https://validator.w3.org/feed/docs/rss2.html AgentWall: A Runtime Safety Layer for Local AI Agents ASTRA: Communication-Efficient Acceleration for Multi-Device Transformer Inference Modernising Reinforcement Learning-Based Navigation for Embodied Semantic Scene Graph Generation RL Squeezes, SFT Expands: A Comparative Study of Reasoning LLMs Beyond the Data Mesh Illusion: Designing Modern AI-augmented Lakehouses to Bridge the Gap Between Theory and Practice Deep-layer limit and stability analysis of the basic forward-backward-splitting induced network (II): learning problems Rethinking Weak Supervision in Anomaly Detection: A Comprehensive Benchmark BrickAnything: Geometry-Conditioned Buildable Brick Generation with Structure-Aware Tokenization Governed Capability Evolution: Lifecycle-Time Compatibility Checking and Rollback for AI-Component-Based Systems, with Embodied Agents as Case Study Where Code Meets Natural Language: Taxonomy-Driven Information Flow Analysis for LLM-Integrated Applications SWAP: Towards Copyright Auditing of Soft Prompts via Sequential Watermarking Vital Trace: Protocol-Constrained Patient-State Reasoning for Longitudinal Clinical Trajectories SSDAU: Structured Semantic Data Augmentation for Joint Entity and Relation Extraction Position: The Turing-Completeness of Autoregressive Transformers Relies Heavily on Context Management Position: Retire the “Positive Backdoor” Label — Secret Alignment Requires Strict and Systematic Evaluation READER: Reasoning-Enhanced AI-Generated Text Detection CausalFlow: Causal Attribution and Counterfactual Repair for LLM Agent Failures A general tensor-structured compression scheme for efficient large language models CoSPlay: Cooperative Self-Play at Test-Time with Self-Generated Code and Unit Test In Search of the Ingredients of Open-Endedness: Replicating Picbreeder with Large Vision-Language Models How Far Can Disaggregation Go? A Design-Space Exploration of Attention-FFN Disaggregation for Efficient MoE LLM Serving Preisach Attention: A Hysteretic Model of Sequential Memory Proxy-Based Approximation of Shapley and Banzhaf Interactions BOHM: Zero-Cost Hierarchical Attribution for Compound AI Systems Atom-level Protein Representation Learning Improves Protein Structure Prediction Cost-Effective Model Evaluation with Meta-Learning From sleep staging to spindle detection: a case study on end-to-end automated sleep analysis Compositional Literary Primitives in Instruction-Tuned LLMs: Cross-Architectural SAE Features for Self, Style, and Affect LIFT and PLACE: A Simple, Stable, and Effective Knowledge Distillation Framework for Lightweight Diffusion Models RoadmapBench: Evaluating Long-Horizon Agentic Software Development Across Version Upgrades Automated ICD Classification of Psychiatric Diagnoses: From Classical NLP to Large Language Models Rebalancing Reference Frame Dominance to Improve Motion in Image-to-Video Models Author Correction: Biophysical prediction of protein–peptide interactions and signaling networks using machine learning Neural operators for free-boundary problems How we’re using AI tools to improve psychedelic-drug research Deep neural operator for free boundary problems Comparative Analysis of Military Detection Using Drone Imagery Across Multiple Visual Spectrums KappaPlace: Learning Hyperspherical Uncertainty for Visual Place Recognition via Prototype-Anchored Supervision PromptRad: Knowledge-Enhanced Multi-Label Prompt-Tuning for Low-Resource Radiology Report Labeling Vision-OPD: Learning to See Fine Details for Multimodal LLMs via On-Policy Self-Distillation MINTEval: Evaluating Memory under Multi-Target Interference in Long-Horizon Agent Systems Metric-Gradient Projection for Stable Multi-Agent Policy Learning Nested Spatio-Temporal Time Series Forecasting Bridging Silicon and the Hippocampus: Algebro-Deterministic Memory “VaCoAl” as a Substrate for Vector-HaSH and TEM BacktestBench: Benchmarking Large Language Models for Automated Quantitative Strategy Backtesting Training data attribution in diffusion models via mirrored unlearning and noise-consistent skew No Free Swap: Protocol-Dependent Layer Redundancy in Transformers D-PACE: Dynamic Position-Aware Cross-Entropy for Parallel Speculative Drafting SOLAR: A Self-Optimizing Open-Ended Autonomous Agent for Lifelong Learning and Continual Adaptation AI cracks 80-year-old mathematics challenge — researchers are astonished