Provide.ai https://validator.w3.org/feed/docs/rss2.html Measuring What Matters: Benchmarking Generative, Multimodal, and Agentic AI in Healthcare ASD-Bench: A Four-Axis Comprehensive Benchmark of AI Models for Autism Spectrum Disorder ROMER: Expert Replacement and Router Calibration for Robust MoE LLMs on Analog Compute-in-Memory Systems Active inference as a unified model of collision avoidance behavior in human drivers Auditing Data Membership in Reinforcement Learning With Verifiable Rewards DARLING: Detection Augmented Reinforcement Learning with Non-Stationary Guarantees Correcting Selection Bias in Sparse User Feedback for Large Language Model Quality Estimation: A Multi-Agent Hierarchical Bayesian Approach STL-Based Motion Planning and Uncertainty-Aware Risk Analysis for Human-Robot Collaboration with a Multi-Rotor Aerial Vehicle LLM-Augmented Chemical Synthesis and Design Decision Programs LLM-guided Semi-Supervised Approaches for Social Media Crisis Data Classification Enabling Performant and Flexible Model-Internal Observability for LLM Inference GEAR: Granularity-Adaptive Advantage Reweighting for LLM Agents via Self-Distillation Alignment as Jurisprudence RoboBlockly Studio: Conversational Block Programming with Embodied Robot Feedback for Computational Thinking Relational In-Context Learning via Synthetic Pre-training with Structural Prior Hyperbolic Concept Bottleneck Models Mitigating Context-Memory Conflicts in LLMs through Dynamic Cognitive Reconciliation Decoding Rollbot: a Spherical Robot Driven by a Single Actuator Newton’s Lantern: A Reinforcement Learning Framework for Finetuning AC Power Flow Warm Start Models StepCodeReasoner: Aligning Code Reasoning with Stepwise Execution Traces via Reinforcement Learning SHIELD: Scalable Optimal Control with Certification using Duality and Convexity AI Alignment via Incentives and Correction Clin-JEPA: A Multi-Phase Co-Training Framework for Joint-Embedding Predictive Pretraining on EHR Patient Trajectories Mechanistic Interpretability of ASR models using Sparse Autoencoders SOAR: Regression-based LiDAR Relocalization for UAVs Mid-Training with Self-Generated Data Improves Reinforcement Learning in Language Models GRAFT-ATHENA: Self-Improving Agentic Teams for Autonomous Discovery and Evolutionary Numerical Algorithms SkillSafetyBench: Evaluating Agent Safety under Skill-Facing Attack Surfaces Kairos: A Scalable Serving System for Physical AI Approximating Simple ReLU Networks based on Spectral Decomposition of Fisher Information Combining On-Policy Optimization and Distillation for Long-Context Reasoning in Large Language Models MonitoringBench: Semi-Automated Red-Teaming for Agent Monitoring Efficient Emotion-Aware Iconic Gesture Prediction for Robot Co-Speech Language Modeling with Hyperspherical Flows Design Your Ad: Personalized Advertising Image and Text Generation with Unified Autoregressive Models Distributed Pose Graph Optimization via Continuous Riemannian Dynamics Feedback Lunch: Learned Feedback Codes for Secure Communications Mind the Pause: Disfluency-Aware Objective Tuning for Multilingual Speech Correction with LLMs Computational Design of a Low-Visibility UAV Using a Human-Aligned Perceptual Metric AI-Care: A Conversational Agentic System for Task Coordination in Alzheimer’s Disease Care HEPA: A Self-Supervised Horizon-Conditioned Event Predictive Architecture for Time Series Not How Many, But Which: Parameter Placement in Low-Rank Adaptation Forecast-aware Gaussian Splatting for Predictive 3D Representation in Language-Guided Pick-and-Place Manipulation Efficient Remote KV Cache Reuse with GPU-native Video Codec PreScam: A Benchmark for Predicting Scam Progression from Early Conversations ASIP-Planner: Adaptive Planning for UAV Surface Inspection in Partially Known Indoor Environments Steerable Neural ODEs on Homogeneous Spaces Predicting Decisions of AI Agents from Limited Interaction through Text-Tabular Modeling SEVO: Semantic-Enhanced Virtual Observation for Robust VLA Manipulation via Active Illumination and Data-Centric Collection UFO: A Unified Flow-Oriented Framework for Robust Continual Graph Learning