https://validator.w3.org/feed/docs/rss2.html A unified framework for global and local interpretability using adaptive derivative-ordered random explanation GYROval: A Robust Benchmark for Cultural Value Orientation in Large Language Models Reliable Virtual Sensing: A Multi-Domain Benchmark for Robustness Under Sensor Failures Cross-Modal Attention Acts as a Frequency Filter: Why Verbose Prompts Improve Robustness in Vision-Language Models Dreaming the Sound of Contact: Leveraging Video and Audio Generation for Zero-Shot Force-Aware Manipulation and Data Generation Regularized Emphatic Temporal-Difference Learning: Stability under Constant Stepsizes Vroom-Vroom at SHROOM-Visions: A Multi-Judge Committee for Detecting Hallucinated Spans in Vision-Language Outputs Making AI-Assisted Claims Independently Challengeable: Publication Authority and a Protocol for Falsifiable Publication Records A Conservative OCR-Enabled Workflow for R214 Sodium Screening of South African Packaged Foods What Breaks Local Watermarks? A Robustness Benchmark for Local Invisible Image Watermarking StackTok: Accelerating VLMs Inference with Budget-Adaptive Visual Token Selection K-Bench: a clinically calibrated benchmark for evaluating large language models in high-risk mental health conversations Optimal Pruning for Neural Architectures using Fisher Information Distances ActSafeGuard: Differentiable and Training-Aligned Constraint Enforcement for Flow-Matching Policies LiftGCN: Efficient Energy-Preserving Graph Learning via Joukowski Spectral Lifting for Finite Element Stress Prediction ActGuard: Pre-execution Action Auditing against Indirect Prompt Injection in LLM Agents Evaluating Context Segmentation in Locally Deployable SLMs for Cybersecurity CTF Tasks ZGCM-1: A Fully Open and Extremely Efficient Foundation Model for Math and Agentic Search Publisher Correction: Quantum neural operators with implicit quadratic frame and expressivity advantages scTransMIL bridges patient-level disease states and single-cell transcriptomics for cancer screening and heterogeneity inference Drug firms’ secret data supercharge AI protein models The Einstein test: what happens when AI tries to rediscover relativity? AdaRepair-Mem: Adaptive Experience Orchestration for Repository-Level Program Repair Use AI as a sparring partner, not an oracle ‘Multifunctional’ brain implant translates speech and gestures in real time Edu-QuRating: Multi-Dimensional Educational Data Curation with Distilled Pairwise Judgements Buyer Artificial Intelligence-Enabled Environmental Governance and Supplier Environmental Controversies: An Organizational Information Processing and Signaling PACE: Perceived-Latency-Aware Cascading Service Routing and Filler Control for QoE-Efficient Retrieval-Augmented Dialogue Serving Probabilistic Focal Search: Accelerating Bounded-Suboptimal Search via Lower-Bound Advancement SAFER-Activities: A Dataset for Smart Assessment of Fall Events and Routine Activities MetroLLM-Bench: Evaluating Language Models as Transit Kiosk Runtimes Elastoformer: Enabling Dynamic Adaptivity via Elastic Model Transformation Omni Interaction Agent Technical Report OpenDiscoveryTrace: Process Traces for Evaluating AI Scientist Workflows MCPO: Modality-Contrastive Preference Optimization for Multimodal Chain-of-Thought Compression Explainable data generation from observed small samples by matrix tri-factorization Quantifying the Engagement Trap: Impact of Short-form Video Recommender Systems on Users with ADHD Climate-ModernBERT: Revisiting Corpus Composition for Domain-Adaptive Continued Pretraining Ask Before You Optimize: Dynamic Pre-Formulation Clarification for Interactive Optimization Beyond Right and Wrong: Evaluating Second-order Social Reasoning in Large Language Models When pathology segmentation learns to listen Segment anything in pathology images with natural language A clinically-oriented foundation model for intraoperative pathology A collaborative agent with two lightweight synergistic models for autonomous crystal materials research Briefing Chat: The Bunsen burner myth that turns out to be just hot air Breaking timescales with generative sampling of conformational transitions VikingRAG: Accurate and Token-efficient Retrieval-augmented Generation over Structured Documents Predicting genome-wide functional constraints with GPN-Star AI model predicts which breast-cancer drugs work best CSWAM: Better Causal Semantic Representations for Out-of-Distribution Generalization in World Action Models