Yu-Cheng Shi

Undergraduate Student
Nanjing University
231250034@smail.nju.edu.cn

About Me

I am a third-year undergraduate in School of Computer Science at Nanjing University. Currently (Oct. 2025-), I am working as a research intern under the supervision of Dr. Da-Wei Zhou in LAMDA Group, Nanjing University.

Research Interests

Multi-Modal Learning: multi-modal alignment, continual instruction tuning
Transfer Learning: parameter-efficient fine-tuning, pretrained-model reuse
Continual Learning: catastrophic forgetting avoidance

News

[May. 2026] We release a toolbox for MCIT (Technical Report)
[May. 2026] Two papers are accepted to ICML 2026.

Publications

Publications

ICML

SAME: Stabilized Mixture-of-Experts for Multimodal Continual Instruction Tuning

Zhen-Hao Xie*, Jun-Tao Tang*, Yu-Cheng Shi, Han-Jia Ye, De-Chuan Zhan, Da-Wei Zhou
(* Equal contribution)

International Conference on Machine Learning. (ICML), 2026

PDF Code

ICML

AREA: Attribute Extraction and Aggregation for CLIP-Based Class-Incremental Learning

Zhen-Hao Xie*, Yu-Cheng Shi*, Da-Wei Zhou
(* Equal contribution)

International Conference on Machine Learning. (ICML), 2026

PDF Code

Preprints

arXiv

Prism: A Plug-in Reproducible Infrastructure for Scalable Multimodal Continual Instruction Tuning

Jun-Tao Tang*, Yu-Cheng Shi*, Zhen-Hao Xie, Da-Wei Zhou
(* Equal contribution)

arXiv:2605.26110, 2026.

PDF Code

Services

Conference Reviewers

Journal Reviewers

Powered by Jekyll and Minimal Light theme.