I am a MPhil student at The Hong Kong University of Science and Technology (Guangzhou), supervised by Prof. Zeke Xie. Previously, I received my Bachelor’s degree in Computer Science and Technology from Harbin Institute of Technology (Shenzhen) in 2025, advised by Prof. Xinyang Chen.

Research Interests 🧠

I study why modern machine learning systems fail to generalize across tasks, models, and environments. My work focuses on analyzing internal representation and adaptation mechanisms, and designing methods that improve transfer and robustness. In the long term, I aim to build AI systems that learn to understand and interact with the physical world.

Please feel free to reach out to me for discussion or potential collaborations!

News 🗞️

• 2026.05 One paper is accepted to ICML 2026.
• 2025.09 Start my MPhil journey at HKUST(GZ)!
• 2025.06 Graduate from HITSZ!
• 2025.05 First paper is accepted to ICML 2025.

Publications 📔

Exploring Data-Free LoRA Transferability for Video Diffusion Models

Yuchen Wang, Wenliang Zhong, Lichen Bai, Zikai Zhou, Shitong Shao, Bojun Cheng, Shuo Chen, Shuo Yang, Zeke Xie

International Conference on Machine Learning (ICML), 2026

Paper / Code

Handling Imbalanced Pseudolabels for Vision-Language Models with Concept Alignment and Confusion-Aware Calibrated Margin

Yuchen Wang, Xuefeng Bai, Xiucheng Li, Weili Guan, Liqiang Nie, Xinyang Chen

International Conference on Machine Learning (ICML), 2025

Paper / Code

Education 🎓

The Hong Kong University of Science and Technology (Guangzhou)

2025 - Present

MPhil in Data Science and Analytics

Harbin Institute of Technology (Shenzhen)

2021 - 2025

BEng in Computer Science and Technology