RIT Research AssistantHi! It's Run here! ツ
I am currently a first-year PhD student at RIT, advised by Prof. Dongfang Liu.Email: runjia@msn.com (Preferred) / rz4545@rit.edu / zrainj@uw.edu / z@runjia.tech
Action required
Problem: The current root path of this site is "baseurl ("_config.yml.
Solution: Please set the
baseurl in _config.yml to "Education
-
Rochester Institute of TechnologyPh.D. Student in Electrical and Computer EngineeringSep. 2024 - present -
![Guangdong University of Technology <span style='color:#0070f8;'>[Honors Program]</span>](/assets/images/badges/Guangdong_University_of_Technology_Logo.svg.png)
Guangdong University of Technology [Honors Program]B. Eng in Computer Science and TechnologySep. 2020 - Jul. 2024
Experience
-
Institute of Software Chinese Academy of SciencesNLP InternApr. 2023 - Sep. 2023
Honors & Awards
-
National Scholarship Award, PRC2021
-
China Robot Competition & Robocup China Open National Champion2022
News
Selected Publications (view all )
Visual Fourier Prompt Tuning
Runjia Zeng, Cheng Han, Qifan Wang, Chunshu Wu, Tong Geng, Lifu Huang, Ying Nian Wu, Dongfang Liu
NeurIPS Conference on Neural Information Processing Systems 2024
To tackle performance drops caused by data differences between pretraining and finetuning, we propose Visual Fourier Prompt Tuning (VFPT), which leverages the Fast Fourier Transform to combine spatial and frequency domain information, achieving better results with fewer parameters.
Visual Fourier Prompt Tuning
Runjia Zeng, Cheng Han, Qifan Wang, Chunshu Wu, Tong Geng, Lifu Huang, Ying Nian Wu, Dongfang Liu
NeurIPS Conference on Neural Information Processing Systems 2024
To tackle performance drops caused by data differences between pretraining and finetuning, we propose Visual Fourier Prompt Tuning (VFPT), which leverages the Fast Fourier Transform to combine spatial and frequency domain information, achieving better results with fewer parameters.
