|
I am a second-year PhD student at UCLA, advised by Prof. Kai-Wei Chang and Prof. Nanyun Peng. Preivously, I received my master's degree from UIUC in 2023 advised by Prof. Heng Ji, and my bachelor's degree from USTC in 2020. I have work experience in Meta, IBM Research, Bytedance AI Lab and MSRA. Research: My research interests focus on multi-modal reasoning, such as grounding, self-reflection, and reasoning enhanced by code generation. |
|
|
|
|
|
New! FronTalk: Benchmarking Front-End Development as Conversational Code Generation with Multi-Modal Feedback
|
|
New! LLMs as Scalable, General-Purpose Simulators For Evolving Digital Agent Training
Yiming Wang, Da Yin, Yuedong Cui, Ruichen Zheng, Zhiqian Li, Zongyu Lin, Di Wu, Xueqing Wu, Chenchen Ye, Yu Zhou, Kai-Wei Chang
Arxiv 2510 [ Paper | Project | Code | Model and Data ] |
|
|
|
VISCO: Benchmarking Fine-Grained Critique and Correction Towards Self-Improvement in Visual Reasoning
|
|
VDebugger: Harnessing Execution Feedback for Debugging Visual Programs
Xueqing Wu, Zongyu Lin, Songyan Zhao, Te-Lin Wu, Pan Lu, Nanyun Peng, Kai-Wei Chang
EMNLP 2024 Findings [ Paper | Project | Code | Model and data ] |
|
Reflection-Reinforced Self-Training for Language Agents
|
|
DACO: Towards Application-Driven and Comprehensive Data Analysis via Code Generation
Xueqing Wu, Rui Zheng, Te-Lin Wu, Hanyu Zhou, Tang Mohan, Kai-Wei Chang, Nanyun Peng, Haoran Huang
NeurIPS 2024 Dataset and Benchmark Track [ Paper | Project | Code and data ]
|
|
Are LLMs Capable of Data-based Statistical and Causal Reasoning? Benchmarking Advanced Quantitative Reasoning with Data
|
|
Retrieval-Based Transformer for Table Augmentation
|
|
Cross-document Misinformation Detection based on Event Graph Reasoning
|
|
Text-to-Table: A New Way of Information Extraction
|
|
Temporally Correlated Task Scheduling for Sequence Learning
|
|
|
|
|
|
