Ruopeng Gao

About Me

I’m a Ph.D candidate in MCG Group, School of Computer Science, Nanjing University, under the supervision of Prof. Limin Wang. I’m currently a research intern at Tencent ARC Lab, working on research related to world models. Before that, I was also a research intern at ByteDance, focusing on discrete autoregressive video generation. Besides, I have a long-standing focus on Multi-Object Tracking.

Before that, I spent wonderful years as an undergraduate in the Department of Computer Science and Technology, Nanjing University and received my Bachelor of Science in June 2021. During this period, I studied the impact propagation of code changes with Jiaming Xu and Prof. Liang Wang.

News

  1. 🎉 Two papers are accepted by ECCV 2026.
  2. 🔭 We propose HATReID-MOT, rethinking and improving the ReID cues in MOT tasks.
  3. 🎉 One paper is accepted by CVPR 2025.
  4. 🔭 Regarding Multiple Object Tracking as ID Prediction problems, a streamlined yet effective method MOTIP is proposed.
  5. 🎉 One paper is accepted by IEEE Transactions on Pattern Analysis and Machine Intelligence.
  6. 🚀 MeMOTR is released on arXiv, a simple but effective long-term memory-augmented multi-object tracker.
  7. 🎉 One paper is accepted by ICCV 2023, the paper and code are released.
  8. 🚀 Fengyuan Shi and I release Dynamic MDETR, a sparse and light decoder for visual grounding.
  9. 🚀 I release a modern and user-friendly personal homepage template.

Publications

ECCV 2026

History-Aware Transformation of ReID Features for Multiple Object Tracking

Ruopeng Gao, Yuyao Wang, Chunxu Liu, Limin Wang

Paper arXiv Code
ECCV 2026

UniDDT: Unifying Multimodal Understanding and Generation with Decoupled Diffusion Transformer

Shuai Wang, Liang Li, Yang Chen, Ruopeng Gao, Yao Teng, Limin Wang

Paper arXiv
arXiv 2025

Reasoning Guided Embeddings: Leveraging MLLM Reasoning for Improved Multimodal Retrieval

Chunxu Liu, Jiyuan Yang, Ruopeng Gao, Yuhan Zhu, Feng Zhu, Rui Zhao, Limin Wang

Paper Code
TPAMI 2023

Dynamic MDETR: A Dynamic Multimodal Transformer Decoder for Visual Grounding

Fengyuan Shi, Ruopeng Gao, Weilin Huang, Limin Wang

Paper arXiv Code

Internships

Research Intern Tencent ARC Lab Shenzhen Project Up

Research on world models, specifically causal diffusion video generation.

Research Intern ByteDance Shanghai

Focused on discrete autoregressive video generation and motion-aware visual tokenizer.

Mini-app Development Intern Tencent PCG Shenzhen

Worked as an intern on mini-app development.

Education

Ph.D Nanjing University Department of Computer Science and Technology Nanjing

Research in Computer Vision and Deep Learning, supervised by Prof. Limin Wang.

Undergraduate Nanjing University Department of Computer Science and Technology Nanjing

Focused on Computer Vision and Deep Learning, mainly about RGB-D scene recognition.

Worked on propagation of the effects after code commits.

High School Guiyang No.1 High School Guiyang

Honors

The second prize of Doctoral Scholarship of Nanjing University in 2023.
PhD President Scholarship of Nanjing University, 2021.
Well completed in National Training Program of Innovation for Undergraduates as the first host, 2020.
The second prize of Renmin Scholarship of Nanjing University in 2019.

Academic Service

Journal Review

  • IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI)
  • IEEE Transactions on Circuits and Systems for Video Technology (TCSVT)
  • IEEE Transactions on Multimedia (TMM)
  • Computer Vision and Image Understanding (CVIU)

Conference Review

  • IEEE Conference on Computer Vision and Pattern Recognition (CVPR)
  • European Conference on Computer Vision (ECCV)
  • Annual Conference on Neural Information Processing Systems (NeurIPS)
  • ACM SIGGRAPH Conference and Exhibition on Computer Graphics and Interactive Techniques in Asia (SIGGRAPH ASIA)
  • AAAI Conference on Artificial Intelligence (AAAI)

Contact