Runpei Dong

PhD Candidate, Computer Science, University of Illinois Urbana-Champaign
Email / Google Scholar / GitHub / DBLP / LinkedIn / Twitter
I am a 2nd year CS PhD candidate at UIUC, advised by Prof. Saurabh Gupta.
I got my MS in CS in 2024, where I was jointly trained at Tsinghua University & Xi'an Jiaotong University, under the supervision of Prof. Andrew Chi-Chih Yao. I was fortunate to collaborate closely with Prof. Kaisheng Ma, Prof. Li Yi and Prof. He Wang. I also spent one year at Megvii Research, working on computer vision with Dr. Xiangyu Zhang.

Research

I enjoy working on real-world problems that fascinate me, and I am currently trying to build scalable, generalizable & human-centered robotic, vision, and language models / systems. I am enthusiastic about contributing to the research community and I support Slow Science. I am currently working in several areas:

Other areas of work recently and in the past include: 1) foundation models (mainly generative vision-language models) and 2) representation learning.

Recent News

Papers

  (show selected / show by date)
*: Equal contribution. †: Project leader. See also my Google Scholar profile for the most recent publications.

Learning Humanoid End-Effector Control for Open-Vocabulary Visual Loco-Manipulation
Runpei Dong*, Ziyan Li*, Xialin He, Saurabh Gupta
Tech Report, Feb. 2026
PDF / Project / Code (Coming Soon)
Press: Quantum Zeitgeist

Learning Getting-Up Policies for Real-World Humanoid Robots
Xialin He*, Runpei Dong*, Zixuan Chen, Saurabh Gupta
RSS 2025 / PDF / Project / Code / Poster
Press: Tech Xplore

AlphaOne: Reasoning Models Thinking Slow and Fast at Test Time
Junyu Zhang*, Runpei Dong*, Han Wang, Xuying Ning, Haoran Geng, Peihao Li, Xialin He, Yutong Bai, Jitendra Malik, Saurabh Gupta, Huan Zhang
EMNLP 2025 Main / PDF / Project / Code
Press: Venture Beat

DreamLLM: Synergistic Multimodal Comprehension and Creation
Runpei Dong*, Chunrui Han*, Yuang Peng, Zekun Qi, Zheng Ge, Jinrong Yang, Liang Zhao, Jianjian Sun, Hongyu Zhou, Haoran Wei, Xiangwen Kong, Xiangyu Zhang, Kaisheng Ma, Li Yi
ICLR 2024 / PDF / Project / Code / OpenReview / Poster / Slides
Spotlight Presentation (4.96%)

ShapeLLM: Universal 3D Object Understanding for Embodied Interaction
Zekun Qi, Runpei Dong†, Shaochen Zhang, Haoran Geng, Chunrui Han, Zheng Ge, He Wang, Li Yi, Kaisheng Ma
ECCV 2024 / PDF / Project / Code / 3D MM-Vet Benchmark / Data

Autoencoders as Cross-Modal Teachers: Can Pretrained 2D Image Transformers Help 3D Representation Learning?
Runpei Dong, Zekun Qi, Linfeng Zhang, Junbo Zhang, Jianjian Sun, Zheng Ge, Li Yi, Kaisheng Ma
ICLR 2023 / PDF / Code / OpenReview / Poster / Slides

Contrast with Reconstruct: Contrastive 3D Representation Learning Guided by Generative Pretraining
Zekun Qi*, Runpei Dong*, Guofan Fan, Zheng Ge, Xiangyu Zhang, Kaisheng Ma, Li Yi
ICML 2023 / PDF / Code / OpenReview / Poster / Slides

Finding the Task-Optimal Low-Bit Sub-Distribution in Deep Neural Networks
Runpei Dong*, Zhanhong Tan*, Mengdi Wu, Linfeng Zhang, Kaisheng Ma
ICML 2022 / PDF / Code / Slides
Spotlight Presentation

Data & Software

Selected Honors

Service

I am always willing to contribute to making our community fairer and better.

Random

Runpei Dong · Last updated: Feb, 2026 · Website adapted from here.