Heng Zhou
Logo USTC
Logo Shanghai AI Laboratory

I am currently an intern at the Shanghai Artificial Intelligence Laboratory, focusing on multi-agent systems, reinforcement learning, and LLM alignment. I am a Ph.D. student at the University of Science and Technology of China (USTC) in a joint training program with the Shanghai AI Lab, advised by Prof. Wanli Ouyang and Prof. Lei Bai.

Research interests: machine learning, multimodal learning, AI agents, robotics.


Education
  • USTC & PJLAB
    USTC & PJLAB
    Ph.D. Student, advised by Prof. Wanli Ouyang and Prof. LEI BAI
    Sep. 2025 - present
Experience
  • Shanghai AI Laboratory
    Shanghai AI Laboratory
    Research Intern, advised by Prof. LEI BAI
    Oct. 2024 - present
Honors & Awards
  • Beijing Merit Student
    2025
  • National Scholarship
    2023
Selected Publications (view all )
VIKI-R: Coordinating Embodied Multi-Agent Cooperation via Reinforcement Learning
VIKI-R: Coordinating Embodied Multi-Agent Cooperation via Reinforcement Learning

Li Kang*, Xiufeng Song*, Heng Zhou*, Yiran Qin#, Jie Yang, Xiaohong Liu, Philip Torr, Lei Bai#, Zhenfei Yin# (* equal contribution, # corresponding author)

Annual Conference on Neural Information Processing Systems (NeurIPS) 2025

VIKI-R: Coordinating Embodied Multi-Agent Cooperation via Reinforcement Learning

Li Kang*, Xiufeng Song*, Heng Zhou*, Yiran Qin#, Jie Yang, Xiaohong Liu, Philip Torr, Lei Bai#, Zhenfei Yin# (* equal contribution, # corresponding author)

Annual Conference on Neural Information Processing Systems (NeurIPS) 2025

ReSo: A Reward-driven Self-organizing LLM-based Multi-Agent System for Reasoning Tasks
ReSo: A Reward-driven Self-organizing LLM-based Multi-Agent System for Reasoning Tasks

Heng Zhou*, Hejia Geng*, Xiangyuan Xue, Li Kang, Yiran Qin, Zhiyong Wang, Zhenfei Yin#, Lei Bai# (* equal contribution, # corresponding author)

EMNLP 2025 main

ReSo: A Reward-driven Self-organizing LLM-based Multi-Agent System for Reasoning Tasks

Heng Zhou*, Hejia Geng*, Xiangyuan Xue, Li Kang, Yiran Qin, Zhiyong Wang, Zhenfei Yin#, Lei Bai# (* equal contribution, # corresponding author)

EMNLP 2025 main

SS3DM: Benchmarking Street-View Surface Reconstruction with a Synthetic 3D Mesh Dataset
SS3DM: Benchmarking Street-View Surface Reconstruction with a Synthetic 3D Mesh Dataset

Yubin Hu*, Kairui Wen*, Heng Zhou, Xiaoyang Guo, Yong-Jin Liu# (* equal contribution, # corresponding author)

Annual Conference on Neural Information Processing Systems (NeurIPS)

SS3DM: Benchmarking Street-View Surface Reconstruction with a Synthetic 3D Mesh Dataset

Yubin Hu*, Kairui Wen*, Heng Zhou, Xiaoyang Guo, Yong-Jin Liu# (* equal contribution, # corresponding author)

Annual Conference on Neural Information Processing Systems (NeurIPS)

All publications