Shengbang Liu | 刘盛邦

Shengbang Liu | 刘盛邦

I have loved the stars too fondly to be fearful of the night

About Me🧑‍🚀

I’m Shengbang Liu, currently an undergraduate student at the School of Computer Science and Engineering, Sun Yat-sen University. I will join the Embodied Decision Intelligence Lab(EDI Lab) at Tsinghua University as a PhD student, supervised by Prof. Chao Yu and Prof. Yu Wang. Previously, I was fortunate to work as a research intern at the Human Machine Intelligence Lab(HMI Lab), under the supervision of Prof. Shanghang Zhang.

My research interests primarily focus on Robotic Manipulation 🤖 and Reinforcement Learning 🍭. My long-term goal is to build general-purpose robot agents that can understand, interact with, and create meaningful value in the physical world, paving the way toward Physical AGI.

Publications📃

First Author/Co-First Author

Overview of RoboValue: A Fine-Grained Sim-and-Real Benchmark for Unified Evaluation of Robotic Value Models 2026
RoboValue: A Fine-Grained Sim-and-Real Benchmark for Unified Evaluation of Robotic Value Models
Shengbang Liu*, Zhengye Du*, Zhilong Wan*, Honghao Su*, Chenxiang Xia, Chang Ge, Jinyang Xiao, Nan Wang, Zhipeng Hu, Huining Yuan, Shu'ang Yu, Yue Chen, Tianxing Chen, Chuankang Li, Maoqing Yao, Wenbo Ding, Yu Wang, Guanghui Ren, Chao Yu
Manuscript, 2026.
Tech Report Project Page Document Code Dataset Leaderboard Community 具身智能之心
Overview of Robo-Dopamine 2.0: History-Conditioned and OOD-Aware Process Reward Modeling for Robotic Manipulation arXiv 2026
Robo-Dopamine 2.0: History-Conditioned and OOD-Aware Process Reward Modeling for Robotic Manipulation
Yijie Xu, Haopeng Jin, Run Zhou, Shengbang Liu*, Sixiang Chen, Hongyang Cheng, Sicheng Hu, Peterson Co, Jinwen Luo, Huajie Tan, Shanghang Zhang
arXiv Preprint, 2026.
Paper
Overview of TACO: TActile World Model as a Self-COrrector for Scalable VLA Post-Training arXiv 2026
TACO: TActile World Model as a Self-COrrector for Scalable VLA Post-Training
Shengbang Liu*, Yueru Jia*, Yuyang Yan*, Jiaming Liu*, Xinran Zhang, Qiuxuan Feng, Yandong Guo, Shiji Zhou, Boxin Shi, Shanghang Zhang
arXiv Preprint, 2026.
Paper Project Page Code
Overview of Video2Act: A Dual-System Video Diffusion Policy with Robotic Spatio-Motional Modeling arXiv 2025
Video2Act: A Dual-System Video Diffusion Policy with Robotic Spatio-Motional Modeling
Yueru Jia*, Jiaming Liu*, Shengbang Liu*, Rui Zhou, Wanhe Yu, Yuyang Yan, Xiaowei Chi, Yandong Guo, Boxin Shi, Shanghang Zhang
arXiv Preprint, 2025.
Paper Project Page Code

Co-Author

Overview of Decomposed Object Manipulation via Dual-Actor Policy arXiv 2025
Decomposed Object Manipulation via Dual-Actor Policy
Bin Fan*, Jianjian Jiang*, Zhuohao Li, Yixiang He, Xiaoming Wu, Yihan Yang, Shengbang Liu, Weishi Zheng
arXiv Preprint, 2025.
Paper

Education🎓

  • THU Logo PhD in Information and Communication Engineering, Tsinghua University (Incoming, 2027.9)
  • SYSU Logo Bachelor’s in Computer Science and Technology, Sun Yat-sen University (2023.9–Present)
  • JZ Logo Sun Yat-sen Memorial Middle School (2017.9–2023.6)

Honors🏆

  • National Scholarship, 2025, 2024
  • First Class Academic Scholarship, 2025, 2024

Personality🥳

Beyond academics and research, I enjoy fitness 🏋️, podcasts 🎙️, reading 📚, and comedy 🤣. To me, life is a continuous process of debugging, discovering, and growing. Driven by curiosity, I am always eager to explore the world 🌍 and experience new things—and I can’t wait to share adventures and stories with you!

Contact💬

If you are interested in joining the Embodied Decision Intelligence Lab(EDI Lab) as a research assistant, please feel free to reach out to me directly via edi_hire@163.com. In your message, please briefly introduce yourself and share your research interests and relevant experience.