Zibin Dong / 董子斌

PhD student at CollegeAI, Tsinghua University.

photo.jpg

I obtained my Master’s degree at TJURLLAB, under the supervision of Prof. Jianye Hao. Starting Fall 2026, I will be pursuing my PhD at CollegeAI, Tsinghua University, joining the MARS Lab under the supervision of Prof. Hang Zhao.

My research interests focus on Embodied AI, VLA models, generative models, and reinforcement learning. I aspire to leverage the transformative power of AI in shaping the world. I am highly self-motivated and possess a strong passion for AI research. I am constantly seeking opportunities for research collaborations. You can find detailed information about me in my CV. Feel free to contact me at zibindong@outlook.com or wechat dongzibin1112.

news

Feb 25, 2026 One paper accepted by CVPR 2026: “SemanticVLA: Towards Semantic Reasoning over Action Memorization via Synergistic Explicit Trace and Latent Action Planning”
Jan 20, 2026 Three papers accepted by ICLR 2026: “From Seeing to Doing: Bridging Reasoning and Decision for Robotic Manipulation”, “Embodied-R1: Reinforced Embodied Reasoning for General Robotic Manipulation”, “FASTer: Toward Powerful and Efficient Autoregressive Vision-Language-Action Models with Learnable Action Tokenizer and Block-wise Decoding”
Sep 20, 2025 One paper accepted by NeurIPS 2025: “Conditioning Matters: Training Diffusion Policies is Faster Than You Think”
May 01, 2025 Two papers accepted by ICML 2025: “MODULI: Unlocking Preference Generalization via Diffusion Models for Offline Multi-Objective Reinforcement Learning”, “R*: Efficient Reward Design via Reward Structure Evolution and Parameter Alignment Optimization with Large Language Models”
Jan 23, 2025 One paper accepted by ICLR 2025: “Entropy-based Activation Function Optimization: A Method on Searching Better Activation Functions”

selected publications

  1. ActionCodec: What Makes for Good Action Tokenizers
    Zibin Dong, Yicheng Liu, Shiduo Zhang, Baijun Ye, Yifu Yuan, and 6 more authors
    arXiv preprint arXiv:2602.15397, 2026
  2. From Seeing to Doing: Bridging Reasoning and Decision for Robotic Manipulation
    Yifu Yuan, Haiqin Cui, Yibin Chen, Zibin Dong, Fei Ni, and 5 more authors
    In The Fourteenth International Conference on Learning Representations, ICLR, 2026
  3. Embodied-R1: Reinforced Embodied Reasoning for General Robotic Manipulation
    Yifu Yuan, Haiqin Cui, Yaoting Huang, Yibin Chen, Fei Ni, and 5 more authors
    In The Fourteenth International Conference on Learning Representations, ICLR, 2026
  4. FASTer: Toward Powerful and Efficient Autoregressive Vision–Language–Action Models with Learnable Action Tokenizer and Block-wise Decoding
    Yicheng Liu, Shiduo Zhang, Zibin Dong, Baijun Ye, Tianyuan Yuan, and 10 more authors
    In The Fourteenth International Conference on Learning Representations, ICLR, 2026
  5. Conditioning Matters: Training Diffusion Policies is Faster Than You Think
    Zibin Dong, Yicheng Liu, Yinchuan Li, Hang Zhao, and Jianye Hao
    In The Thirty-ninth Annual Conference on Neural Information Processing Systems, NeurIPS, 2025
  6. dong2024cleandiffuser.png
    CleanDiffuser: An Easy-to-use Modularized Library for Diffusion Models in Decision Making
    Zibin Dong, Yifu Yuan, Jianye Hao, Fei Ni, Yi Ma, and 2 more authors
    In The Thirty-eight Conference on Neural Information Processing Systems Datasets and Benchmarks Track, NeurIPS, 2024
    HTML
  7. dong2024diffuserlite.png
    DiffuserLite: Towards Real-time Diffusion Planning
    Zibin Dong, Jianye Hao, Yifu Yuan, Fei Ni, Yitian Wang, and 2 more authors
    In The Thirty-eighth Annual Conference on Neural Information Processing Systems, NeurIPS, 2024
    HTML
  8. dong2024aligndiff.png
    AlignDiff: Aligning Diverse Human Preferences via Behavior-Customisable Diffusion Model
    Zibin Dong, Yifu Yuan, Jianye Hao, Fei Ni, Yao Mu, and 5 more authors
    In The Twelfth International Conference on Learning Representations, ICLR, 2024
    HTML