AI news archive.
19,864 articles, newest first, from the outlets listed on the sources page.
- arXiv cs.AIresearchVIRENA: Virtual Arena for Research, Education, and Democratic Innovation
arXiv:2602.12207v3 Announce Type: replace-cross Abstract: Digital platforms shape how people communicate, deliberate, and form opinions. Studying these dynamics has become harder because of restricted data access, ethica…
- arXiv cs.AIagentsSame Pieces, Different Servers: A Tetris Benchmark for AI Agents as Served
arXiv:2603.02348v2 Announce Type: replace-cross Abstract: An agent meets a model as served: through an endpoint with a price card, a shared cache and other tenants, or on whatever hardware a self-hosted model runs. Bench…
- arXiv cs.AIresearchDissecting Quantization Error: A Concentration-Alignment Perspective
arXiv:2603.04359v2 Announce Type: replace-cross Abstract: Quantization can drastically increase the efficiency of large language and vision models, but typically incurs an accuracy drop. Recently, function-preserving tra…
- arXiv cs.AIresearchRAC: Rectified Flow Auto Coder
arXiv:2603.05925v2 Announce Type: replace-cross Abstract: In this paper, we propose a Rectified Flow Auto Coder (RAC) inspired by Rectified Flow to replace the traditional VAE: 1. It achieves multi-step decoding by apply…
- arXiv cs.AIresearchTowards Robust Speech Deepfake Detection via Human-Inspired Reasoning
arXiv:2603.10725v4 Announce Type: replace-cross Abstract: The modern generative audio models can be used by an adversary in an unlawful manner, specifically, to impersonate other people to gain access to private informat…
- arXiv cs.AIagentsCOMIC: Agentic Sketch Comedy Generation
arXiv:2603.11048v2 Announce Type: replace-cross Abstract: We propose a fully automated AI system that produces short comedic videos similar to sketch shows such as Saturday Night Live. Starting from character references,…
- arXiv cs.AIresearchYou've Got a Golden Ticket: Improving Generative Robot Policies With A Single Noise Vector
arXiv:2603.15757v4 Announce Type: replace-cross Abstract: Generative robot policies trained on demonstrations using behavior cloning often learn actions that are sub-optimal or misaligned with respect to the downstream t…
- arXiv cs.AIagentsMulti-Agent Reinforcement Learning Counteracts Delayed CSI in Multi-Satellite Systems
arXiv:2603.16470v2 Announce Type: replace-cross Abstract: The integration of satellite communication networks with next-generation (NG) technologies is a promising approach towards global connectivity. However, the quali…
- arXiv cs.AIresearchBeyond TVLA: Anderson-Darling Leakage Assessment for Neural Network Side-Channel Leakage Detection
arXiv:2603.18647v2 Announce Type: replace-cross Abstract: Test Vector Leakage Assessment (TVLA) is widely used for side-channel leakage detection, but its reliance on Welch's t-test makes it primarily sensitive to differ…
- arXiv cs.AIresearchDeepStock: Reinforcement Learning with Policy Regularizations for Inventory Management
arXiv:2603.19621v2 Announce Type: replace-cross Abstract: Deep Reinforcement Learning (DRL) provides a general-purpose methodology for training inventory policies that can leverage big data and compute. However, off-the-…
- arXiv cs.AIagentsWebNavigator: Global Web Navigation via Interaction Graph Retrieval
arXiv:2603.20366v2 Announce Type: replace-cross Abstract: Despite significant advances in autonomous web navigation, current methods remain far from human-level performance in complex web environments. We argue that this…
- arXiv cs.AIresearchUpgrade the Retriever First: What an LLM Call per Chunk Buys in RAG
arXiv:2603.23533v4 Announce Type: replace-cross Abstract: Many RAG pipelines pay one LLM call per chunk at indexing time to add titles, summaries, keywords and questions (enrichment) or document context (contextual retri…
- arXiv cs.AIresearchPre-Deployment Complexity Estimation for Federated Perception Systems
arXiv:2603.28282v3 Announce Type: replace-cross Abstract: Edge AI systems increasingly rely on federated learning to train perception models in distributed, privacy-preserving, and resource-constrained environments. Befo…
- arXiv cs.AIresearchSven: Singular Value Descent as a Computationally Efficient Natural Gradient Method
arXiv:2604.01279v2 Announce Type: replace-cross Abstract: We introduce Sven (Singular Value dEsceNt), a new optimization algorithm for neural networks that exploits the natural decomposition of loss functions into a sum…
- arXiv cs.AIagentsAn AI Teaching Assistant for Motion Picture Engineering
arXiv:2604.04670v2 Announce Type: replace-cross Abstract: The rapid rise of LLMs over the last few years has promoted growing experimentation with LLM-driven AI tutors. However, the details of implementation, as well as…
- arXiv cs.AIresearch$\pi^2$: Structure-Originated Reasoning Data Improves Long-Context Reasoning Ability of Large Language Models
arXiv:2604.05114v2 Announce Type: replace-cross Abstract: We study a QA curation pipeline for improving long-context complex reasoning in large language models (LLMs). Our approach, $\pi^2$, constructs high-quality reaso…
- arXiv cs.AIresearchA Self-Calibrating Framework for Analog Circuit Sizing Using LLM-Derived Analytical Equations
arXiv:2604.07387v3 Announce Type: replace-cross Abstract: We present a design automation framework for analog circuit sizing that produces calibrated, topology-specific analytical equations from raw circuit netlists. A l…
- arXiv cs.AIresearchOn the use of evolutionary optimization for the dynamic chance constrained open-pit mine scheduling problem
arXiv:2604.13385v3 Announce Type: replace-cross Abstract: Open-pit mine scheduling is a complex real-world optimization problem that involves uncertain economic values and dynamically changing resource capacities. Evolut…
- arXiv cs.AIagentsEvaluating a Layered Prompt-Injection Defence for the Model Context Protocol: A Record-Level Audit of Decision Conventions, Corpus Provenance and Reproducibility
arXiv:2604.17125v3 Announce Type: replace-cross Abstract: The Model Context Protocol (MCP) extends the prompt-injection attack surface of large language model applications to tool descriptions, parameter schemas and tool…
- arXiv cs.AIresearchPSI-Bench: Interpretable and Clinically Meaningful Evaluation of Depression Patient Simulators
arXiv:2604.25840v2 Announce Type: replace-cross Abstract: Patient simulators are gaining traction in mental health training by providing scalable exposure to complex and sensitive patient interactions. Simulating depress…
- arXiv cs.AIagentsActive Learning for Communication Structure Optimization in LLM-Based Multi-Agent Systems
arXiv:2605.05703v3 Announce Type: replace-cross Abstract: Optimizing the communication structure of large language model based multi-agent systems (LLM-MAS) has been shown to improve downstream performance and reduce tok…
- arXiv cs.AIresearchIs Escalation Worth It? On the Depth of LLM Cascades
arXiv:2605.06350v2 Announce Type: replace-cross Abstract: LLM cascades, in which a cheap model defers to an expensive one on low-confidence queries, are widely used to reduce inference cost. Given a pool of models, a pra…
- arXiv cs.AIresearchPLOT: Progressive Localization via Optimal Transport in Neural Causal Abstraction
arXiv:2605.06979v2 Announce Type: replace-cross Abstract: Causal abstraction offers a principled framework for mechanistic interpretability, aligning a high-level causal model with low-level neural computation through in…
- arXiv cs.AIresearchMask2Cause: Temporal Causal Discovery Beyond Causality in Mean
arXiv:2605.07280v2 Announce Type: replace-cross Abstract: One approach to discovering causal relationships in multivariate time series is to ask whether a variable's history improves prediction of another variable. When…
- arXiv cs.AIagentsThe Endogeneity of Miscalibration: Impossibility and Escape in Scored Reporting
arXiv:2605.07671v3 Announce Type: replace-cross Abstract: An agent's probability report is paid for twice: by a strictly proper scoring rule, and by an approval rule for the decision it triggers. In this classical decisi…
- arXiv cs.AIresearchTIDES: Implicit Time-Awareness in Selective State Space Models
arXiv:2605.09742v3 Announce Type: replace-cross Abstract: Selective state space models (SSMs), such as Mamba, achieve strong per-token expressivity by making the time discretization step $\Tilde{\Delta}$ a learned functi…
- arXiv cs.AIresearchNCO: A Versatile Plug-in for Handling Negative Constraints in Decoding
arXiv:2605.10065v2 Announce Type: replace-cross Abstract: Controlling Large Language Models (LLMs) to prevent the generation of undesirable content, such as profanity and personally identifiable information (PII), has be…
- arXiv cs.AIresearchWhen Can Digital Personas Reliably Approximate Human Survey Findings?
arXiv:2605.10659v3 Announce Type: replace-cross Abstract: Digital personas powered by Large Language Models (LLMs) are increasingly proposed as substitutes for human survey respondents, yet it remains unclear when they c…
- arXiv cs.AIresearchPremover: Fast Vision-Language-Action Control via Early Execution During Instruction Delivery
arXiv:2605.12160v2 Announce Type: replace-cross Abstract: Vision-Language-Action (VLA) policies are typically evaluated under the assumption that the robot starts acting only after the user has finished typing or speakin…
- arXiv cs.AIagentsLarge Language Models for Agentic NetOps and AIOps: Architectures, Evaluation, and Safety
arXiv:2605.12729v4 Announce Type: replace-cross Abstract: Large language models (LLMs) are increasingly being used in network operations (NetOps) and artificial intelligence for IT operations (AIOps) for tasks ranging fr…
- arXiv cs.AIagentsAgentLens: Revealing The Lucky Pass Problem in SWE-Agent Evaluation
arXiv:2605.12925v4 Announce Type: replace-cross Abstract: Evaluation of software engineering (SWE) agents is dominated by a binary signal: whether the final patch passes the tests. This outcome-only view treats a princip…
- arXiv cs.AIresearchAnalog RF Computing: A New Paradigm for Energy-Efficient Edge AI Over MU-MIMO Systems
arXiv:2605.14331v2 Announce Type: replace-cross Abstract: Modern edge devices increasingly rely on neural networks for intelligent applications. However, conventional digital computing-based edge inference requires subst…
- arXiv cs.AIresearchText Knows What, Tables Know When: Clinical Timeline Reconstruction via Retrieval-Augmented Multimodal Alignment
arXiv:2605.15168v2 Announce Type: replace-cross Abstract: Clinical language models increasingly operate over electronic health records (EHRs), yet patient records are not stored as temporally grounded trajectories. Clini…
- arXiv cs.AIresearchGraViti: Graph-Level Variational Autoencoders with Relaxed Permutation Invariance
arXiv:2605.16668v2 Announce Type: replace-cross Abstract: We introduce GraViti, a transformer-based graph-level variational autoencoder that encodes entire graphs into single, fixed-dimensional latent vectors rather than…
- arXiv cs.AIresearchAn Assessment of Human vs. Model Uncertainty in Soft-Label Learning and Calibration
arXiv:2605.18648v2 Announce Type: replace-cross Abstract: Central to human-aligned AI is understanding the benefits of human-elicited labels over synthetic alternatives. While human soft-labels improve calibration by cap…
- arXiv cs.AIagentsPopPy: Opportunistically Exploiting Parallelism in Python Agentic Workflows
arXiv:2605.18697v2 Announce Type: replace-cross Abstract: Agentic workflows, which compose calls to ML models using a general-purpose programming language like Python, are widely used for a variety of user-facing tasks,…
- arXiv cs.AIresearchLess Back-and-Forth: A Comparative Study of Structured Prompting
arXiv:2605.20149v2 Announce Type: replace-cross Abstract: Large language models (LLMs) are widely used for open-ended tasks, but underspecified prompts can lead to low-quality answers and additional interaction. This pap…
- arXiv cs.AIresearchTextReg: Mitigating Prompt Distributional Overfitting via Regularized Text-Space Optimization
arXiv:2605.21318v2 Announce Type: replace-cross Abstract: Large language models (LLMs) are highly sensitive to the prompts used to specify task objectives and behavioral constraints. Many recent prompt optimization metho…
- arXiv cs.AIresearchTranscoders Trace Visual Grounding and Hallucinations in Vision-Language Models
arXiv:2605.22902v3 Announce Type: replace-cross Abstract: Generative Vision-Language Models (VLMs) perform well on multimodal reasoning, but how visual inputs are transformed to text remains poorly understood. Existing i…
- arXiv cs.AIresearchThe TIME Machine: On The Power of Motion for Efficient Perception
arXiv:2605.23045v4 Announce Type: replace-cross Abstract: Video representation learning has seen tremendous progress in recent years. This has been driven by many factors, including the scale of training and the success…
- arXiv cs.AIresearchDrawVideo: Grounded and Faithful Multi-Shot Video Generation from Storyboard Keyframe Sketches
arXiv:2605.23508v2 Announce Type: replace-cross Abstract: Long video generation requires high-fidelity visual synthesis, coherent narrative organization, shot-level structure, and explicit user control. Existing text-to-…
- arXiv cs.AIresearchMeasuring the Depth of LLM Unlearning via Activation Patching
arXiv:2605.24614v3 Announce Type: replace-cross Abstract: Large language model (LLM) unlearning has emerged as a crucial post-hoc mechanism for privacy protection and AI safety, yet auditing whether target knowledge is t…
- arXiv cs.AIresearchA Controlled Synthetic Benchmark for Educational Aspect-Based Sentiment Analysis
arXiv:2605.25502v2 Announce Type: replace-cross Abstract: Educational aspect-based sentiment analysis (ABSA) can support course improvement, but public aspect-labeled student feedback remains scarce because educational r…
- arXiv cs.AIresearchErased but Exploitable: Black-box Embedding-Aware Prompting Against Unlearned Text-to-Image Diffusion Models
arXiv:2605.26332v2 Announce Type: replace-cross Abstract: Machine unlearning aims to remove specific concepts from pretrained text-to-image diffusion models, yet several white- and black-box attacks have been introduced…
- arXiv cs.AIresearchvSV-ViT: Variable-size SuperVertex Vision Transformer for Cortical Surface Learning in Alzheimer's Disease
arXiv:2605.26514v2 Announce Type: replace-cross Abstract: Learning from 3D meshes is challenging because the data reside on non-Euclidean surfaces embedded in 3D space. This is particularly evident in domains such as bra…
- arXiv cs.AIresearchCiteCheck: Retrieval-Grounded Detection of LLM Citation Hallucinations in Scientific Text
arXiv:2605.27700v2 Announce Type: replace-cross Abstract: Large language models (LLMs) are increasingly used to generate scientific reports, but they can produce references that appear plausible while containing corrupte…
- arXiv cs.AIresearchBrain-IT-VQA: From Brain Signals to Answers
arXiv:2605.29588v3 Announce Type: replace-cross Abstract: Decoding visual content from fMRI signals recorded while a person views images, and specifically answering questions about the seen images, is a long-standing cha…
- arXiv cs.AIresearchEUDAIMONIA: Evaluating Undesirable Dynamics in AI
arXiv:2605.30654v2 Announce Type: replace-cross Abstract: Large language models (LLMs) are increasingly used as conversational partners for companionship, emotional disclosure, and interpersonal advice, but the social dy…
- arXiv cs.AIresearchSWIM: Compact Environment Representation for Reinforcement Learning Human Swimming
arXiv:2605.31120v2 Announce Type: replace-cross Abstract: Deep reinforcement learning (RL) has driven rapid progress in physically-based motion generation, yet synthesizing robust motion policies in dense fluid environme…
- arXiv cs.AIresearchGEM: Geometric Erasure by Contrastive Velocity Matching in Rectified Flows
arXiv:2606.00140v4 Announce Type: replace-cross Abstract: While the rapid adoption of multimodal generative models offers immense potential, it has also increased the risks of harmful content synthesis, deepfakes, and co…