Provide.ai https://validator.w3.org/feed/docs/rss2.html DUET: Optimizing Training Data Mixtures via Feedback from Unseen Evaluation Tasks Know When To Fold ‘Em: Token-Efficient LLM Synthetic Data Generation via Multi-Stage In-Flight Rejection MahaVar: OOD Detection via Class-wise Mahalanobis Distance Variance under Neural Collapse Separating Intrinsic Ambiguity from Estimation Uncertainty in Deep Generative Models for Linear Inverse Problems ViMU: Benchmarking Video Metaphorical Understanding A Problem-Oriented Taxonomy of Evaluation Metrics for Time Series Anomaly Detection Conformal Thinking: Risk Control for Reasoning on a Compute Budget SemaTune: Semantic-Aware Online OS Tuning with Large Language Models Higher-order Linear Attention The Pitfalls of KV Cache Compression R-DMesh: Video-Guided 3D Animation via Rectified Dynamic Mesh Flow Learning Developmental Scaffoldings to Guide Self-Organisation Stochastic dynamics learning with state-space systems Krause Synchronization Transformers SkillFlow: Flow-Driven Recursive Skill Evolution for Agentic Orchestration What if Tomorrow is the World Cup Final? Counterfactual Time Series Forecasting with Textual Conditions An Interpretable Latency Model for Speculative Decoding in LLM Serving A New Framework for Convex Clustering in Kernel Spaces: Finite Sample Bounds, Consistency and Performance Insights Learning Polyhedral Conformal Sets for Robust Optimization CalibAnyView: Beyond Single-View Camera Calibration in the Wild Small, Private Language Models as Teammates for Educational Assessment Design BRIDGE: Building Representations In Domain Guided Program Synthesis It Takes Two: Your GRPO Is Secretly DPO ChromaFlow: A Negative Ablation Study of Orchestration Overhead in Tool-Augmented Agent Evaluation On the Burden of Achieving Fairness in Conformal Prediction EMA: Efficient Model Adaptation for Learning-based Systems Do We Really Need External Tools to Mitigate Hallucinations? SIRA: Shared-Prefix Internal Reconstruction of Attribution Collaborative Yet Personalized Policy Training: Single-Timescale Federated Actor-Critic TFGN: Task-Free, Replay-Free Continual Pre-Training Without Catastrophic Forgetting at LLM Scale Beyond the Final Answer: Evaluating the Reasoning Trajectories of Tool-Augmented Agents Orchard: An Open-Source Agentic Modeling Framework Training-Free Generative Sampling via Moment-Matched Score Smoothing ScaLoRA: Optimally Scaled Low-Rank Adaptation for Efficient High-Rank Fine-Tuning XTinyU-Net: Training-Free U-Net Scaling via Initialization-Time Sensitivity Achieving Approximate Symmetry Is Exponentially Easier than Exact Symmetry Non-Stationary Online Structured Prediction with Surrogate Losses Modeling Bounded Rationality in Drug Shortage Pharmacists Using Attention-Guided Dynamic Decomposition Pause and Reflect: Conformal Aggregation for Chain-of-Thought Reasoning Towards the Next Frontier of LLMs, Training on Private Data: A Cross-Domain Benchmark for Federated Fine-Tuning UniTriGen: Unified Triplet Generation of Aligned Visible-Infrared-Label for Few-Shot RGB-T Semantic Segmentation Case-Based Calibration of Adaptive Reasoning and Execution for LLM Tool Use FrontierSmith: Synthesizing Open-Ended Coding Problems at Scale DiffusionOPD: A Unified Perspective of On-Policy Distillation in Diffusion Models Catching the Infection Before It Spreads: Foresight-Guided Defense in Multi-Agent Systems To discretize continually: Mean shift interacting particle systems for Bayesian inference EvolveMem:Self-Evolving Memory Architecture via AutoResearch for LLM Agents CUICurate: A GraphRAG-based Framework for Automated Clinical Concept Curation for NLP applications MAPLE: Self-Supervised Learning-Enhanced Nonlinear Dimensionality Reduction for Visual Analysis AMiD: Knowledge Distillation for LLMs with $\alpha$-mixture Assistant Distribution MultiEmo-Bench: Multi-label Visual Emotion Analysis for Multi-modal Large Language Models