首页 > 开发 > Hugging Face Hugging Face 共 4381 条资讯 SeePhys Pro: Diagnosing Modality Transfer and Blind-Training Effects in Multimodal RLVR for Physics Reasoning LoopUS: Recasting Pretrained LLMs into Looped Latent Refinement Models RubricEM: Meta-RL with Rubric-guided Policy Decomposition beyond Verifiable Rewards Teaching Language Models to Think in Code Continual Harness: Online Adaptation for Self-Improving Foundation Agents Agent-ValueBench: A Comprehensive Benchmark for Evaluating Agent Values The Many Faces of On-Policy Distillation: Pitfalls, Mechanisms, and Fixes FocuSFT: Bilevel Optimization for Dilution-Aware Long-Context Fine-Tuning Towards On-Policy Data Evolution for Visual-Native Multimodal Deep Search Agents δ-mem: Efficient Online Memory for Large Language Models Reward Hacking in Rubric-Based Reinforcement Learning Geometric Factual Recall in Transformers AlphaGRPO: Unlocking Self-Reflective Multimodal Generation in UMMs via Decompositional Verifiable Reward SenseNova-U1: Unifying Multimodal Understanding and Generation with NEO-unify Architecture MEME: Multi-entity & Evolving Memory Evaluation VidSplat: Gaussian Splatting Reconstruction with Geometry-Guided Video Diffusion Priors Beyond the Last Layer: Multi-Layer Representation Fusion for Visual Tokenization CausalCine: Real-Time Autoregressive Generation for Multi-Shot Video Narratives ToolCUA: Towards Optimal GUI-Tool Path Orchestration for Computer Use Agents L2P: Unlocking Latent Potential for Pixel Generation « 上一页1…9899100101102…220下一页 » 相关分类 Hugging Face 51CTO ADGuider Android Police Android Weekly Update Android开发技术周报 Blow Studio Blur Studio CSDN CSDN博客 CSDN资讯 CSS-Tricks DEV Community