25 days agoHugging Face Daily PapersVisualToolAgent (VisTA): A Reinforcement Learning Framework for Visual Tool Selection
25 days agoHugging Face Daily PapersMotionPro: A Precise Motion Controller for Image-to-Video Generation
25 days agoHugging Face Daily PapersAlita: Generalist Agent Enabling Scalable Agentic Reasoning with Minimal Predefinition and Maximal Self-Evolution
25 days agoHugging Face Daily PapersVLM-3R: Vision-Language Models Augmented with Instruction-Aligned 3D Reconstruction
25 days agoHugging Face Daily PapersThe Coverage Principle: A Framework for Understanding Compositional Generalization
25 days agoHugging Face Daily PapersOmni-R1: Reinforcement Learning for Omnimodal Reasoning via Two-System Collaboration
25 days agoHugging Face Daily PapersPosition: Mechanistic Interpretability Should Prioritize Feature Consistency in SAEs
25 days agoHugging Face Daily PapersFLAME-MoE: A Transparent End-to-End Research Platform for Mixture-of-Experts Language Models
25 days agoHugging Face Daily PapersAdaptive Classifier-Free Guidance via Dynamic Low-Confidence Masking
25 days agoHugging Face Daily PapersHard Negative Contrastive Learning for Fine-Grained Geometric Understanding in Large Multimodal Models
25 days agoAI News CN (Telegram) - English TranslationEnterprises have been applying generative AI to employee training and assessment, etc.
25 days agoHugging Face Daily PapersStructEval: Benchmarking LLMs' Capabilities to Generate Structural Outputs
25 days agoHugging Face Daily PapersLarge Language Models Meet Knowledge Graphs for Question Answering: Synthesis and Opportunities