✨ About me

Bonjour, I am currently a master student at the School of Electronic and Computer Engineering, Peking University, advised by Prof. Jie Chen. Before this, I received a B.S. degree from the College of Computer Science (Elite Class), in Jilin University, in 2022.

My research interests are Trustworthy AI, especially:

• (a) Foundation Model (e.g. LLM/LMM) Safety
• (b) Semi-supervised Learning (e.g. classification and segmentation)
• (c) Responsible AIGC (e.g. talking head generation, t2i/t2v generation model)

😃 I am looking for USA PhD to start in 2025 Fall. Feel free to contact me if you have any opening!

📰 News

• 2024/07: 🎉 Two papers (Adashield about VLM Safety and ParCo about Text-to-Motion Synthesis) are accepted by ECCV 2024.
• 2024/04: 🚀 We release an open-source repository about Awesome-T2I-safety-Papers.
• 2023/10: 🎉 One paper (TIDA) about open-set semi-supervised learning is accepted by NeurIPS 2023.
• 2023/03: 🎉 Two papers (OSP about robust semi-supervised learning and FPR about semi-supervised semantic segmentation) are accepted by CVPR 2023.

💻 Selected Publication

My full paper list is shown at Google Scholar.

Open-set/Robust Semi-supervised Learning

• NeurIPS 2023 Discover and Align Taxonomic Context Priors for Open-world Semi-Supervised Learning, Yu Wang,Zhun Zhong, Pengchong Qiao, Xiawu Zheng, Chang Liu, Nicu Sebe, Rongrong Ji, Jie Chen. [Code]
• CVPR 2023 Out-of-Distributed Semantic Pruning for Robust Semi-Supervised Learning, Yu Wang*, Pengchong Qiao*, Chang Liu, Guoli Song, Xiawu Zheng, Jie Chen. [Code]

Safety AI

• ECCV 2024 AdaShield: Safeguarding Multimodal LLMs from Structure-based Attack via Adaptive Shield Prompting, Yu Wang, Xiaogeng Liu , Yu Li, Muhao Chen, Chaowei Xiao. [Code]
• Awesome Github Repo Awesome-T2I-safety-Papers.

🎖 Honors and Awards

• 2023/11: Merit Student at Peking University
• 2023/03: Excellent Papers of China Computer Federation Computer Application Conference (Top 1%)
• 2022/12: Jilin Bank Wang Xianghao Scholarship (Top 1%)
• 2021/11: National Scholarship
• 2020/10: National Inspirational Scholarship (Top 1%)

💪 Academic Service

• PC Member: CVPR’24, ICLR’24, ICML’24, ACM MM’24, ECCV’24, NeurIPS’24

🙌 Open Source Contribution

• Github: Open Sora Plan, Peking University, Yuan Group, Contributors, 10.9k Stars.
  • Role: Contribute the evaluation code for video generation, e.g. Clip-Score, FVD, SSIM, LPIPS, and PSNR.

If you like the template of this homepage, welcome to star and fork the open-sourced template version AcadHomepage .