Yaoting WANG
Introduction
Hallo! I'm Yaoting Wang, and I'm currently a research intern at Tsinghua University. My primary interests lie in Multimodal LLM, Multimodal NLP, and Audio-Visual Learning.
Education
- Ph.D. @ Coming soon... (2025 - 2029, expected)
- M.Sc. @ University of Edinburgh (2021 - 2022)
- B.Sc. @ University of Limerick (2019 - 2021)
- B.Eng. @ Shandong University of Science and Technology (2017 - 2021)
Professional
-
Research Intern @ THU AIR (02/2025 - Present)
Advised by Prof. Yunxin Liu. -
Visiting Student @ KAUST Vision-CAIR (04/2024 - 02/2025)
Advised by Dr. Jian Ding and Prof. Mohamed Elhoseiny. -
Research Assistant @ RUC GSAI (03/2023 - 03/2024)
Advised by Prof. Di Hu.
News
- [23-05-2025] We organize the 1st International Workshop on MLLM for Unified Comprehension and Generation (MUCG) at ACM 2025, Call for Papers is now open!
- [01-05-2025] Our paper "On Path to Multimodal Generalist" has been accepted as a Spotlight presentation at ICML 2025!
- [18-03-2025] We release the first comprehensive survey on multimodal chain-of-thought reasoning, along with the Awesome-MCoT repository.
-
[30-08-2024]
- Thanks QBitAI's report for our work Ref-AVS, welcome to follow! -
[09-07-2024]
- Glad to have a speech on GAVS at Vision and Learning SEminar (VASLE)! -
[16-07-2024]
- We are excieted to release our new task Reference Audio-Visual Segmentation (Ref-AVS) and its benchmark dataset Ref-AVS Bench. How can we ask machines to locate objects of interest in the real-world with vision, audio, language... just like a human! -
[01-07-2024]
- Three papers Ref-AVS, Segmentation-Preference and Stepping-Stones have been accepted by ECCV 2024! -
[01-03-2024]
- Joined Vision-CAIR, KAUST! -
[09-12-2023]
- One paper GAVS has been accepted by AAAI 2024 main track and ICCV 2023 AV4D workshop! -
[05-01-2023]
- Joined GeWu Lab, Gaoling School of Artificial Intelligence, Renmin University of China!