💬 About Me

I work at Shanghai Artificial Intelligence Laboratory as a internship now, doing Unified Generation and Understanding research.
I am a PhD student at Shanghai Innovation Institute (SII) & Nanjing University (NJU), under the supervision of Prof. Xiaohong Liu and Prof. Yu Qiao. Before that, I received my B.Sc. degree from Northeastern University in June 2021.

📖 Educations

2025.09 - 2027.06: Ph.D, Shanghai Innovation Institute, Shanghai.
2023.09 - 2027.06: Ph.D, Computer Science and Techonology, Nanjing University, Nanjing.
2021.09 - 2023.06: Master, Computer Science and Techonology, Nanjing University, Nanjing.
2017.09 - 2021.06: Undergraduate, Software College, Northeastern University, Shenyang.

2025.08: One paper is accepted by ACMMM 2025.
2025.06: Four papers are accepted by ICCV 2025. (Two Co-first Author Papers)
2025.03: One paper is accepted by TCSVT 2025.
2025.01: One paper is accepted by ICLR 2025.
2024.12: Two papers are accepted by AAAI 2025.
2024.09: Two papers are accepted by NeurIPS 2024. (One First Author Paper and One Co-first Author Paper)
2024.03: One paper is accepted by ICLR Workshop 2024.
2023.12: Two papers are accepted by AAAI 2024. (Two First Author Papers)
2023.10: One paper is accepted by Machine Learning.
2023.01: One paper is accepted by DASFAA Research Track 2023. (First Author)

TR-PTS: Task-Relevant Parameter and Token Selection for Efficient Tuning. S Luo, H Yang, Y Xin*, etc. International Conference on Computer Vision, 2025. (ICCV, CCF-A, Equal Contributions)
Lumina-image 2.0: A unified and efficient image generative framework. Q Qin, Y Xin, R Du, Z Li, etc. International Conference on Computer Vision, 2025. (ICCV, CCF-A, Equal Contributions)
V-PETL Bench: A Unified Visual Parameter-Efficient Transfer Learning Benchmark. Y Xin, S Luo, X Liu, Y Du, etc. International Conference on Neural Information Processing Systems, 2024. (NeurIPS, CCF-A)
Towards Understanding the Working Mechanism of Text-to-Image Diffusion Model. M Yi, A Li, Y Xin*, Z Li. International Conference on Neural Information Processing Systems, 2024. (NeurIPS, CCF-A, Equal Contributions)
VMT-Adapter: Parameter-Efficient Transfer Learning for Multi-Task Dense Scene Understanding. Y Xin, J Du, Q Wang, Z Lin, K Yan. AAAI Conference on Artificial Intelligence, 2024. (AAAI, CCF-A)
MmAP : Multi-modal Alignment Prompt for Cross-domain Multi-Task Learning. Y Xin, J Du, Q Wang, K Yan, S Ding. AAAI Conference on Artificial Intelligence, 2024. (AAAI, CCF-A)
Self-Training with Label-Feature-Consistency for Domain Adaptation. Y Xin, S Luo, P Jin, Y Du, C Wang. International Conference on Database Systems for Advanced Applications, 2023. (DASFAA, CCF-B, $\color{red}{Oral}$)

Generation, augmentation, and alignment: A pseudo-source domain based method for source-free domain adaptation. Y Du, H Yang, M Chen, H Luo, J Jiang, Y Xin, C Wang. Machine Learning, 2023. (CCF-B)
Building Load Forecasting Using Deep Neural Network with Efficient Feature Fusion. J Wang, X Chen, F Zhang, F Chen, Y Xin. Journal of Modern Power Systems and Clean Energy, 2021. (SCI Q1)

2021.04: Digital China Innovation Contest, Champion（1/1538）, 100,000RMB. [Solution] [Code]