AI news archive.
10,659 articles filed under Research, newest first, from the outlets listed on the sources page.
- arXiv cs.AIresearchTraceForge: Distilling with Your Own Thinking
arXiv:2610.29680v3 Announce Type: replace Abstract: Using an LLM to generate training data for another is among the most general ways to train one, and it remains common practice. Some frontier teams have closed that rou…
- arXiv cs.AIresearchCOMET: A coordinated multi-layer runtime monitoring framework for human-supervised AI-enabled safety systems
arXiv:2610.29816v1 Announce Type: new Abstract: Incorporating AI systems into safety systems requires monitoring to avoid silent faults and ensure safe and reliable operation. Single monitors often do not provide actiona…
- arXiv cs.AIresearchCommit or Abstain? System One Decision Models, LLMs, and Missing Legal Authority
arXiv:2610.29961v1 Announce Type: new Abstract: Given the enormous number of claims to be checked, verifiable legal AI requires scalable, cost-effective models that answer the practical needs of law. System One decision…
- arXiv cs.AIresearchTIDE: Tree-Induced Fine-Grained Diagnostic Evaluation from Model Behaviors
arXiv:2610.29985v1 Announce Type: new Abstract: Benchmark performance is the dominant standard for comparing large language models (LLMs), typically summarized by a single aggregate score, such as accuracy, pass rate, or…
- arXiv cs.AIresearchWhich Differences Matter? Controlled Tests of Rule Transfer, Joint Reliability, and Information Use in Decision Models
arXiv:2610.30045v1 Announce Type: new Abstract: Decision models map stated rules and observed states to discrete answers. Aggregate accuracy leaves unresolved which rule and information changes guide those answers. We co…
- arXiv cs.AIresearchFirst Passage Attention
arXiv:2610.22714v1 Announce Type: cross Abstract: Augmenting softmax attention with forget gates typically relies on summing decay contributions along the key--query path. Because such accumulation is monotonic, these me…
- arXiv cs.AIresearchZero-Cost Detection of Fabricated Citations: A Staged Heuristic Approach for Computing Dissertation Assessment
arXiv:2610.28649v1 Announce Type: cross Abstract: Generative AI's growing role in academic writing has driven a rise in fabricated references across dissertations and student reports. We present the Fabrication Severity…
- arXiv cs.AIresearchThe CIDOC CRM Periodic Table: Documentation You Can Test to Support the Adoption of Scientific Research Ontologies for the Humanities
arXiv:2610.28650v1 Announce Type: cross Abstract: The CIDOC CRM family is not only a schema for museum collections. Its extensions formalise the apparatus through which research knowledge is produced and justified: CRMsc…
- arXiv cs.AIresearchWhat Git Does Not Record: Provenance Legibility in Two AI-Assisted Research Repositories
arXiv:2610.28655v1 Announce Type: cross Abstract: Publishers and funders increasingly ask authors to disclose how AI tools contributed to a piece of research. In computational work the repository is where an author or an…
- arXiv cs.AIresearchFutureLens: Longitudinal Topic Patterns in Scholarly Text and Future-Work References
arXiv:2610.28656v1 Announce Type: cross Abstract: Future-work statements offer a record of the questions researchers choose to leave open. Using them to describe a field, however, requires separating thematic change from…
- arXiv cs.AIresearchBeyond source attribution: Address authorship and comparability decisions in an LLM-built scholarly knowledge graph
arXiv:2610.28663v1 Announce Type: cross Abstract: A knowledge graph needs a stable address for its evidence even where the literature offers competing classifications and agrees on none. Yet an address chosen for retriev…
- arXiv cs.AIresearchLearning Checklists to Reduce Lottery Effects in Scientific Peer Review
arXiv:2610.28666v1 Announce Type: cross Abstract: Reviewer lottery error describes error due to a small set of peer reviews attending to only some of the issues with a paper that a larger pool of eligible reviewers would…
- arXiv cs.AIresearchVHDLBench: Benchmarking and Fine-Tuning Large Language Models for VHDL-Based Chip Design
arXiv:2610.28676v1 Announce Type: cross Abstract: The rapid evolution of digital circuit complexity demands innovative approaches to hardware design automation. While Large Language Models (LLMs) have influenced software…
- arXiv cs.AIresearchInteraction-Gated Time-Frequency Learning for Parameter-Efficient PPG-Based Heart Rate Estimation
arXiv:2610.28693v1 Announce Type: cross Abstract: Photoplethysmography (PPG) enables low-cost and non-invasive heart rate (HR) monitoring but remains sensitive to waveform distortion, physiological variability, and measu…
- arXiv cs.AIresearchSTAR-XPC: Set Transformer for Estimating X-ray Transmission in Polymer Composites
arXiv:2610.28709v1 Announce Type: cross Abstract: Evaluating the energy transmission ratio of an X-ray beam through a polymer composite is a challenging task in radiation shielding studies. The reference solution with Mo…
- arXiv cs.AIresearchOffline Apprenticeship Learning for Human-Centric Environments
arXiv:2610.28716v1 Announce Type: cross Abstract: Effective decision-making in human-centric environments such as Intelligent Tutoring Systems (ITSs) and clinical healthcare requires policies that are adaptive, data-effi…
- arXiv cs.AIresearchGPU-Accelerated Construction of the Gabriel Graph: Parallelization Strategies and Applications to Large-Margin Classification and Graph-Based Clustering
arXiv:2610.28759v1 Announce Type: cross Abstract: The Gabriel graph is a proximity graph widely used in computational geometry and geometric machine learning, underlying large-margin classifiers and, as we show in this w…
- arXiv cs.AIresearchSkillEval: Learning Interpretable Ability Profiles of LLMs via Cognitive Diagnosis Models
arXiv:2610.28767v1 Announce Type: cross Abstract: Current evaluation of LLMs on benchmarks typically aggregates performance over individual examples into a single scalar score. This approach is overly coarse and ignores…
- arXiv cs.AIresearchReAPO: Retry-Aware Policy Optimization for Efficient Exploration in LLM Reasoning
arXiv:2610.28770v1 Announce Type: cross Abstract: RLVR improves language-model reasoning, but commonly relies on independent stochastic rollouts for exploration, which can repeatedly sample similar failed strategies. Pri…
- arXiv cs.AIresearchArcFlow: Training Flow Policies for Multiple Solver Budgets
arXiv:2610.28788v1 Announce Type: cross Abstract: Flow-matching policies adjust inference cost through the number of solver steps, but reinforcement learning at a single fixed solver budget can hide degradation at cheape…
- arXiv cs.AIresearchCALLIOPE: Private Insights into AI Use, Without Embeddings
arXiv:2610.28797v1 Announce Type: cross Abstract: We introduce CALLIOPE, a top-down framework for discovering topic hierarchies in large corpora of unstructured data (e.g., LLM conversations), while supporting differenti…
- arXiv cs.AIresearchTowards Realistic Models of Change: A Causal Perspective on Decision-Making and Dynamical Systems
arXiv:2610.28803v1 Announce Type: cross Abstract: While statistical learning has made remarkable progress in recent decades, driven by large datasets and data-driven protocols that have transformed scientific practice, i…
- arXiv cs.AIresearchCombining Long-Term Memory and LLMs Comes at a High Cost: From Prompt Injection to Persistent Compromise
arXiv:2610.28810v1 Announce Type: cross Abstract: The widespread adoption of generative artificial intelligence in recent years has brought a parallel rise in prompt injection and jailbreak attacks. By embedding maliciou…
- arXiv cs.AIresearchBrittle by Design? Multi-Scenario Reinforcement Learning for Robust Mission Coordination in Systems of Systems
arXiv:2610.28818v1 Announce Type: cross Abstract: As systems engineering (SE) shifts from monolithic systems to Systems of Systems, Mission Engineering (ME) has emerged as a new line of thinking in SE. Mission environmen…
- arXiv cs.AIresearchHow to Use Parallel Data for Multilingual Pretraining
arXiv:2610.28838v1 Announce Type: cross Abstract: High-quality human-translated parallel corpora can improve cross-lingual transfer, but are typically too small for large-scale pretraining. Machine-translated web corpora…
- arXiv cs.AIresearchWhen Do Gaussian Priors Fail? A Latent Geometry Investigation of RL Fine-Tuning
arXiv:2610.28849v1 Announce Type: cross Abstract: Latent diffusion models almost universally place a Gaussian prior on the VAE latent space. For base generation this default is unproblematic; under reinforcement-learning…
- arXiv cs.AIresearchDualHeads: Reward-tilted few-step diffusion made simple
arXiv:2610.28858v1 Announce Type: cross Abstract: Distilled diffusion models generate high-quality images in a few sampling steps, but aligning them with task requirements and human preferences is difficult. Methods deve…
- arXiv cs.AIresearchA General Topological Symmetry Index for Critical Orbits In Neural Network Loss Landscapes
arXiv:2610.28864v2 Announce Type: replace-cross Abstract: A systematic understanding of the global structure of neural-network loss landscapes remains challenging due to their high dimensionality. Symmetries arising from…
- arXiv cs.AIresearchinr2action: Encoding Robot Episodes as Neural Implicit Representations for Recall and Action
arXiv:2610.28882v1 Announce Type: cross Abstract: Long-horizon robotic operation requires memory that scales with essential information rather than execution time. We present a parameter-space memory framework where each…
- arXiv cs.AIresearchRL-IF: Tracking Non-local Training Data Influence for Online Reinforcement Learning
arXiv:2610.28883v1 Announce Type: cross Abstract: Online reinforcement learning (RL) has achieved significant success in decision-making tasks, but modern online RL remains highly sensitive to the quality of training exp…
- arXiv cs.AIresearchSANE: Automated Scorer-Specific Metamorphic Testing for LLM Judges
arXiv:2610.28886v2 Announce Type: replace-cross Abstract: LLM judges increasingly mediate benchmark evaluation, model selection, data curation, and training. Their decisions are useful only when each judge responds relia…
- arXiv cs.AIresearchStyleStream 2.0: Fast and Controllable Streaming Voice Style Conversion
arXiv:2610.28940v1 Announce Type: cross Abstract: Voice style conversion (VSC) aims to transform a source utterance to match the timbre, accent, and emotion of a target voice while preserving linguistic content. StyleStr…
- arXiv cs.AIresearchHyperDrone: Simulation-to-Reality Transfer at Millions of Frames per Second
arXiv:2610.28950v1 Announce Type: cross Abstract: We present HyperDrone, an extremely fast quadrotor simulator focused on high-performance batch rendering that is more than 20x faster than existing state-of-the-art batch…
- arXiv cs.AIresearchSLoSa: Small, Low-Power, and Safe Foundation Models for Robotic Task Planning
arXiv:2610.28955v1 Announce Type: cross Abstract: Safe robotic task planning requires planners that can reliably achieve task goals while satisfying safety constraints. Classical planners search over explicit symbolic ta…
- arXiv cs.AIresearchCan Quantum Layers offer Performance and Security Advantages in Vision-Language Models?
arXiv:2610.28964v1 Announce Type: cross Abstract: As quantum computing moves from the noisy intermediate-scale quantum (NISQ) era toward early fault-tolerant quantum computing (EFTQC), quantum-enhanced AI is shifting fro…
- arXiv cs.AIresearchUnit-Aware Differentially Private Quantum Machine Learning for Clinical and Wearable Health Data
arXiv:2610.28968v1 Announce Type: cross Abstract: Clinical registries and wearable sensors support early health-risk assessment, yet models trained on these records may leak sensitive information when released. Different…
- arXiv cs.AIresearchFrom Weather to Enhanced Weathering: Weather Foundation Models for Carbon Dioxide Removal at Operational Scale
arXiv:2610.28973v1 Announce Type: cross Abstract: Enhanced Rock Weathering (ERW) is a carbon removal solution with the potential to remove gigatons of CO$_2$ per year, but quantifying that removal today requires dense so…
- arXiv cs.AIresearchSSMCGM-Stream: A Streaming State-Space Model for Personalized Diabetes Management
arXiv:2610.28976v1 Announce Type: cross Abstract: Continuous glucose monitoring supports diabetes management but requires forecasting models that are accurate, interpretable, and efficient enough for real-time deployment…
- arXiv cs.AIresearchRethinking Time Series Tokenization from a Frequency Perspective
arXiv:2610.28997v2 Announce Type: replace-cross Abstract: Tokenization that partitions time series into subsequences has become a foundational paradigm in modern time series modeling. However, we find that current tokeni…
- arXiv cs.AIresearchEnhancing Cross-Grade Generalization in Banana Variety Classification via Hybrid CNN-Transformers and Knowledge Self-Distillation
arXiv:2610.29008v1 Announce Type: cross Abstract: In recent years, automated fruit classification systems have become a more critical component in precision agriculture for efficient yield estimation, quality control, an…
- arXiv cs.AIresearchPHD-Hand: A Printable Humanoid Dexterous Hand with Linkage-Driven 3-DOA Digits
arXiv:2610.29030v1 Announce Type: cross Abstract: Currently, dexterous humanoid robot hands are widely considered the final hardware bottleneck that hampers generalist robots from physically assisting people at home and…
- arXiv cs.AIresearchHumanCentric-Scenes-AI: A Human-Curated Multimodal Dataset of AI-Generated Human-Centric Scenes Across Surveillance, Occupational Portraits, AI-Edited Images, and Short-Form Video
arXiv:2610.29045v1 Announce Type: cross Abstract: We introduce HumanCentric-Scenes-AI, a human-curated dataset of 296 AI-generated stimuli that depict people across four contexts in which people encounter AI-generated me…
- arXiv cs.AIresearchOur Own Jev: Typed Decisions in One Forward Pass, from an In-House Judge to Open LoRA Models
arXiv:2610.29052v1 Announce Type: cross Abstract: A typed decision maps evidence, a question and a fixed set of options to a probability for every option, computed in one forward pass, by reading a language model's logit…
- arXiv cs.AIresearchDistilling Multi-Teacher Scoring Principles for Unsupervised Time Series Anomaly Detection
arXiv:2610.29063v1 Announce Type: cross Abstract: Time series anomalies take diverse forms, and individual detectors encode different anomaly scoring principles that rarely cover all anomaly types. Recent unsupervised ti…
- arXiv cs.AIresearchA Large-Scale Evaluation of Role-Enhanced Zero-Shot Chain-of-Thought Prompting
arXiv:2610.29073v1 Announce Type: cross Abstract: This paper proposes Role-Enhanced Zero-Shot Chain-of-Thought (RE-ZS-CoT), a prompting framework that systematically integrates domain-specific expert roles to enhance rea…
- arXiv cs.AIresearchValue-Rectified Distillation for Flow-based Offline Reinforcement Learning
arXiv:2610.29075v2 Announce Type: replace-cross Abstract: We aim to address the problem of Out-of-Distribution (OOD) Mode Averaging, a critical problem that emerges when distilling Flow Matching (FM) based behavior polic…
- arXiv cs.AIresearchReSeg: Retraining-free segmentation of abdominal organs via generalizable semantic representation learning
arXiv:2610.29090v1 Announce Type: cross Abstract: Abdominal organ segmentation is essential in modern medical applications. While existing deep learning approaches demonstrate promising performance, their heavy reliance…
- arXiv cs.AIresearchUNIVERS: Learning UNIversal Voxel-wise Embedding via Randomized Synthesis for generalizable one-shot landmark localization
arXiv:2610.29098v1 Announce Type: cross Abstract: One-shot landmark localization in volume scans with varying fields of view (FOVs) is challenging. While existing self-supervised learning methods have shown promising per…
- arXiv cs.AIresearchDual-Channel Contrastive Encoding of Sperm Whale Coda
arXiv:2610.29101v1 Announce Type: cross Abstract: Sperm whales (Physeter macrocephalus) communicate through short click sequences called codas, whose structure includes the rhythmic pattern of inter-click intervals (ICI)…
- arXiv cs.AIresearchAn Eco-Friendly Tourism Trip Planner Driven by Z-Number Uncertainty: Evidence from Baku, Dubai, Abu Dhabi, Tashkent, and Istanbul
arXiv:2610.29120v2 Announce Type: replace-cross Abstract: Deployed tourism trip planners ingest travel times and ratings as exact numbers, although routing services return travel times that vary with the hour of departur…