I am an Assistant Professor in the Department of Computer Science and Engineering at Texas A&M University, where I lead the FLAIR Lab. Before that, I was a postdoctoral researcher at the University of Illinois Urbana-Champaign, working with Heng Ji. I received my Ph.D. in computer science from the University of California, Los Angeles, where I worked with Kai-Wei Chang and Nanyun Peng. My research focuses on natural language processing, with a focus on developing trustworthy and generalizable language AI systems. These systems aim to understand human concepts, speak human languages, and perform logical reasoning. Additionally, they are designed to be robust, reliable, and adaptable to new domains, languages, and modalities. Currently, my research includes several key directions: (1) Robustness of large langauge models (LLMs), (2) Multimodal concept learning and alignment, (3) Multilingual text understanding, and (4) Data-driven knowledge extraction.

For prospective students: I am looking for self-motivated students to join my group in Fall 2026. If you are interested in large language models, multimodal learning, or multilingual NLP, please find more information here.

• [03.2024] Two papers have been accepted by NAACL 2024
• [01.2024] Our paper about spurious correlations in text classification has been accepted by EACL-Findings 2024
• [11.2023] Please check out our TextEE project about benchmakring event extraction
• [10.2023] Our paper about easily updated text representations has been accepted by EMNLP-Findings 2023
• [09.2023] Please check out our AACL 2023 paper about zero-shot cross-lingual transfer
• [07.2023] Our ParaAMR paper receives ACL 2023 Area Chair Award
• [04.2023] Please check out our five papers accepted by ACL 2023
• [10.2022] Our paper about syntactically controlled paraphrase generation has been accepted by EMNLP-Findings 2022
• [04.2022] Our paper about generation-based event extraction for the low-resource setting has been accepted by NAACL 2022
• [02.2022] Our paper about zero-shot cross-lingual event argument extraction has been accepted by ACL 2022
• [08.2021] Our paper about zero-shot cross-lingual transfer has been accepted by EMNLP 2021