Cheng Chi's Homepage

About Me

I am currently an Assistant Professor (Young Talent Program) at the School of Information, Renmin University of China (RUC). Previously, I was a Research Scientist at the Beijing Academy of Artificial Intelligence (BAAI), where I led and made major contributions to the RoboBrain and RoboOS series of works. Before that, I served as the Perception Lead at IDRIVERPLUS, where I built its production-grade autonomous driving perception system from the ground up and led its research, development, and deployment. I received my Ph.D. in 2020 from the University of Chinese Academy of Sciences (UCAS), under the supervision of Prof. Xudong Zou, Zhen Lei and Stan Z. Li. My dissertation was recognized as an Excellent Doctoral Dissertation by the China Education Society of Electronics (CESE).

My research interests now lie in Embodied Intelligence — empowering robots with the ability to perceive, reason, and act in the physical world.

I am recruiting motivated undergraduate, master's, and Ph.D. students to work on embodied AI and VLM/VLA.

Interested students are encouraged to contact me via email at chengchi@ruc.edu.cn.

News

• 09 / 2026: PIGEON (VLM-Driven Object Navigation) is accepted by CoRL 2026
• 08 / 2026: Embodied Manipulation Survey and Well-Posed Robotic Decomposition framework (Theory-Grounded Brain–Cerebellum Hierarchy), are accepted by IEEE Transactions on Robotics (T-RO)
• 08 / 2026: RoboMirror (Video to Humanoid Locomotion), Robobench (Embodied Brain Benchmark), and RoboTracer (Spatial Trace VLM), are accepted by ECCV 2026
• 06 / 2026: VCoT-Grasp (Grasp Foundation Model) is accepted by IROS 2026
• 05 / 2026: LaRA-VLA(Latent Reasoning VLA) and Dyn-VPP(WAM Post-Training for Visual Dynamics) are accepted by ICML 2026
• 04 / 2026: RoboPerform and SaPaVe are selected as CVPR 2026 Highlight (Top 11% of accepted papers, top 3% of all submissions).
• 03 / 2026: I will serve as Area Chair of NeurIPS 2026
• 03 / 2026: DualMindVLM(Adaptive Thinking for VLMs) is accepted by ViSCALE Workshop at CVPR 2026
• 02 / 2026: Four papers (RoboPerform(Audio-Control Humanoid Locomotion), SaPaVe(VLA Active Perception), Action-Sketcher(Dual-system VLA with Visual Sketches), Robo-Dopamine(General Process Reward Model)) are accepted by CVPR 2026
• 01 / 2026: We release RoboBrain 2.5, our more powerful embodied foundation model
• 01 / 2026: TIGeR(Tool-use Embodied VLM) is accepted by ICRA 2026
• 01 / 2026: RoboGhost(Latent-driven Language-guided Humanoid Locomotion) is accepted by ICLR 2026
• 12 / 2025: I am invited to be a speaker in the The first CVPR workshop on Embodied Reasoning in Action (ERA) at CVPR 2026
• 09 / 2025: MathSticks(Visual Symbolic Reasoning Benchmark) is accepted by MATH-AI Workshop at NeurIPS 2025
• 09 / 2025: RefSpatial-Bench is now used by Qwen3-VL, Gemini-Robotics-1.5 and Seed1.8 to evaluate spatial reasoning in complex scenes
• 09 / 2025: RoboRefer(Spatial-Reasoning Embodied VLM) is accepted by NeurIPS 2025
• 08 / 2025: I will serve as Area Chair of ICLR 2026
• 06 / 2025: We release RoboOS 2.0 (cross-embodiment and multi-agent collaboration framework) & RoboBrain 2.0 (new generation open-source embodied VLM) at BAAI Conference 2025!
• 02 / 2025: Code-as-Monitor(efficient and precise failure detection system) is accepted by CVPR 2025
• 10 / 2020: Obtain China Postdoctoral Science Foundation
• 09 / 2020: One paper is accepted by NeurIPS 2020 as Spotlight
• 06 / 2020: Our paper ATSS was nominated for Best Paper Award at CVPR 2020
• 05 / 2020: One paper is accepted by TPAMI
• 02 / 2020: One paper is accepted by CVPR 2020 as Oral
• 05 / 2020: One paper is accepted by ICML 2020

Selected Preprints

( *, †, ‡ indicates the equal contributions, corresponding author, project leader, respectively.)

RoboBrain 2.0 Technical Report

BAAI RoboBrain Team (I serve as project leader)

paper

project

RoboOS: A Hierarchical Embodied Framework for Cross-Embodiment and Multi-Agent Collaboration

Huajie Tan^*, Xiaoshuai Hao^*, Cheng Chi^*, Minglan Lin^*^‡, Yaoxu Lyu, Mingyu Cao, Dong Liang, Zhuo Chen, Mengsi Lyu, Cheng Peng, Chenrui He, Yulong Ao, Yonghua Lin, Pengwei Wang^‡, Zhongyuan Wang, Shanghang Zhang^†

Under Review

paper

project

Selected Publications

( *, †, ‡ indicates the equal contributions, corresponding author, project leader, respectively.)

PIGEON: VLM-Driven Object Navigation via Points of Interest Selection

Cheng Peng^*, Zhenzhe Zhang^*, Xiaobao Wei, Yanhao Zhang, Heng Wang, Pengwei Wang, Zhongyuan Wang, Cheng Chi^†, Shanghang Zhang^†, Jing Liu

Conference on Robot Learning (CoRL), 2026

paper

code

From Ill-Posed to Well-Posed: A Decomposition Framework for Reliable Robot Learning with Foundation Models

Yuheng Ji^*, Cheng Chi^*, Huajie Tan, Yuting Zhao, Huaihai Lyu, Enshen Zhou, Pengwei Wang, Zhongyuan Wang, Xiaolong Zheng, Shanghang Zhang

IEEE Transactions on Robotics (T-RO), 2026

RoboMirror: Understand Before You Imitate for Video to Humanoid Locomotion

Zhe Li, Boan Zhu, Yangyang Wei, Shuanghao Bai, Yuheng Ji, Tao Huang, Pengwei Wang, Zhongyuan Wang, Gary Chan, Chang Xu, Cheng Chi^†, Jianfei Yang^†, Shanghang Zhang^†

European Conference on Computer Vision (ECCV), 2026

paper

Robobench: A Comprehensive Evaluation Benchmark for Multimodal Large Language Models as Embodied Brain

Yulin Luo^*, Chun-Kai Fan^*, Menghang Dong^*, Jiayu Shi^*, Mengdi Zhao^*, Bo-Wen Zhang^*, Cheng Chi^*^‡, Jiaming Liu, Gaole Dai, Rongyu Zhang, Ruichuan An, Kun Wu, Zhengping Che, Shaoxuan Xie, Guocai Yao, Zhongxia Zhao, Pengwei Wang, Guang Liu, Zhongyuan Wang, Tiejun Huang, Shanghang Zhang

European Conference on Computer Vision (ECCV), 2026

paper

project

code

Towards Spatial Trace with Reasoning in Vision-Language Models for Robotics

Enshen Zhou, Yibo Li, Jingkun An, Jiayuan Zhang, Shanyu Rong, Mengzhen Liu, Yi Han, Yuheng Ji, Huajie Tan, Jiawei He, Pengwei Wang, Zhongyuan Wang, Cheng Chi^†, Lu Sheng^†, Shanghang Zhang^†

European Conference on Computer Vision (ECCV), 2026

paper

project

Latent Reasoning VLA: Latent Thinking and Prediction for Vision-Language-Action Models

Shuanghao Bai^*, Jing Lyu^*, Wanqi Zhou, Zhe Li, Dakai Wang, Lei Xing, Xiaoguang Zhao, Pengwei Wang, Zhongyuan Wang, Cheng Chi^†, Badong Chen^†, Shanghang Zhang^†

International Conference on Machine Learning (ICML), 2026

paper

project

Do You Have Freestyle? Expressive Humanoid Locomotion via Audio Control

Zhe Li^*, Cheng Chi^†, Yangyang Wei^*, Boan Zhu, Tao Huang, Zhenguo Sun, Yibo Peng, Pengwei Wang, Zhongyuan Wang, Fangzhou Liu, Chang Xu^†, Shanghang Zhang^†

IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2026

paper

project

Learning to Think Fast and Slow for Visual Language Models

Chenyu Lin, Cheng Chi^†, Jinlin Wu, Sharon Li, Kaiyang Zhou^†

2nd Workshop on Test-time Scaling for Computer Vision (ViSCALE) at CVPR, 2026

paper

project

TIGeR: Tool-Integrated Geometric Reasoning in Vision-Language Models for Robotics

Yi Han^*, Enshen Zhou^*, Shanyu Rong, Jingkun An, Pengwei Wang, Zhongyuan Wang, Cheng Chi^†, Lu Sheng^†, Shanghang Zhang^†

International Conference on Robotics and Automation (ICRA), 2026

paper

project

From Language To Locomotion: Retargeting-free Humanoid Control via Motion Latent Guidance

Zhe Li^*^‡, Yangyang Wei^*, Boan Zhu^*, Yibo Peng, Tao Huang, Pengwei Wang, Zhongyuan Wang, Cheng Chi^†, Chang Xu^†, Shanghang Zhang^†

International Conference on Learning Representations (ICLR), 2026

paper

project

RoboRefer: Towards Spatial Referring with Reasoning in Vision-Language Models for Robotics

Enshen Zhou^*, Jingkun An^*, Cheng Chi^*^†^‡, Yi Han, Shanyu Rong, Chi Zhang, Pengwei Wang, Zhongyuan Wang, Tiejun Huang, Lu Sheng^†, Shanghang Zhang^†

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

paper

project

code

Code-as-Monitor: Constraint-aware Visual Programming for Reactive and Proactive Robotic Failure Detection

Enshen Zhou^*, Qi Su^*, Cheng Chi^*^†, Zhizheng Zhang, Zhongyuan Wang, Tiejun Huang, Lu Sheng^†, He Wang^†

IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2025

paper

project

RelationNet++: Bridging Visual Representations for Object Detection via Transformer Decoder

Cheng Chi, Fangyun Wei, Han Hu

Thirty-fourth Conference on Neural Information Processing Systems (NeurIPS), Spotlight, 2020

paper

code

RefineFace: Refinement Neural Network for High Performance Face Detection

Shifeng Zhang^*, Cheng Chi^*, Zhen Lei, Stan Z Li

IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI)

^*equal contribution

paper

Bridging the Gap Between Anchor-based and Anchor-free Detection via Adaptive Training Sample Selection

Shifeng Zhang, Cheng Chi, Yongqiang Yao, Zhen Lei, Stan Z. Li

IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Oral, Best Paper Nomination, 2020

paper,

code

Relational Learning for Joint Head and Human Detection

Cheng Chi, Shifeng Zhang, Junliang Xing, Zhen Lei, Stan Z. Li, Xudong Zou

Association for the Advancement of Artificial Intelligence (AAAI), 2020

paper

PedHunter: Occlusion Robust Pedestrian Detector in Crowded Scenes

Cheng Chi, Shifeng Zhang, Junliang Xing, Zhen Lei, Stan Z. Li, Xudong Zou

Association for the Advancement of Artificial Intelligence (AAAI), 2020

paper

Selective Refinement Network for High Performance Face Detection

Cheng Chi, Shifeng Zhang, Junliang Xing, Zhen Lei, Stan Z. Li, Xudong Zou

Association for the Advancement of Artificial Intelligence (AAAI), Oral, 2019

paper

code

Education

B.Eng. in College of Electrical and Information Engineering, Hunan University of China

Sep. 2011 - Jul. 2015

Ph.D. in Aerospace Information Research Institute, Chinese Academy of Sciences

Sep. 2015 - Jul. 2020

Postdoctor in Institute of Automation, Chinese Academic of Sciences

Sep. 2020 - Jul. 2022