Yushi Feng

Yushi Feng

PhD Student

Division of AI & Data Science

School of Computing & Data Science

The University of Hong Kong

Email: fengys [at] connect.hku.hk

About

I am a PhD student at The University of Hong Kong, advised by Prof. Lequan Yu, where I also received my BSc in 2024.

My research interests include: (1) Agentic AI: Autonomous agents capable of continual learning from experience and self-reflective reasoning; (2) Trustworthy Multimodal LLMs: Interpretable, robust, and uncertainty-aware multimodal LLMs; (3) Medical AI: Evidence-grounded, precise, and proactive AI for healthcare.

News

Selected Publications []

* indicates co-first author; † indicates corresponding authorship.

PASS: Probabilistic Agentic Supernet Sampling for Interpretable and Adaptive Chest X-Ray Reasoning

Yushi Feng, Junye Du, Yingying Hong, Qifan Wang, Lequan Yu†.

AAAI Conference on Artificial Intelligence (AAAI), 2026. (Oral, top 5%)

Democratizing Large Language Model-Based Graph Data Augmentation via Latent Knowledge Graphs

Yushi Feng*, Tsai Hor Chan*, Guosheng Yin, Lequan Yu†.

Neural Networks, 2025.

IPAD: Inverse Prompt for AI Detection - A Robust and Interpretable LLM-Generated Text Detector

Zheng Chen*, Yushi Feng*, Jisheng Dang, Yue Deng, Changyang He, Hongxi Pu, Haoxuan Li†, Bo Li†.

Conference on Neural Information Processing Systems (NeurIPS), Main Track, 2025;
Meeting of the Association for Computational Linguistics (ACL) KnowFM Workshop, Full Paper, 2025.

A Dynamic Agent Framework for Large Language Model Reasoning for Medical and Visual Question Answering

Ziyan Xiao, Ruiyang Zhang, Yushi Feng, Lingting Zhu, Liang Peng, Lequan Yu†.

International Conference on Computer Vision (ICCV) CVAMD Workshop, Full Paper, 2025. (Oral)

Awards & Honors

Professional Activities