https://validator.w3.org/feed/docs/rss2.html A Blind Spot in Alignment: Quantifying Biosecurity Risks in Large Language Models Guideline-as-Oracle: Zero-Annotation Training of an Ophthalmic Telephone Triage Agent SMOPD: Multi-Reward Reinforcement Learning via Specialize-and-Merge Online Policy Distillation GPTKB 2.0: Direct Construction of Disambiguated Knowledge Bases from Large Language Models LEAP: Lean Environment-Feedback via Adaptive Pruning for Code RL in GPU Kernel Generation MRICombo: a deep-learning-based framework for universal volumetric segmentation grading-staging and malignancy detection across heterogeneous MRI Machine learning-based classification of diabetes mellitus using sociodemographic, behavioral, and clinical predictor HarnessSafe: Evaluating Safety Across Persistent Carriers in Agent Harnesses Audio-to-Score Transcription using Pre-trained Features, Data Augmentation, and the New SheetSage-A2S Dataset Towards Multi-Label Graph Foundation Models: from Single-Vector Representation Learning to Multi-Semantic Basis Learning RepoProbe: Benchmarking Architecture-Aware Repository Comprehension with Checklists Answer First, Reason Later: Commitment Order in Diffusion LLMs IMFACT: Counterfactual Explanations for Time Series via Intrinsic Mode Function Substitution Spectral Aliasing Pretext: A novel task for Self-Supervised fault diagnosis in rotating machinery AI-based augmentation of oncology clinical trials A Long-Run Persistence Theory for AI Systems under the Redundancy-Adjusted Artificial Age Score (AAS) OPD-V: Visual On-Policy Self-Distillation with Modality Balance Inference of tumor spatial habitats AI agents are checking the scientific literature — and spotting decades-old errors Agentic Nesting: A New Methodology for Existing Enterprise Application Integration and Services FakeI2V-Bench: Benchmarking the Applicability of Image-level Deepfake Detectors for Deepfake Video Detection PhyCheck: Fine-Grained Evidence-Grounded Dataset for Physical Law Understanding in Video-LLMs ISEE: Interactive Semantic Enrichment for Database Fields The Virtual Tissues foundation model resolves spatial proteomics across scales Trajectory forecasting lifts the femtosecond ceiling in molecular simulation Dynamic feature pyramid network for real-time gesture recognition Deep-learning-enabled multi-omics analyses for prediction of future metastasis in cancer LabEvolver: Training-Free Experience Evolution for Safe and Grounded Wet-Lab Agents Stable Autoregressive Speech Generation with Low-Frame-Rate High-Dimensional Continuous Tokens Dense Temporal Contrast Synthesis via Conditioned Latent Transport On a joint simultaneous learning of relevant feature subsets and subspaces in regression-like problems OpenClaw and Ollama in Agentic AI: Toward Fully Autonomous and Scalable AI Agent Systems Tools Are Not Islands: Set-Level Tool Retrieval for LLM Agents via Query-Conditioned Hyperedge Prediction SymmGrid: Super-Scaling On-Robot Learning with Parallelized Symmetries and Egocentric-Exocentric Visual Perception PatientAgentBench: A Benchmark Framework for Evaluating Patient-Facing Health AI Agents PHASE-Tree: Modeling Character-State Evolution in Long-Horizon Role-Playing Dialogue BayesAME: Bayesian Active Model Evaluation Knowledge-Guided Multimodal Reasoning over Interacting Streams for Video-Level Ambivalence and Hesitancy Recognition Probing the Origins of Reasoning Performance: Representational Quality for Mathematical Problem-Solving in RL vs. SFT Fine-Tuned Models A machine learning framework for predicting and modulating condition-dependent protein phase separation Learning from routine health system data builds better neuroimaging AI models Unify learns cellular evolution with universal multimodal embeddings Scientists using LLMs will ‘do more, less well’, modelling study predicts Continual integration of single-cell multimodal data with MIRACLE Deep learning prediction of left atrial structure and function from 12-lead electrocardiograms Matrix-Free Photoacoustic Image Reconstruction via Sensor-Token Self-Attention Evaluating Communicative Belief Updates in Large Language Models via Implicature Recognition and Cancellation Toward Standardized Cross-Vendor Agent Tool Trust Management in Autonomous Networks Inferring Missing Trajectory Data with Temporal Convolutional Networks HyTBE: Hyperbolic Target-Background Expert Model for Cross-Domain Infrared Small Target Detection