| layout | permalink | title |
|---|---|---|
page-head |
/ |
Yuan Liu |
Currently, I am a senior researcher at WeChat AI, focusing on large language model. Before that, I obtained my Master degree from the University of Hong Kong, and Bachelor degree from Southeast University. I take great pride in my contributions as a core developer and maintainer to a number of renowned open-source projects including MMSelfSup, MMPretrain, MMEngine, MMSegmentation, and OpenCompass. Currently, my interests focus on vision-language model, large language model, representation learning and basemodel.
We are looking for excellent interns. If you are interested in multimodal foundation models and large language models, please contact me.
- 2024.12.06 We release POINTS1.5. A strong vision-language model, which ranks first on the OpenCompass leaderboard among all models under 10B🎉🎉🎉.
- 2024.10.14 We release MEGA-Bench, which contains 500+ real-world tasks to evaluate vision-language models🎉🎉🎉.
- 2024.10.10 We launch the WePOINTS project and opensource POINTS🔥🔥🔥.
- 2024.09.10 We propose a brand new vision-language model, called POINTS.
- 2024.07.27 VLMEvalKit Technical Report is accepted by ACMMM2024 OpenSource 🎉🎉🎉.
- 2024.07.01 MMBench is accepted by ECCV2024 as Oral Presentation 🎉🎉🎉.
- 2024.05.21 We release a paper focusing on aspects previously overlooked in vision-language model.
- 2024.01.16 One paper on self-supervised learning is accepted by TMLR 🎉🎉🎉.
- 2023.08.29 Join in WeChat as a full-time researcher 🎉🎉🎉.