Biography
Minghui Chen is a researcher at the Nanyang Technological University (advisors: Dr. Xiaoxiao Li, Dr. Yu Han and Dr. Zehua Wang). His research interests are Reliable AI, Deep phenomena.
Interests
- LLM Agent
- Reliable AI
- AI for Healthcare
Education
MSc in Computer Science
Southern University of Science and Technology
BSc in Software Engineering
Sun Yat-sen University
Publications
(2025).
Can Textual Gradient Work in Federated Learning?.
In ICLR 2025.
(2025).
Revisiting Delta-Parameter Pruning For Fine-Tuned Models.
In ICLR 2025 (Spotlight).
(2024).
Local Superior Soups: A Catalyst for Model Merging in Cross-Silo Federated Learning.
In NeurIPS 2024.
(2024).
Debiased Noise Editing on Foundation Models for Fair Medical Image Classification.
In MICCAI 2024.
(2024).
Forgettable Federated Linear Learning with Certified Data Removal.
In WWW 2024 FL@FM Workshop (Best Paper Award).
(2023).
FedSoup: Improving Generalization and Personalization in Federated Learning via Selective Model Interpolation.
In MICCAI 2023.
(2022).
VITA: A Multi-Source Vicinal Transfer Augmentation Method for Out-of-Distribution Generalization.
In AAAI 2022.
(2021).
Benchmarks for Corruption Invariant Person Re-Identification.
In NeurIPS 2021.
Experience
Research Associate
Multi-Agent Decision.
Doctoral Researcher
Trustworthy AI.
Doctoral Researcher
Decentralized Learning.
Academic Service
Journal Reviewer
Conference Reviewer
Teaching
Teaching Assistant
Teaching Assistant