Wenfang Sun(孙文放)

I am a final-year master student at University of Science and Technology of China(USTC). I am grateful to be supervised by Yingjun Du and Prof. Dr. Cees Snoek. I also received valuable guidance from Dr. Xiantong Zhen and Dr. Gaowen Liu.

Email  /  CV  /  Google Scholar  /  Twitter  /  Github

[Sep 2024] One paper was accepted by NeurIPS 2024.

[Apr 2024] One paper was accepted by CVPR 2024 Workshop.

[Apr 2023] One paper was accepted by ICML 2023.

My previous research primarily focused on the probabilistic meta-learning in few-shot learning. I have also explored prompt learning for vision-language models. Currently, I am enthusiastic about foundation models.

We propose IPO, an interpretable prompt optimizer that uses LLMs to dynamically generate and refine prompts, while incorporating an LMM to enhance textual-visual interaction.

We propose a novel text-supervised semantic segmentation framework that leverages large language model supervision for enhanced class descriptors, refined subclass generation, and effective ensembling for improved segmentation accuracy.

We propose a method for few-shot learning with fewer tasks, which we call MetaModulation.

This website is based on Jon's source code.