Runpei Dong

Runpei Dong

M.S. Candidate

Xi'an Jiaotong University

Biography

Runpei Dong is currently a second-year M.S. student in Computer Science at Xi’an Jiaotong University, supervised by Prof. Andrew C. Yao. He collaborates closely with Prof. Kaisheng Ma, and he is also working closely with Prof. Li Yi. Before that, he received his bachelor’s degree in Computer Science from Xidian University in 2021. His current research interests include self-supervised 2D, 3D, and multimodal representation learning like vision language.

Interests
  • Representation Learning
  • Multimodal Learning
  • Vision Language
  • Generative Modeling
  • 3D Computer Vision
Education
  • Master Candidate in Computer Science, 2021 - 2024

    Xi'an Jiaotong University

  • Bachelor in Computer Science, 2017 - 2021

    Xidian University

Recent News

  • NEW [2023/04] I will be attending ICLR 2023 in person, see you in Rwanda!
  • NEW [2023/04] One paper accepted to ICML 2023.
  • NEW [2023/03] One paper accepted to CVPR 2023.
  • NEW [2023/03] One paper accepted to ICASSP 2023.
  • [2023/01] One paper accepted to ICLR 2023.
  • [2022/09] I join Megvii (Foundation Model Group) as a research intern.
  • [2022/06] One paper accepted to ECCV 2022 (Oral).
  • [2021/12] One paper accepted to ICML 2022 (Spotlight).
  • [2021/10] One paper accepted to BMVC 2021.
  • [2021/06] One paper accepted to ISCA 2021.

Selected Publications

*: equal contribution, the full list can be found here or Google Scholar

CLIP-FO3D: Learning Free Open-world 3D Scene Representations from 2D Dense CLIP

Junbo Zhang, Runpei Dong, Kaisheng Ma

Tech Report, Mar 2023

PDF  Code (coming soon)

Exploring Recurrent Long-term Temporal Fusion for Multi-view 3D Perception

Chunrui Han, Jianjian Sun, Zheng Ge, Jinrong Yang, Runpei Dong, Hongyu Zhou, Weixin Mao, Yuang Peng, Xiangyu Zhang

Tech Report, Mar 2023

PDF  Code (coming soon)

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

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

PointDistiller: Structured Knowledge Distillation Towards Efficient and Compact 3D Detection

Linfeng Zhang*, Runpei Dong*, Hung-Shuo Tai, Kaisheng Ma

CVPR 2023

PDF  Code

Contrastive Deep Supervision

Linfeng Zhang, Xin Chen, Junbo Zhang, Runpei Dong, Kaisheng Ma

ECCV 2022 Oral Presentation (2.7%)

PDF  Code

Finding the Task-Optimal Low-Bit Sub-Distribution in Deep Neural Networks

Runpei Dong*, Zhanhong Tan*, Mengdi Wu, Linfeng Zhang, Kaisheng Ma

ICML 2022 Spotlight Presentation

PDF  Code