About Me
Welcome to my page!
At present, I am a second year student in Institute of Computational Linguistic from Peking University. I am privileged to have been supervised by Prof.Baobao Chang. My research interests lie in empowering LLMs with multi-modal abilities and tool-using abilities, also exploring their emerging capabilities in downstream tasks. Previously, I completed my bachelor’s degree at Beijing Jiaotong University.
Out of work, I like traveling, swimming and jogging.
Interests
- AI4Science
- Large Language Model
- Language Grounding with Vision
Education
- MS in Computer Science - Peking University, Supervisor: Prof.Baobao Chang (2022 - 2024)
- BSc in Computer Science - Beijing Jiaotong University (2018 - 2022)
Experience
- Wang Lab at UW supervised by Prof.Sheng Wang
- PLUS Lab at UCLA supervised by Prof.Nanyun (Violate) Peng
- Gerstein Lab at Yale supervised by Prof.Mark Gerstein and Prof.Arman Cohan
- Berkeley Artificial Intelligence Research Lab (BAIR) supervesed by Prof.Shanghang Zhang, Huanrui Yang and Prof.Kurt Keutzer
- DAMO Institute at ALIBABA Group supervised by Tianyu Liu and Mingzhe Ke
- Beijing Institute for General Artificial Intelligence supervised by Prof.Wenjuan Han and Xiaojian Ma
- Microsoft AZURE AI Team at Seattle supervised by Wen Xiao
Sevice
- Reviewer: EMNLP, ACL Rolling Review
News
- Jan 31, 2024 Our paper VeCAF: VLM-empowered Collaborative Active Finetuning with Training Objective Awareness is available on arXiv!
- Jan 19, 2024 Our paper MMICL: Empowering Vision-language Model with Multi-Modal In-Context Learning is accepted at ICLR 2024!
- Dec 01, 2023 I will be attending EMNLP 2023!
- Nov 21, 2023 I am applying for Ph.D position in U.S. now!
- Nov 16, 2023 Our paper ML-Bench: Large Language Models Leverage Open-source Libraries for Machine Learning Tasks is available on arXiv!
- Nov 14, 2023 Our paper Distantly-Supervised Named Entity Recognition with Uncertainty-aware Teacher Learning and Student-student Collaborative Learning is available on arXiv!
- Nov 08, 2023 Our paper Towards End-to-End Embodied Decision Making with Multi-modal Large Language Model is accepted at NeurIPS 2023 Foundation Models for Decision Making Workshop!
- Sept 14, 2023 Our paper MMICL: Empowering Vision-language Model with Multi-Modal In-Context Learning is available on arXiv!
- June 24, 2023 Our paper Human-in-the-Loop through Chain-of-Thought is available on arXiv!
- May 24, 2023 Our paper Large language models are not fair evaluators is available on arXiv!
- May 24, 2023 Our paper DialogVCS: Robust Natural Language Understanding in Dialogue System Upgrade is available on arXiv!
- May 20, 2023 Our paper DiffCap: Exploring Continuous Diffusion on Image Captioning is available on arXiv!
- May 03, 2023 Our paper SANTA: Separate Strategies for Inaccurate and Incomplete Annotation Noise in Distantly-Supervised Named Entity Recognition is accepted at findings of ACL 2023!
- Jan 01, 2023 Our paper Compositional task representations for large language models is accepted at ICLR 2023!