Yong-Ji Wu

Most-cited papers

1. RLinf: Flexible and Efficient Large-scale Reinforcement Learning via Macro-to-Micro Flow Transformation

   Chao Yu, Yuan-Qing Wang, Zhen Guo, Hao Lin +25 more

   2025arXiv.org82 citations

   Semantic Scholar

   Save

2. RLinf-VLA: A Unified and Efficient Framework for VLA+RL Training

   Hong-Zhi Zang, Ming-Jie Wei, Si Xu, Yong-Ji Wu +13 more

   2025arXiv.org37 citations

   Semantic Scholar

   Save

3. RLinf-VLA: A Unified and Efficient Framework for Reinforcement Learning of Vision-Language-Action Models

   Hong-Zhi Zang, Ming-Jie Wei, Si Xu, Yong-Ji Wu +14 more

   202529 citations

   Semantic Scholar

   Save

4. FireRed-OCR Technical Report

   Hao Wu, Haoran Lou, Xin-Yue Li, Zuodong Zhong +18 more

   2026arXiv.org13 citations

   Semantic Scholar

   Save

5. RLux-VLA: A Unified and Efficient Framework for Reinforcement Learning of Vision-Language-Action Models

   Hong-Zhi Zang, Ming-Jie Wei, Si Xu, Yong-Ji Wu +16 more

   2026Robotics6 citations Open access

   Semantic Scholar

   Save

6. STS: Efficient Sparse Attention with Speculative Token Sparsity

   Ce-Yu Xu, Jiang-Nan Yu, Yong-Ji Wu, Yuan Xie

   2026arXiv.org1 citations

   Semantic Scholar

   Save

7. AstraFlow: Dataflow-Oriented Reinforcement Learning for Agentic LLMs

   Hai-Zhong Zheng, Yi-Zhu Di, Jiahui Wang, Shuo-Wei Jin +6 more

   2026arXiv.org1 citations

   Semantic Scholar

   Save