Tonghe Zhang

News

Talks

Research

Preprints

• 
  π_RL: Online RL Fine-tuning for Flow-based Vision-Language-Action Models

  Kang Chen*, Zhihao Liu*, Tonghe Zhang*, Zhen Guo, Si Xu, Hao Lin, Hongzhi Zang, Quanlu Zhang, Zhaofei Yu, Guoliang Fan, Tiejun Huang, Yu Wang, Chao Yu.

  Preprint.

  TL;DR: Online RL fine-tuning for flow-based VLAs (π0, π0.5) with policy gradient, achieving near perfect success rate in LIBERO and 90%+ success rate in ManiSkill via heterogeneous parallel sim across 320 envs.

  arXiv GitHub HuggingFace BibTex

  @misc{chen2025pitextttrlonlinerlfinetuning,
        title={$\pi_\texttt{RL}$: Online RL Fine-tuning for Flow-based Vision-Language-Action Models}, 
        author={Kang Chen and Zhihao Liu and Tonghe Zhang and Zhen Guo and Si Xu and Hao Lin and Hongzhi Zang and Quanlu Zhang and Zhaofei Yu and Guoliang Fan and Tiejun Huang and Yu Wang and Chao Yu},
        year={2025},
        eprint={2510.25889},
        archivePrefix={arXiv},
        primaryClass={cs.LG},
        url={https://arxiv.org/abs/2510.25889}, 
  }

Publications

• BFM-Zero: A Promptable Behavioral Foundation Model for Humanoid Control Using Unsupervised Reinforcement Learning

  Yitang Li*^$, Zhengyi Luo*^$, Tonghe Zhang^$, Cunxi Dai^$, Anssi Kanervisto, Andrea Tirinzoni, Haoyang Weng, Kris Kitani, Mateusz Guzek, Ahmed Touati, Alessandro Lazaric, Matteo Pirotta, Guanya Shi.

  The Fourteenth International Conference on Learning Representations (ICLR 2025).

  TL;DR: Building behavior foundation model for multitask humanoid loco-manipulation via unsupervised sim2real RL.

  Website arXiv GitHub BibTex

  @misc{li2025bfmzeropromptablebehavioralfoundation,
        title={BFM-Zero: A Promptable Behavioral Foundation Model for Humanoid Control Using Unsupervised Reinforcement Learning}, 
        author={Yitang Li and Zhengyi Luo and Tonghe Zhang and Cunxi Dai and Anssi Kanervisto and Andrea Tirinzoni and Haoyang Weng and Kris Kitani and Mateusz Guzek and Ahmed Touati and Alessandro Lazaric and Matteo Pirotta and Guanya Shi},
        year={2025},
        eprint={2511.04131},
        archivePrefix={arXiv},
        primaryClass={cs.RO},
        url={https://arxiv.org/abs/2511.04131}, 
  }

• 
  Sample-Efficient Reinforcement Learning of Flow Policies via Sequence Modeling

  Yixian Zhang*, Shu'ang Yu*, Tonghe Zhang, Mo Guang, Haojia Hui, Kaiwen Long, Yu Wang, Chao Yu, Wenbo Ding.

  The Fourteenth International Conference on Learning Representations (ICLR 2025).

  TL;DR: Training flow matching policies via off-policy RL by treating the process as RNN/Transformer.

  arXiv GitHub Website

• 
  ReinFlow: Fine-tuning Flow Matching Policy with Online Reinforcement Learning

  Tonghe Zhang, Chao Yu, Sichang Su, Yu Wang.

  The Thirty-Ninth Annual Conference on Neural Information Processing Systems (NeurIPS 2025).

  TL;DR: Injecting learnable noise to fine-tune flow matching policies and VLAs with policy gradient.

  NeurIPS Homepage Website arXiv Google Scholar GitHub WandB HuggingFace BibTex

  @misc{zhang2025reinflowfinetuningflowmatching,
        title={ReinFlow: Fine-tuning Flow Matching Policy with Online Reinforcement Learning}, 
        author={Tonghe Zhang and Chao Yu and Sichang Su and Yu Wang},
        year={2025},
        eprint={2505.22094},
        archivePrefix={arXiv},
        primaryClass={cs.RO},
        url={https://arxiv.org/abs/2505.22094}, 
  }