Rui Li (李锐)

AI for Science (AI4SCI) · Embodied AI

Rui Li (李锐)

🧭 Research

My work builds toward embodied agents that can actually run experiments — grounded in realistic environments, and closed by contact-rich control.

Keystone

Embodied Agents for Scientific Discovery

Agents that perceive, plan and manipulate inside real laboratories, turning written protocols into executed experiments.

Left Pillar

Simulation & Benchmarks

High-fidelity, protocol-grounded environments and hierarchical benchmarks that make scientific embodiment measurable — LabUtopia, LabBuilder, CoEnv.

Right Pillar

Multimodal Manipulation Policies

Tactile-centric representations, vision-tactile-language-action models and world models for contact-rich manipulation — the N₀ series.

I graduated from Central South University with a degree in Computer Science and Technology. I am currently a first-year joint Ph.D. student at Harbin Institute of Technology and Shanghai AI Laboratory, supervised by Wangmeng Zuo and Dongzhan Zhou. My primary research interests lie in AI for Science (AI4SCI) and Embodied AI.

If you are interested in connecting or discussing potential collaborations, feel free to email me.

🔥 News

  • 2026.08:  🎉🎉 The N₀ series technical reports (N₀-Foundation, N₀-VTLA, N₀-TWAM) are released!
  • 2026.05:  🎉🎉 Our paper “LabBuilder” is accepted by ICML 2026!
  • 2025.09:  🎉🎉 Our paper “LabUtopia” is accepted by NeurIPS 2025!
  • 2025.07:  🎉🎉 Our paper “CFSSeg” is accepted by ACM MM 2025!
  • 2024.10:  🎉🎉 My first paper is accepted by BIBM 2024.
  • 2024.09:  🎉🎉 Excited to join the Shanghai AI Laboratory as a Ph.D. student in AI4Science.

📝 Publications

†: Corresponding Author , *: Equal Contribution

Tech Report

N₀-Foundation: Towards the Age of Tactile Intelligence

Rui Li (Core Contributor), NeoteAI Team, Fudan TEAI Team

Technical Report, 2026

A tactile-centric foundation for embodied manipulation that unifies scalable tactile hardware, 30,000+ hours of multimodal data across six embodiments, transferable tactile representations, and standardized real-world and simulated benchmarks.

Paper | Homepage | Code | Dataset

Tech Report

N₀-VTLA: Scaling Vision-Tactile-Language-Action Model with Latent Tactile Tokens

Rui Li (Data Processing), NeoteAI Team, Fudan TEAI Team

Technical Report, 2026

A vision-tactile-language-action foundation model for contact-rich manipulation that predicts future tactile tokens and improves offline from demonstrations, failures, human corrections, and recoveries.

Paper | ArXiv | Homepage | Code | Checkpoints

Tech Report

N₀-TWAM: Scaling Tactile-Native World Action Model for Contact-Rich Manipulation

Rui Li (Pretraining), NeoteAI Team, Fudan TEAI Team

Technical Report, 2026

A tactile-native world-action model that jointly predicts future vision, touch, and action, combining anticipatory and observed tactile pathways for contact-rich manipulation.

Paper | ArXiv | Homepage | Code | Checkpoints

ICML 2026
LabBuilder protocol-grounded laboratory layout generation overview

LabBuilder: Protocol-Grounded 3D Layout Generation for Interactable and Safe Laboratory

Jianbao Cao, Zhangrui Zhao, Bohan Feng, Zixuan Hu, Rui Li, Haiyuan Wan, Chenxi Li, Jingyuan Li, Wenzhe Cai, Lei Bai, Wanli Ouyang, Lingyu Duan, Di Huang, Mingting Pan, Sha Zhang, Xinzhu Ma, Shixiang Tang†, Dongzhan Zhou†

International Conference on Machine Learning (ICML), 2026

ArXiv | Website

Preprint

CoEnv: Driving Embodied Multi-Agent Collaboration via Compositional Environment

Li Kang, Yutao Fan, Rui Li, Heng Zhou, Yiran Qin, Zhemeng Zhang, Songtao Huang, Xiufeng Song, Zaibin Zhang, Bruno N.Y. Chen, Zhenfei Yin, Dongzhan Zhou, Wangmeng Zuo, Lei Bai

Preprint, 2026

ArXiv | Website

Preprint
LabRobFail benchmark showing injected robot failure cases in a chemical self-driving laboratory

LabRobFail: A Benchmark for Robotic Failure Analysis in Chemical Self-driving Laboratory

Haobo Wang*, Baoli Sun*, Anqi Zou, Dongsheng Huang, Zelin Lv, Ning Wang, Rui Li, Dongzhan Zhou, Weiyu Guo, Zhihui Wang, Wanli Ouyang

Preprint, 2026 (Under Review)

ArXiv | Code

Preprint
LabVLA vision-language-action framework grounded in laboratory embodied data

LabVLA: Grounding Vision-Language-Action Models in Scientific Laboratories

Baochang Ren, Xinjie Liu, Xi Chen, Yanshuo Liu, Chenxi Li, Daqi Gao, Zeqin Su, Jintao Xing, Zirui Xue, Rui Li, Xiangyu Zhao, Shuofei Qiao, Minting Pan, Wangmeng Zuo, Lei Bai, Dongzhan Zhou, Ningyu Zhang, Huajun Chen

Preprint, 2026

ArXiv | Website

NeurIPS 2025 Workshop

Advances and Innovations in the Multi-Agent Robotic System (MARS) Challenge

Li Kang, Heng Zhou, Xiufeng Song, Rui Li, Bruno N. Y. Chen, Ziye Wang, Ximeng Meng, Stone Tao, Yiran Qin, et al.

MARS Challenge @ NeurIPS 2025 Workshop on Space in Vision, Language, and Embodied AI

ArXiv | Challenge

NeurIPS 2025

LabUtopia: High-Fidelity Simulation and Hierarchical Benchmark for Scientific Embodied Agents

Rui Li*, Zixuan Hu, Wenxi Qu, Jinouwen Zhang, Zhenfei Yin, Sha Zhang, Xuantuo Huang, Hanqing Wang, Tai Wang, Jiangmiao Pang, Wanli Ouyang, Lei Bai, Wangmeng Zuo, Ling-Yu Duan†, Dongzhan Zhou†, Shixiang Tang†

NeurIPS 2025 Dataset and Benchmark Track

Paper | Website | Code | Dataset

ACM MM 2025
CFSSeg class-incremental semantic segmentation framework

CFSSeg: Closed-Form Solution for Class-Incremental Semantic Segmentation of 2D Images and 3D Point Clouds

Jiaxu Li*, Rui Li*, Jianyu Qi, Songning Lai, Linpu Lv, Kejia Fan, Jianheng Tang, Yutao Yue, Dongzhan Zhou, Yuanhuai Liu, Huiping Zhuang†

ACM International Conference on Multimedia (ACM MM), 2025

ArXiv | Code

Preprint
Intelligent science laboratory integrating cognitive agents with embodied perception, manipulation and navigation

Position: Intelligent Science Laboratory Requires the Integration of Cognitive and Embodied AI

Sha Zhang, Suorong Yang, Tong Xie, Xiangyuan Xue, Zixuan Hu, Rui Li, Wenxi Qu, Zhenfei Yin, Tianfan Fu, Di Hu, Andres M Bran, Nian Ran, Bram Hoex, Wangmeng Zuo, Philippe Schwaller, Wanli Ouyang, Lei Bai, Yanyong Zhang, Lingyu Duan, Shixiang Tang, Dongzhan Zhou

Preprint, 2025

ArXiv

ICASSP 2025
AIDC analytical incremental disease classification framework

AIDC: Benchmark for Analytical Learning in Incremental Disease Classification

Rongchang Zhao, Jianyu Qi, Rui Li, Zhijie Zheng,Jian Zhang,Jiaxu Li†

2025 IEEE International Conference on Acoustics, Speech, and Signal Processing

Paper

BIBM 2024
HFGS high-frequency guided pseudo-CT synthesis framework

HFGS: High-Frequency Information Guided Net for Multi-Regions Pseudo-CT Synthesis

Rongchang Zhao, Jianyu Qi, Rui Li, Teng Yang, Jiaxu Li, Jian Zhang, and Zijian Zhang†

IEEE International Conference on Bioinformatics and Biomedicine (BIBM), 2024.

Paper

📖 Educations

Harbin Institute of Technology

Joint Ph.D. Program with Shanghai AI Laboratory

Ph.D. Student

2025.09 - Present

China

Central South University

Computer Science and Engineering

Bachelor's Degree

2021.09 - 2025.07

Changsha, China

🤝 Collaborators

Supervisors

Collaborators

ZH Zixuan Hu Peking University
Yiran Qin Yiran Qin CUHK, Shenzhen Li Kang Li Kang Shanghai Jiao Tong University Yutao Fan Yutao Fan Harbin Institute of Technology
HZ Heng Zhou University of Science and Technology of China
CL Chenxi Li Shanghai AI Laboratory
Zhangrui Zhao Zhangrui Zhao Beihang University
JL Jiaxu Li Central South University