Plug-and-play Spatial Pruning for 3D Visual Grounding
arXiv:2606.31148v3 Announce Type: replace-cross Abstract: 3D Visual Grounding (3DVG) aims to localize target objects in 3D scenes given natural language descriptions. Existing approaches typically perform reasoning over…
- arXiv cs.AIresearchTORINO: Token Reduction via Interpretable Concept Overlap in Vision-Language Models
arXiv:2607.04593v2 Announce Type: replace-cross Abstract: Vision-Language Models (VLMs) have demonstrated impressive capabilities across different tasks, but their computational cost is dominated by the large number of v…
- arXiv cs.AIresearchIs Your NPU Ready for LLMs? Dissecting the Hidden Efficiency Bottlenecks in Mobile LLM Inference
arXiv:2607.05475v2 Announce Type: replace-cross Abstract: Deploying Large Language Models (LLMs) on mobile devices enhances privacy and reduces latency, but is severely constrained by hardware inefficiencies. We present…
- arXiv cs.AIagentsDo Multi-Agent LLMs Explore Each Other?
arXiv:2607.11250v2 Announce Type: replace-cross Abstract: Exploration is essential for reliable autonomy in multi-agent systems, yet it remains unclear whether large language model (LLM) agents can explore effectively wh…
- arXiv cs.AIagentsHow Agents Ask for Permission: User Permissions for AI Agents, from Interfaces to Enforcement
arXiv:2607.13718v3 Announce Type: replace-cross Abstract: As AI agents grow in prevalence, so too do their risks to users, creating a need for robust and usable systems for agent permissions. Many recent proposals implem…
- arXiv cs.AIagentsEvery Model Cheats: Prompt-Level Mitigation of Cheating on Offensive Cyber Tasks
arXiv:2607.21763v2 Announce Type: replace-cross Abstract: Large language model (LLM) agents routinely cheat on cybersecurity benchmarks, inflating reported pass rates far beyond genuine capability. Prior audits of Cybenc…
- arXiv cs.AIresearchKAYROS: An Anytime and Exact Open-Source Solver for Duration-Minimization Time-Dependent Vehicle Routing. A Technical Report and a Case Study in Human-AI Engineering
arXiv:2607.23116v4 Announce Type: replace-cross Abstract: Time-dependent routing recognizes that the same journey can take a different time depending on when it begins. Under duration minimization, even the departure tim…
- arXiv cs.AIresearchEfficient LLM-Generated Shuttling Compilers for Complex Trapped-Ion Architectures
arXiv:2607.24714v2 Announce Type: replace-cross Abstract: Trapped-ion quantum computers rely on shuttling compilers, which cast an input algorithm into a sequence of ion-qubit movements within a given architecture. We pr…
- arXiv cs.AIresearchEKLAV: Elicited Key CoT Learning via Answer only superVision
arXiv:2607.25182v2 Announce Type: replace-cross Abstract: Reasoning distillation trains a student to reproduce both the teacher's chain-of-thought trace and its final answer. We ask whether the trace is better used as pr…
- arXiv cs.AIresearchAn AI Approach to Verified Production Cryptographic Libraries
arXiv:2608.00965v2 Announce Type: replace-cross Abstract: Cryptographic code is critical infrastructure that must be correct, yet formally verifying production libraries remains difficult. Existing language-model proof s…
- arXiv cs.AIresearchDemystifying When and Why VLAs Fail in Contact-Rich Tasks and How to Fix Them
arXiv:2608.01402v2 Announce Type: replace-cross Abstract: We address the problem of understanding when and why Vision-Language-Action models struggle with contact-rich manipulation tasks that require precise physical int…
- arXiv cs.AIresearchMANGO-Grasp: Mahalanobis Fields over Geometry-Oriented 3D Gaussians for Cross-Embodiment Dexterous Grasping
arXiv:2608.02014v2 Announce Type: replace-cross Abstract: Cross-embodiment dexterous grasping aims to synthesize stable grasps across heterogeneous multi-fingered hands with little or no embodiment-specific tuning. Exist…
- arXiv cs.AIresearchRescene: stable century-long climate emulation from a frozen weather model
arXiv:2608.09971v2 Announce Type: replace-cross Abstract: Machine-learning weather models now match or exceed operational numerical prediction in the medium range, but when they are run freely for years they drift, blow…
- arXiv cs.AIresearchBEAR-Bench: A Bilingual Enterprise and Academic Reasoning Benchmark for Multimodal Models
arXiv:2608.17895v2 Announce Type: replace-cross Abstract: While Multimodal Large Language Models (MLLMs) have made significant strides in visual comprehension, their ability to reason about text-dense, professional docum…
- arXiv cs.AIresearchSelf- and Other-Labels Induce Bidirectional Bias in LLM Judges
arXiv:2608.18091v3 Announce Type: replace-cross Abstract: As LLM-as-a-judge becomes increasingly widespread, self-preference -- the tendency of a judge to favor its own outputs -- raises growing concerns about evaluation…
- arXiv cs.AIresearchADEPT: Accelerating Dexterity via Pre-Training and Post-Training using Reinforcement Learning
arXiv:2608.19182v2 Announce Type: replace-cross Abstract: We introduce Accelerating Dexterity via Pre-Training (ADEPT), a large-scale reinforcement learning (RL) framework for learning sim-to-real transferable dexterity…
- arXiv cs.AIresearchBenthicDINO: Physics-Informed Self-Distillation for View-Invariant Side-Scan Sonar Representations
arXiv:2608.23215v2 Announce Type: replace-cross Abstract: Automated interpretation of side-scan sonar (SSS) imagery is traditionally hindered by view-dependence, as recorded intensities inextricably conflate intrinsic se…
- arXiv cs.AIresearchIndicDetect: Evaluating Cross-Lingual LLM-Generated Text Detection for Hindi, Telugu, and Tamil
arXiv:2608.29919v2 Announce Type: replace-cross Abstract: The rapid proliferation of LLMs has further heightened the need to develop dependable AI-generated text detection, especially beyond English. Nevertheless, curren…
- arXiv cs.AIagentsTowards Agentic Cloud Engineering: Graph and Loop Engineering with a Zero-Trust Agent Harness
arXiv:2609.00050v2 Announce Type: replace-cross Abstract: Agentic AI is enabling cloud-based workflows in which autonomous agents reason over operational state, invoke authorized tools, modify software and infrastructure…
- arXiv cs.AIresearchMind the Phase: Effective Rank and Representation Health in Legged Locomotion
arXiv:2609.06958v2 Announce Type: replace-cross Abstract: Reinforcement learning has become the leading paradigm in legged locomotion, enabling complex behaviors from backflips to parkour via massively parallel simulatio…
- arXiv cs.AIresearchGardenBench: A lightweight, daily evaluation of LLM capabilities
arXiv:2610.23866v1 Announce Type: new Abstract: We introduce GardenBench, a benchmark with 11 test suites that evaluate the capabilities of Large Language Models (LLMs) across a range of tasks. By systematically promptin…
- arXiv cs.AIagentsDoing Less with More: A First-Principles Exploration of the Suitability of Agentic Computing over Alternative Architectural Choices
arXiv:2610.23921v1 Announce Type: new Abstract: There is growing interest in automating business activities with Agentic Artificial Intelligence (AI) due to latter's seeming ease of use. Never has it been easier, or cost…
- arXiv cs.AIagentsA Controlled LLM Workflow for Evidence-Grounded Diagnosis of Risk Score Differences
arXiv:2610.23962v1 Announce Type: new Abstract: We propose a controlled Large Language Model (LLM) workflow for explaining risk score differences using similar historical transactions. The workflow combines reference ret…
- arXiv cs.AIresearchWhat Social Media Teaches Us About Accumulative AI Risks
arXiv:2610.24006v1 Announce Type: new Abstract: Prominent AI safety discussions emphasize existential threats and catastrophic events, such as AI-enabled nuclear conflict or engineered biological outbreaks. This position…
- arXiv cs.AIresearchBeyond Explicit Intent: Discovering and Shaping Artistic Intent through Human-AI Co-Creation
arXiv:2610.24010v1 Announce Type: new Abstract: Generative AI is becoming an important medium for artistic creation, yet existing interactions often assume that creators can specify intentions in advance and accurately c…