AI news archive.
10,659 articles filed under Research, newest first, from the outlets listed on the sources page.
- arXiv cs.AIresearchMachine Unlearning in Low-Dimensional Feature Subspace
arXiv:2601.22456v3 Announce Type: replace-cross Abstract: Machine Unlearning (MU) aims at removing the influence of specific data from a pretrained model while preserving performance on the remaining data. In this work,…
- arXiv cs.AIresearchTTCS: Test-Time Curriculum Synthesis for Self-Evolving
arXiv:2601.22628v3 Announce Type: replace-cross Abstract: Test-Time Training offers a promising way to improve the reasoning ability of large language models (LLMs) by adapting the model using only the test questions. Ho…
- arXiv cs.AIresearchMOSAIC: More LLMs, Less Cost through Collaborative Reasoning for Compiler Optimizations
arXiv:2602.01935v3 Announce Type: replace-cross Abstract: LLM-guided compiler optimization has recently shown promise. However, current LLM-guided optimizers query a single LLM at every search step, so their cost grows w…
- arXiv cs.AIresearchDo We Need Asynchronous SGD? On the Near-Optimality of Synchronous Methods
arXiv:2602.03802v2 Announce Type: replace-cross Abstract: Modern distributed optimization methods mostly rely on traditional synchronous approaches, despite substantial recent progress in asynchronous optimization. We re…
- arXiv cs.AIresearchSkin Tokens: A Learned Compact Representation for Unified Autoregressive Rigging
arXiv:2602.04805v2 Announce Type: replace-cross Abstract: The rapid proliferation of generative 3D models has created a critical bottleneck in animation pipelines: rigging. Existing automated methods are fundamentally li…
- arXiv cs.AIresearchSHINE: A Scalable In-Context Hypernetwork for Mapping Context to LoRA in a Single Pass
arXiv:2602.06358v4 Announce Type: replace-cross Abstract: We propose SHINE (Scalable Hyper In-context NEtwork), a scalable hypernetwork that can map diverse meaningful contexts into high-quality LoRA adapters for large l…
- arXiv cs.AIresearchRAG Strategies for Natural Language-Based SQL Query and REST API Call Generation
arXiv:2602.07086v3 Announce Type: replace-cross Abstract: Enterprise software systems commonly expose functionality through relational databases and REST APIs, requiring users to understand schemas, endpoints, and parame…
- arXiv cs.AIresearchSLA2: Sparse-Linear Attention with Learnable Routing and Quantization-aware Training
arXiv:2602.12675v2 Announce Type: replace-cross Abstract: Sparse-Linear Attention (SLA) combines sparse and linear attention to accelerate diffusion models and has shown strong performance in video generation. However, (…
- arXiv cs.AIresearchPushing the Frontier of Black-Box LVLM Attacks via Fine-Grained Detail Targeting
arXiv:2602.17645v2 Announce Type: replace-cross Abstract: Black-box adversarial attacks on Large Vision-Language Models (LVLMs) are challenging due to missing gradients and complex multimodal boundaries. Prior state-of-t…
- arXiv cs.AIresearchWhat Drives Students' Use of AI Chatbots? Technology Acceptance in Conversational AI
arXiv:2602.20547v2 Announce Type: replace-cross Abstract: Conversational AI tools have been rapidly adopted by students and are becoming part of their learning routines. This widespread use comes amid ongoing concerns ab…
- arXiv cs.AIresearchGRAU: A Generic Runtime-Reconfigurable Activation-Requantization Unit for Quantized Neural Network Accelerators
arXiv:2602.22352v3 Announce Type: replace-cross Abstract: As neural networks continue to scale, low-precision quantization is widely adopted in edge accelerators, but conventional multi-threshold activation hardware requ…
- arXiv cs.AIresearchBrain-OF: An Omnifunctional Foundation Model for fMRI, EEG and MEG
arXiv:2602.23410v4 Announce Type: replace-cross Abstract: Brain foundation models have achieved remarkable advances across a wide range of neuroscience tasks. However, most existing models are limited to a single functio…
- arXiv cs.AIresearchDifferential privacy representation geometry for medical image analysis
arXiv:2603.01098v4 Announce Type: replace-cross Abstract: Differential privacy (DP)'s effect in medical imaging is typically evaluated only through end-to-end performance, leaving the mechanism of privacy-induced utility…
- arXiv cs.AIresearchRigidity-Aware Geometric Pretraining for Protein Design and Conformational Ensembles
arXiv:2603.02406v3 Announce Type: replace-cross Abstract: Generative models have recently advanced $\textit{de novo}$ protein design by learning the statistical regularities of natural structures. However, current approa…
- arXiv cs.AIresearchRoboPocket: Improve Robot Policies Instantly with Your Phone
arXiv:2603.05504v3 Announce Type: replace-cross Abstract: Scaling robot learning is bottlenecked not only by data volume, but also by whether the data targets the policy's failures. Existing robot-free handheld interface…
- arXiv cs.AIresearchBrittlebench: Quantifying LLM robustness via prompt sensitivity
arXiv:2603.13285v4 Announce Type: replace-cross Abstract: Existing evaluation methods largely rely on clean, static benchmarks, which can overestimate true model performance by failing to capture the noise and variabilit…
- arXiv cs.AIresearchBridging the Gap in the Responsible AI Divides
arXiv:2603.14495v2 Announce Type: replace-cross Abstract: Tensions between AI Safety (AIS) and AI Ethics (AIE) have created what we term a "responsible AI divide." This divide has been persistent, and has dominated the p…
- arXiv cs.AIresearchSF-Mamba: Rethinking State Space Model for Vision
arXiv:2603.16423v2 Announce Type: replace-cross Abstract: Visual Mamba models have recently emerged as alternatives to Vision Transformers (ViTs), which suffer from quadratic complexity. While the recurrent scanning mech…
- arXiv cs.AIresearchAttention Sinks Induce Gradient Sinks: Massive Activations as Gradient Regulators in Transformers
arXiv:2603.17771v3 Announce Type: replace-cross Abstract: Attention sinks and massive activations are recurring and closely related phenomena in Transformer models. Existing explanations have largely focused on the forwa…
- arXiv cs.AIresearchEVA: Aligning Video World Models with Executable Robot Actions via Inverse Dynamics Rewards
arXiv:2603.17808v3 Announce Type: replace-cross Abstract: Video generative models offer a promising basis for robotic planning by predicting future visual rollouts from observations and task instructions. However, their…
- arXiv cs.AIresearchSpan-Level Machine Translation Meta-Evaluation
arXiv:2603.19921v2 Announce Type: replace-cross Abstract: Machine Translation (MT) and automatic MT evaluation have improved dramatically in recent years, enabling numerous novel applications. Automatic evaluation techni…
- arXiv cs.AIresearchCTFS : Collaborative Teacher Framework for Forward-Looking Sonar Image Semantic Segmentation with Extremely Limited Labels
arXiv:2603.21071v3 Announce Type: replace-cross Abstract: As one of the most important underwater sensing technologies, forward-looking sonar exhibits unique imaging characteristics. Sonar images are often affected by se…
- arXiv cs.AIresearchEstimating Individual Tree Height and Species from UAV Imagery
arXiv:2603.23669v3 Announce Type: replace-cross Abstract: Accurate estimation of forest biomass, a major carbon sink, relies heavily on tree-level traits such as height and species. Unoccupied Aerial Vehicles (UAVs) capt…
- arXiv cs.AIresearchDerived Fields Increase the Recoverable Information in Budgeted Neural PDE Surrogate
arXiv:2603.29224v2 Announce Type: replace-cross Abstract: For neural surrogates of time-dependent partial differential equations (PDEs), storage and memory budgets require training data to be obtained by coarsening and q…
- arXiv cs.AIresearchBringing Up a Bilingual BabyLM: Investigating Multilingual Language Acquisition Using Small-Scale Models
arXiv:2603.29552v3 Announce Type: replace-cross Abstract: Multilingualism is incredibly common around the world, leading to many important theoretical and practical questions, including whether multilingual acquisition l…
- 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.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.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.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.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.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.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…