https://validator.w3.org/feed/docs/rss2.html Reference-Sampled Boltzmann Projection for KL-Regularized RLVR: Target-Matched Weighted SFT, Finite One-Shot Gaps, and Policy Mirror Descent Core-Halo Decomposition: Decentralizing Large-Scale Fixed-Point Problems AsymTalker: Identity-Consistent Long-Term Talking Head Generation via Asymmetric Distillation Reusability report: Meta-learning for antigen-specific T cell receptor binder identification Governing AI-Assisted Security Operations: A Design Science Framework for Operational Decision Support One Token Per Frame: Reconsidering Visual Bandwidth in World Models for VLA Policy Operating Within the Operational Design Domain: Zero-Shot Perception with Vision-Language Models Towards Billion-scale Multi-modal Biometric Search A fully automated framework for acoustic identification and localization of terrestrial wildlife at scale Asymmetric On-Policy Distillation: Bridging Exploitation and Imitation at the Token Level The Endogeneity of Miscalibration: Impossibility and Escape in Scored Reporting AI CFD Scientist: Toward Open-Ended Computational Fluid Dynamics Discovery with Physics-Aware AI Agents GraphDC: A Divide-and-Conquer Multi-Agent System for Scalable Graph Algorithm Reasoning The E$Delta$-MHC-Geo Transformer: Adaptive Geodesic Operations with Guaranteed Orthogonality Gradient Extrapolation-Based Policy Optimization Rubric-Grounded RL: Structured Judge Rewards for Generalizable Reasoning Tacit Knowledge Extraction via Logic Augmented Generation and Active Inference Structured Progressive Knowledge Activation for LLM-Driven Neural Architecture Search Schedule-and-Calibrate: Utility-Guided Multi-Task Reinforcement Learning for Code LLMs Dynamic Pondering Sparsity-aware Mixture-of-Experts Transformer for Event Stream based Visual Object Tracking Continual Knowledge Updating in LLM Systems: Learning Through Multi-Timescale Memory Dynamics Understanding Annotator Safety Policy with Interpretability RNA design across eras: from covariance models to modern generative AI AI Inference as Relocatable Electricity Demand: A Latency-Constrained Energy-Geography Framework The Single-File Test: A Longitudinal Public-Interface Evaluation of First-Output LLM Web Generation with Social Reach Tracking Decoupled Guidance Diffusion for Adaptive Offline Safe Reinforcement Learning Social Bias in LLM-Generated Code: Benchmark and Mitigation Revisiting Graph-Tokenizing Large Language Models: A Systematic Evaluation of Graph Token Understanding Enhancing Judgment Document Generation via Agentic Legal Information Collection and Rubric-Guided Optimization CreativityBench: Evaluating Agent Creative Reasoning via Affordance-Based Tool Repurposing Conventional Commit Classification using Large Language Models and Prompt Engineering Silicon Showdown: Performance, Efficiency, and Ecosystem Barriers in Consumer-Grade LLM Inference 2026 Roadmap on Artificial Intelligence and Machine Learning for Smart Manufacturing Unsupervised Learning of Robust Spectral Shape Matching IConFace: Identity-Structure Asymmetric Conditioning for Unified Reference-Aware Face Restoration VeRO: An Evaluation Harness for Agents to Optimize Agents Boundary Mass and the Soft-to-Hard Limit in Mixture-of-Experts From Intent to Execution: Composing Agentic Workflows with Agent Recommendation Agentic-imodels: Evolving agentic interpretability tools via autoresearch Quantifying the human visual exposome with vision language models Self-Improvement for Fast, High-Quality Plan Generation OracleProto: A Reproducible Framework for Benchmarking LLM Native Forecasting via Knowledge Cutoff and Temporal Masking Artificial intelligence for predicting transient hypocalcemia after total thyroidectomy Learning the chemical language of natural products Platonic representation of foundation machine learning interatomic potentials AdaMeZO: Adam-style Zeroth-Order Optimizer for LLM Fine-tuning Without Maintaining the Moments Parametrizing Convex Sets Using Sublinear Neural Networks Reinforcement Learning with Markov Risk Measures and Multipattern Risk Approximation Claw-Eval-Live: A Live Agent Benchmark for Evolving Real-World Workflows SpecKV: Adaptive Speculative Decoding with Compression-Aware Gamma Selection