Hugging Face's logo
Activity Feed

AI & ML interests

None defined yet.

Recent Activity
FlippyDora  submitted a paper 3 days ago
Predictive Divergence Masks for LLM RL
zhouxiangxin  authored a paper 5 days ago
Stale but Stable: Staleness-Adaptive Trust Regions for Stabilizing Asynchronous Reinforcement Learning
zhouxiangxin  authored a paper 5 days ago
MeanFlowNFT: Bringing Forward-Process RL to Average-Velocity Generators
View all activity

Papers

Flow-DPPO: Divergence Proximal Policy Optimization for Flow Matching Models

Beyond Uniform Token-Level Trust Region in LLM Reinforcement Learning

View all Papers

Tencent-Hunyuan-Multimodal-RL 's papers 3