AI news archive.
10,659 articles filed under Research, newest first, from the outlets listed on the sources page.
- arXiv cs.AIresearchPepEVOLVE: Position-Aware Dynamic Peptide Optimization via Group-Relative Advantage
arXiv:2511.16912v2 Announce Type: replace-cross Abstract: Macrocyclic peptides are an emerging modality that combines biologics-like affinity with small-molecule-like developability, yet their vast combinatorial space an…
- arXiv cs.AIresearchMedGemma vs GPT-4: Open-Source and Proprietary Zero-shot Medical Disease Classification from Images
arXiv:2512.23304v2 Announce Type: replace-cross Abstract: Multimodal Large Language Models (LLMs) introduce an emerging paradigm for medical imaging by interpreting scans through the lens of extensive clinical knowledge,…
- arXiv cs.AIresearchReferential Regimes: Transformation-Based Identity Profiles for Neutral Substrates
arXiv:2601.16152v3 Announce Type: replace-cross Abstract: Data systems operating under persistent legal, institutional, and analytic disagreement require shared reference without presupposing agreement about interpretati…
- arXiv cs.AIresearchJacobian Scopes: A Unified Geometric Framework for Token-Level LLM Attribution
arXiv:2601.16407v5 Announce Type: replace-cross Abstract: Large language models (LLMs) make next-token predictions based on clues present in their context, such as semantic descriptions and in-context examples. Yet, eluc…
- arXiv cs.AIresearchIndustrialized Deception: The Collateral Effects of LLM-Generated Misinformation on Digital Ecosystems
arXiv:2601.21963v3 Announce Type: replace-cross Abstract: Generative AI and misinformation research have evolved since our 2024 survey. This paper presents an updated perspective, transitioning from literature review to…
- arXiv cs.AIresearchClueTracer: Question-to-Vision Clue Tracing for Training-Free Hallucination Suppression in Multimodal Reasoning
arXiv:2602.02004v2 Announce Type: replace-cross Abstract: Large multimodal reasoning models solve challenging visual problems via explicit long-chain inference: they gather visual clues from images and decode clues into…
- arXiv cs.AIresearchThe Verification Crisis: Expert Perceptions of GenAI Disinformation and the Case for Reproducible Provenance
arXiv:2602.02100v2 Announce Type: replace-cross Abstract: The growth of Generative Artificial Intelligence (GenAI) has shifted disinformation production from manual fabrication to automated, large-scale manipulation. Thi…
- arXiv cs.AIresearchRethinking Bayesian Optimization for Co-Optimizing LLM Training Configurations
arXiv:2602.08351v3 Announce Type: replace-cross Abstract: Fine-tuning an LLM to maximize performance on a downstream task requires finding the optimal data and model configuration. This is a black-box optimization proble…
- arXiv cs.AIresearchRobust Taylor-Lagrange Control for Safety-Critical Systems with Guaranteed Feasibility
arXiv:2602.20076v2 Announce Type: replace-cross Abstract: The Control Barrier Function (CBF) method has been widely adopted in solving safety-critical control problems. However, the existence of a CBF is only a sufficien…
- arXiv cs.AIresearchA general extractor for coherent patterns across time-frequency measurements
arXiv:2602.20317v3 Announce Type: replace-cross Abstract: Scientific discovery increasingly depends on finding meaningful patterns within volumes of sensor data too large for manual inspection. Existing time-frequency ev…
- arXiv cs.AIresearchExplainability-Aware Evaluation of Transfer Learning Models for IoT DDoS Detection Under Resource Constraints
arXiv:2602.22488v2 Announce Type: replace-cross Abstract: Distributed denial of service (DDoS) attacks threaten the availability of Internet of Things (IoT) infrastructures, particularly under resource-constrained deploy…
- arXiv cs.AIresearchNo Certificate, No Categorical Speech Act: A Brouwerian Assertibility Constraint for Public Reason
arXiv:2603.03971v5 Announce Type: replace-cross Abstract: Generative AI can convert uncertainty into authoritative-seeming verdicts, displacing the justificatory work on which democratic epistemic agency depends. As a co…
- arXiv cs.AIresearchTowards Batch-to-Streaming Deep Reinforcement Learning for Continuous Control
arXiv:2603.08588v3 Announce Type: replace-cross Abstract: State-of-the-art deep reinforcement learning (RL) methods have achieved remarkable performance in continuous control tasks, yet their computational complexity is…
- arXiv cs.AIresearchThe System Hallucination Scale (SHS): A Human-Centered Instrument for Assessing Perceived Reliability of Large Language Models
arXiv:2603.09989v2 Announce Type: replace-cross Abstract: Large language models routinely produce factually incorrect or misleading outputs, yet conventional automated benchmarks overlook how users perceive reliability d…
- arXiv cs.AIresearchECG-Reasoning-Benchmark: A Benchmark for Evaluating Clinical Reasoning Capabilities in ECG Interpretation
arXiv:2603.14326v2 Announce Type: replace-cross Abstract: While Multimodal Large Language Models (MLLMs) show promising performance in automated electrocardiogram interpretation, it remains unclear whether they perform a…
- arXiv cs.AIresearchROM: Real-time Overthinking Mitigation via Streaming Detection and Intervention
arXiv:2603.22016v4 Announce Type: replace-cross Abstract: Large reasoning models (LRMs) often suffer from overthinking, continuing with redundant verification and repeated attempts even after reaching a correct solution.…
- arXiv cs.AIresearchLatent Style-based Quantum Wasserstein GAN for Drug Design
arXiv:2603.22399v2 Announce Type: replace-cross Abstract: The development of new drugs is a time-consuming and expensive process, with average costs estimated to be up to around $2.5 billion. The first step in this proce…
- arXiv cs.AIresearchTrain at Moving Edge: Online-Verified Prompt Selection for Efficient RL Training of Large Reasoning Model
arXiv:2603.25184v4 Announce Type: replace-cross Abstract: Reinforcement learning (RL) has become essential for post-training large language models (LLMs) in reasoning tasks. While scaling rollouts can stabilize training…
- arXiv cs.AIresearchRocks, Pebbles and Sand: Modality-aware Scheduling for Multimodal Large Language Model Inference
arXiv:2603.26498v3 Announce Type: replace-cross Abstract: Multimodal Large Language Models (MLLMs) power platforms like ChatGPT, Gemini, and Copilot, enabling rich interactions across text, images, and videos. Unlike tex…
- arXiv cs.AIresearchLearning unified control of intrinsic nonlinear spin dynamics in atomic qudits for magnetometry
arXiv:2603.28421v3 Announce Type: replace-cross Abstract: Generating and preserving metrologically useful quantum states is a central challenge in quantum-enhanced metrology. In low-field atomic magnetometry with multile…
- arXiv cs.AIresearchTurbo4DGen: Ultra-Fast Acceleration for 4D Generation
arXiv:2603.29572v2 Announce Type: replace-cross Abstract: 4D generation, or dynamic 3D content generation, integrates spatial, temporal, and view dimensions to model realistic dynamic scenes, playing a foundational role…
- arXiv cs.AIresearchGenoBERT: A Language Model for Accurate Genotype Imputation
arXiv:2604.00058v2 Announce Type: replace-cross Abstract: Genotype imputation enables dense variant coverage for genome-wide association and risk-prediction studies, yet conventional reference-panel methods remain limite…
- arXiv cs.AIresearchSAFE: An LLM-as-Verifier Framework for Evidence-Grounded Multi-Hop Reasoning
arXiv:2604.01993v4 Announce Type: replace-cross Abstract: Multi-hop QA benchmarks often reward Large Language Models (LLMs) for spurious correctness, where models reach correct answers through invalid intermediate reason…
- arXiv cs.AIresearchA First Guess Is Rarely the Final Answer: Learned Local Search That Generalizes to Larger Routing Problems
arXiv:2604.06940v3 Announce Type: replace-cross Abstract: Neural routing solvers rarely stop at their first solution: constructed tours are usually refined by search, such as sampling or local search. Neural improvement…
- arXiv cs.AIresearchUniDG: Unified Defect Generation via Defect-Context Editing
arXiv:2604.08915v2 Announce Type: replace-cross Abstract: Generating realistic visual defects is crucial for alleviating the scarcity of abnormal samples in anomaly detection, yet existing methods often rely on category-…
- arXiv cs.AIresearchEdgeCIM: A Hardware-Software Co-Design for CIM-Based Acceleration of Small Language Models
arXiv:2604.11512v2 Announce Type: replace-cross Abstract: The growing demand for deploying Small Language Models (SLMs) on edge devices, including laptops, smartphones, automotive and robotic computing platforms, and hig…
- arXiv cs.AIresearchAdaptive Query Routing: A Tier-Based Framework for Hybrid Retrieval Across Financial, Legal, and Medical Documents
arXiv:2604.14222v2 Announce Type: replace-cross Abstract: Retrieval-Augmented Generation (RAG) has become the standard paradigm for grounding Large Language Model outputs in external knowledge. Lumer et al. presented the…
- arXiv cs.AIresearchLow-Rank Adaptation for Critic Learning in Off-Policy Reinforcement Learning
arXiv:2604.18978v3 Announce Type: replace-cross Abstract: Scaling critic capacity is a promising direction for improving off-policy reinforcement learning (RL). However, recent work shows that larger critics are prone to…
- arXiv cs.AIresearchInterpretable Difficulty-Aware Knowledge Tracing in Tutor-Student Dialogues
arXiv:2605.01097v2 Announce Type: replace-cross Abstract: Recent advances in large language models (LLMs) have led to the development of AI-powered tutoring systems that provide interactive support via dialogue. To enabl…
- arXiv cs.AIresearchValidity-Calibrated Reasoning Distillation
arXiv:2605.04078v3 Announce Type: replace-cross Abstract: Reasoning distillation aims to transfer multi-step reasoning capabilities from large language models to smaller, efficient ones. While recent methods have shown p…
- arXiv cs.AIresearchASTOR: Multi-Task Code Reinforcement Learning via Utility-Driven Coordination
arXiv:2605.06111v2 Announce Type: replace-cross Abstract: Reinforcement learning (RL) with verifiable rewards has proven effective at post-training LLMs for coding, yet deploying separate task-specific specialists incurs…
- arXiv cs.AIresearchDUET: Optimize Token-Budget Allocation for Reinforcement Learning with Verifiable Rewards
arXiv:2605.08441v2 Announce Type: replace-cross Abstract: Reinforcement learning with verifiable rewards (RLVR) generates hundreds of thousands of tokens per training step, with rollout generation dominating the computat…
- arXiv cs.AIresearchConditional Memory Enhanced Item Representation for Generative Recommendation
arXiv:2605.11447v2 Announce Type: replace-cross Abstract: Generative recommendation (GR) has emerged as a promising paradigm that predicts target items by autoregressively generating their semantic identifiers (SID). Mos…
- arXiv cs.AIresearchThe Illusion of Power Capping in LLM Decode: A Phase-Aware Energy Characterisation Across Attention Architectures
arXiv:2605.11999v2 Announce Type: replace-cross Abstract: Power capping is a common GPU energy lever in LLM serving, and it appears to work: the cap is set, the GPU reports drawing less than it, and the energy budget is…
- arXiv cs.AIresearchMahaVar: OOD Detection via Class-wise Mahalanobis Distance Variance under Neural Collapse
arXiv:2605.14413v2 Announce Type: replace-cross Abstract: Out-of-distribution (OOD) detection is a critical component for ensuring the reliability of deep neural networks in safety-critical applications. In this work, we…
- arXiv cs.AIresearchAlways Learning, Always Mixing: Efficient and Simple Data Mixing All the Time
arXiv:2605.15220v2 Announce Type: replace-cross Abstract: Data mixing decides how to combine different sources or types of data and is a consequential problem throughout language model training. In pretraining, data comp…
- arXiv cs.AIresearchOne Model, Two Roles: Emergent Specialization in a Shared Recurrent Transformer
arXiv:2605.17811v2 Announce Type: replace-cross Abstract: Can a shared-weight recurrent Transformer---one that repeatedly applies the same Transformer to update evolving latent states---develop distinct internal roles wi…
- arXiv cs.AIresearchFocused Forcing: Content-Aware Per-Frame KV Selection for Efficient Autoregressive Video Diffusion
arXiv:2605.18346v2 Announce Type: replace-cross Abstract: Recent advances in autoregressive video diffusion have enabled sequential and streaming video generation. However, long-horizon generation requires increasingly l…
- arXiv cs.AIresearchWorse than Random: The Importance of a Baseline for Unsupervised Feature Selection -- Extended Version
arXiv:2605.22973v3 Announce Type: replace-cross Abstract: Many novel unsupervised feature selection methods are proposed each year, yet their empirical evaluation is limited to supervised and unsupervised evaluation metr…
- arXiv cs.AIresearchTackling Multimodal Learning Challenges with Mixture-of-Expert: A Survey
arXiv:2605.27431v2 Announce Type: replace-cross Abstract: Mixture-of-Experts (MoE) presents a naturally compatible and scalable framework for multimodal learning, demonstrating strong adaptability across diverse modaliti…
- arXiv cs.AIresearchFLORO: A Multimodal Geospatial Foundation Model for Ecological Remote Sensing Across Sensors and Scales
arXiv:2605.28174v2 Announce Type: replace-cross Abstract: Foundation models offer a promising route to transferable remote sensing representations, but many current approaches depend on very large pretraining datasets an…
- arXiv cs.AIresearchAnyMo: Scaling Any-Modality Conditional Motion Generation with Masked Modeling
arXiv:2605.29488v3 Announce Type: replace-cross Abstract: Conditional human motion generation remains a fundamental challenge in computer vision and robotics. Despite significant progress, current methods are often const…
- arXiv cs.AIresearchCan I Take Another Dose? DoseBench: Evaluating LLM Decision-Making in OTC Dosing QA
arXiv:2606.04262v2 Announce Type: replace-cross Abstract: Large language models (LLMs) are increasingly used to answer everyday health questions online, including whether someone can take another dose of an over-the-coun…
- arXiv cs.AIresearchInterpretability Is Not Just a Tax: Sparsity and Diversity Yield Legible and Composable Reward Experts for Personalization
arXiv:2606.04284v2 Announce Type: replace-cross Abstract: Preference modeling aims to capture heterogeneous human values and increasingly relies on learning latent components to represent this variation without fine-grai…
- arXiv cs.AIresearchExecutable Schema Contracts: From Automatic Ingestion to Multi-Source Retrieval
arXiv:2606.05415v2 Announce Type: replace-cross Abstract: Real-world data spans tables, documents, and semi-structured files with implicit semantics. Querying this data requires integrating evidence across inconsistent s…
- arXiv cs.AIresearchSelf-Augmenting Retrieval for Diffusion Language Models
arXiv:2606.06474v2 Announce Type: replace-cross Abstract: Diffusion language models generate text by iteratively denoising an entire response in parallel, holding a noisy draft of the answer at every step. We show that t…
- arXiv cs.AIresearchCode2LoRA: Hypernetwork-Generated Adapters for Code Language Models under Software Evolution
arXiv:2606.06492v2 Announce Type: replace-cross Abstract: Code language models need repository-level context to resolve imports, APIs, and project conventions. Existing methods inject this knowledge as long inputs (retri…
- arXiv cs.AIresearchJANUS: Evaluating Goal-Conditioned Distortion in Factually Grounded LLM Communication
arXiv:2606.10852v2 Announce Type: replace-cross Abstract: LLM deception is often evaluated through fabricated claims, explicit lies, or strategic concealment. Yet misleading communication can also arise from selectively…
- arXiv cs.AIresearchTest-Time Gradient Guidance of Flow Policies in Reinforcement Learning
arXiv:2606.11087v2 Announce Type: replace-cross Abstract: Expressive continuous control policies, such as diffusion and flow models, form the backbone of recent advances in scaling imitation learning for simulated and re…
- arXiv cs.AIresearchFine-tuning Multi-modal LLMs with ART: Art-based Reinforcement Training
arXiv:2606.11854v2 Announce Type: replace-cross Abstract: Adapting Large Language Models (LLMs) to specific tasks usually involves fine-tuning: Low-Rank Adaptation (LoRA) edits the weights, while soft prompting prepends…