Kaipeng Fang

Hi, I’m Kaipeng Fang (方恺鹏 in Chinese). I am a third-year Ph.D. student at UESTC, supervised by Prof. Lianli Gao and Prof. Jingkuan Song. I received my Bachelor’s degree from SDUT in 2023. That same year, I joined UESTC to pursue my Ph.D. through the direct doctoral program (a five-year track).

My early research focused on Computer Vision (CV) and Image Retrieval, leading to a publication at CVPR 2024. Currently, my research interests have shifted toward Embodied AI and Robotics. I am particularly focused on exploring how to effectively leverage data from various sources, especially human data, for generalizable robot learning. Having long admired Elon Musk’s mindset, I strictly align my research philosophy with first principles. My ultimate goal is to achieve true generalist robots by scaling up data-driven robot learning.

I also maintain a personal research blog at ByteGather (码途拾遗 in Chinese), where I share insights on algorithms, machine learning, and robotics. It currently hosts 200+ articles and has attracted more than 360k visitors. Additionally, I run a WeChat Official Account with over 3k subscribers.

Publications

CVPR

ProS: Prompting-to-simulate Generalized knowledge for Universal Cross-Domain Retrieval

Kaipeng Fang, Jingkuan Song, Lianli Gao, Pengpeng Zeng, Zhi-Qi Cheng, Xiyao Li, and Heng Tao Shen

In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2024

TL;DR arXiv Bib Code

@inproceedings{fang2024pros,
  title = {ProS: Prompting-to-simulate Generalized knowledge for Universal Cross-Domain Retrieval},
  author = {Fang, Kaipeng and Song, Jingkuan and Gao, Lianli and Zeng, Pengpeng and Cheng, Zhi-Qi and Li, Xiyao and Shen, Heng Tao},
  booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2024},
  tldr = {This paper proposes Prompting-to-Simulate (ProS), a novel prompt tuning framework for Universal Cross-Domain Retrieval (UCDR) that generates Content-aware Dynamic Prompts via a two-stage simulation process to effectively address domain and semantic shifts, achieving state-of-the-art performance with high parameter efficiency.},
}

Programming Competition Awards (Selected)

(ACM-ICPC) International Collegiate Programming Contest Regional Contest

Silver Medal 🥈

With Xinrui Zhao, Junlin Mu. Supervised by Prof. Xiaohong Liu.

Team: Shandong University of Technology

[2022] Silver Award 🥈, (CCCC) China Collegiate Computing Contest
[2022] Second Prize 🥈, RoboCom Robot Development Competition CAIP Programming Design National Finals
[2021] Bronze Medal 🥉, (CCPC) China Collegiate Programming Contest Regional Contest (Harbin)
[2021] Bronze Medal 🥉, (ACM-ICPC) 45th International Collegiate Programming Contest Regional Contest (Shenyang)
[2021] Silver Medal 🥈, (SDCPC) China Collegiate Programming Contest Shandong Provincial Contest
[2021] Team First Prize 🥇, (CCCC) China Collegiate Computing Contest
[2021] Individual First Prize 🥇, (CCCC) China Collegiate Computing Contest
[2020] National Gold Medal Team 🥇, (CCCC) China Collegiate Computing Contest
[2020] Bronze Medal 🥉, (ACM-ICPC) 45th International Collegiate Programming Contest Regional Contest (Jinan)
[2020] Bronze Medal 🥉, (CCPC) China Collegiate Programming Contest Regional Contest (Qinhuangdao)

Honors and Services

Honors
- [2025] Outstanding Student Paper Nomination, Sichuan Computer Federation
- [2024] Academic Second Class Scholarship, University of Electronic Science and Technology of China
- [2021] National Scholarship, Ministry of Education of P.R. China
- [2021] Outstanding Student, Education Department of Shandong Province
- [2021] Science and Technology Innovation Model, Shandong University Of Technology
Services
- Captain & Student Coach of SDUT ACM Competitive Programming Team (2020-2022)
- Regular Reviewer for CVPR2026
- Regular Reviewer for TMM