Hi there! I am Hao Li (李昊 in Chinese), a third-year Ph.D. candidate in the School of Computer Science at Peking University, advised by Prof. Li Yuan. Before that, I got my Bachelor of Science degree in computer science at Peking University with a Summa Cum Laude.
My research interests include multimodality Learning, visual understanding, and AI for Chemical Science. I have published more than 20 papers at the top international AI conferences with total Google Scholar citations 500+.
🔥 News
- 2024.12: 🎉🎉 One papers accepted by Nature Computational Science.
- 2024.08: 🎉🎉 Two papers accepted by The 18th European Conference on Computer Vision(ECCV-2024).
- 2023.08: 🎉🎉 One paper accepted by The International Conference on Computer Vision(ICCV-2023).
- 2023.06: 🎉🎉 One paper accepted by Transactions on Image Processing(TIP).
- 2023.04: 🎉🎉 Three paper accepted by The International Joint Conference on Artifical Intelligence(IJCAI-2023).
- 2022.08: 🎉🎉 One oral paper accepted by The International Conference on Multimedia and Expo(ICME-2022-Oral).
📝 Selected Publications and Preprints

FreestyleRet: Retrieving Images from Style-Diversified Queries
Hao Li, Yanhao Jia, Peng Jin, Zesen Cheng, Kehan Li, Jialu Sui, Chang Liu, Li Yuan
- Official Code for the FreestyleRet framework. Official Released for the Diversified-Style Retrieval Dataset (DSR).

Decoupled peak property learning for efficient and interpretable ECD spectra prediction
Hao Li, Da Long, Li Yuan, Yu Wang, Yonghong Tian, Xinchang Wang, Fanyang Mo
- Existing predictive approaches lack the consideration of ECD spectra due to the data scarcity, and the interpretability to achieve trust-worthy prediction. Here, we establish a large-scale dataset for Chiral Molecular ECD spectra (CMCDS) and propose ECDFormer for accurate and interpretable ECD spectra prediction. ECDFormer decomposes ECD spectra into peak entities, employs the QFormer architecture to learn peak properties, and renders peaks into spectra. Compared to spectra sequence prediction methods, our decoupled peak prediction approach substantially enhances both accuracy and efficiency, improving the peak symbol accuracy from 37.3% to 72.7% and decreasing the time cost from an average of 4.6 CPU hours to 1.5 seconds.

Diffusionret: Generative text-video retrieval with diffusion model
Hao Li, Peng Jin, Zesen Cheng, Kehan Li, Chang Liu, Li Yuan, Jie Chen
- Official Code for the DiffusionRet model.
🎖 Honors and Awards
- 2023.9 Hongqiao Scholarship in Peking University (Top 1%).
📖 Educations
- 2017.09 - 2021.06, Bachelor, in School of Electronics Engineering and Computer Science (EECS), Peking University.
- 2021.09 - 2023.09, Master, School of Electronics and Computer Engineering (ECE), Peking University.
- 2023.09 - now, PhD Candidate, School of Computer Science, Peking University.
💻 Internships
- 2020.07 - 2021.09, Mentored by Xu Li, Cognitive Computing Lab, Baidu Research, Beijing, China.
- 2022.07 - 2023.02, Mentored by Songyang Zhang, OpenMMLab, Shanghai AI Lab, Shanghai, China.
- 2024.12 - present, Mentored by Yu Li, International Digital Economy Academy, Shenzhen, China.