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.
Current Research Interests:
- Agentic AI: Reasoning, Continual Learning, Multi-Agent
- Trustworthy MLLM: Uncertainty Quantification, Interpretability, Alignment
- Medical AI: Multimodality, Clinical Decision Support, Knowledge Representation
News
- 01/2026 Our work DemoGraph was featured in Forbes China.
- 11/2025 One paper was accepted by AAAI 2026 (Oral).
- 09/2025 One paper was accepted by NeurIPS 2025 (main track).
- 07/2025 One paper was accepted by ICCV 2025 CVAMD Workshop (Oral).
- 06/2025 One paper was accepted by ACL 2025 KnowFM Workshop.
- 06/2025 One paper was accepted by Neural Networks.
Selected Publications []
* indicates co-first author; † indicates corresponding authorship.
PASS: Probabilistic Agentic Supernet Sampling for Interpretable and Adaptive Chest X-Ray Reasoning
AAAI 2026 (Oral, top 5%).
Democratizing Large Language Model-Based Graph Data Augmentation via Latent Knowledge Graphs
Neural Networks, 2025.
IPAD: Inverse Prompt for AI Detection - A Robust and Interpretable LLM-Generated Text Detector
NeurIPS 2025 (Main Track);
ACL KnowFM Workshop 2025 (Full Paper).
A Dynamic Agent Framework for Large Language Model Reasoning for Medical and Visual Question Answering
ICCV CVAMD Workshop 2025 (Full Paper, Oral).
Awards & Honors
- Forbes China feature, 2026.
- AAAI-26 Student Scholarship, AAAI, 2025.
- Postgraduate Scholarship, HKU, 2024-Present.
- Dean's Honours List (Top 5%), HKU, 2024.
- Outstanding Tech Final Year Project Award (USD 167,000), Incubation Programme, HKSTP, 2024.
- Summer Research Fellowship (USD 2,000), HKU, 2023.
Professional Activities
- Conference Reviews: ICML 2026, CVPR 2026, AAAI 2026, ICCV 2025, ECCV 2026, MICCAI 2026, ISBI 2026
- Journal Reviews: npj Digital Medicine