(original) (raw)
Menu
Chengzu Li
About me
I am a second-year PhD student in Computation, Cognition and Language at Language Technology Lab in the University of Cambridge, supervised by Dr. Ivan Vulić and Prof. Serge Belongie. My research is supported by Cambridge Trust. I am a member of Jesus College.
Before starting my PhD, I received my MPhil degree in Advanced Computer Science at the Department of Computer Science, supervised by Prof. Simone Teufel, supported by Cambridge Trust. I was an undergraduate student in Automation at Xi'an Jiaotong University.
Research
My research interests include language grounding and multimodal reasoning (eg. image, structural knowledge, etc.). I am currently exploring and focusing on the topics below:
- Spatial reasoning: evaluation and improvements [TopViewRS] [New Recipes]
- Multimodal reasoning: paradigm and methods [MVoT] [Visual Planning]
I'm also interested in the potential downstream application scenarios of multimodal reasoning.
Education
- PhD (Probationary) in Computation, Cognition and Language, Language Technology Lab, University of Cambridge, 2023 - now
- Master of Philosophy in Advanced Computer Science, University of Cambridge, 2022 - 2023
- Graduation with Distinction
- Bachelor of Engineering in Automation, Xi'an Jiaotong University, 2018 - 2022
- Graduate with Distinction (91.88/100)
- Minor in Fintech (China Construction Bank - XJTU Fintech Elite Class)
Publications
(*: equal contribution)
Preprints
- Visual Planning: Let's Think Only with Images
Yi Xu*, Chengzu Li*, Han Zhou*, Xingchen Wan, Caiqi Zhang, Anna Korhonen, Ivan Vulić
arXiv. [code] - Scaling and Beyond: Advancing Spatial Reasoning in MLLMs Requires New Recipes
Huanyu Zhang*, Chengzu Li*, Wenshan Wu, Shaoguang Mao, Yan Xia, Ivan Vulić, Zhang Zhang, Liang Wang, Tieniu Tan, Furu Wei
arXiv.
2025
- Imagine while Reasoning in Space: Multimodal Visualization-of-Thought
Chengzu Li*, Wenshan Wu*, Huanyu Zhang, Yan Xia, Shaoguang Mao, Li Dong, Ivan Vulić, Furu Wei
ICML 2025. [code] [IEEE Spectrum] [TWIML Podcast] [新智元] - Large Language Models are Miscalibrated In-Context Learners
Chengzu Li, Han Zhou, Goran Glavaš, Anna Korhonen, Ivan Vulić.
ACL 2025, Findings. [code]
2024
- TopViewRS: Vision-Language Models as Top-View Spatial Reasoners
Chengzu Li*, Caiqi Zhang*, Han Zhou, Nigel Collier, Anna Korhonen, Ivan Vulić
EMNLP 2024, main (oral). [project website] [code] [data] - Semantic Map-based Generation of Navigation Instructions
Chengzu Li, Chao Zhang, Simone Teufel, Rama Sanand Doddipatla, Svetlana Stoyanchev.
COLING-LREC 2024. [code]
2023
- Generating Data for Symbolic Language with Large Language Models
Jiacheng Ye, Chengzu Li, Lingpeng Kong, Tao Yu.
EMNLP 2023, main. [code] - Binding Language Models in Symbolic Languages
Zhoujun Cheng, Tianbao Xie, Peng Shi, Chengzu Li, Rahul Nadkarni, Yushi Hu, Caiming Xiong, Dragomir Radev, Mari Ostendorf, Luke Zettlemoyer, Noah A. Smith, Tao Yu.
ICLR 2023 (spotlight). [code]
2022
- UnifiedSKG: Unifying and Multi-Tasking Structured Knowledge Grounding with Text-to-Text Language Models
Tianbao Xie, Chen Henry Wu, Peng Shi, Ruiqi Zhong, Torsten Scholak, Michihiro Yasunaga, Chien-Sheng Wu, Ming Zhong, Pengcheng Yin, Sida I. Wang, Victor Zhong, Bailin Wang, Chengzu Li, Connor Boyle, Ansong Ni, Ziyu Yao, Dragomir Radev, Caiming Xiong, Lingpeng Kong, Rui Zhang, Noah A. Smith, Luke Zettlemoyer, Tao Yu.
EMNLP 2022, main (oral). [code]
Internships
- Jun. 2024 - Dec. 2024
Research Intern, GenAI Group, Microsoft Research.
Mentor: Wenshan Wu.
Research on Multimodal Spatial Reasoning. - Jan. 2023 - July 2023
Research Intern, Toshiba Cambridge Research.
Mentor: Svetlana Stoyanchev, Chao Zhang, Rama Sanand Doddipatla and Prof. Simone Teufel.
Research on Generating Instructions for Robot Navigation as the MPhil thesis. - Oct. 2021 - Jan. 2022
Research Intern, Shanghai AI Lab.
Mentor: Lingpeng Kong.
Research on Structural Knowledge Grounding. - June 2021 - Oct. 2022
Research Intern, HKUNLP.
Mentor: Tao Yu and Lingpeng Kong.
Worked on Structural Knowledge Grounding, Semantic Parsing and Neural-Symbolic Reasoning. - July 2020 - Aug. 2020
Engineer Intern, Dianchu Technology.
Worked on machine learning engineering.
Selected Honors & Awards
- Scholar of Jesus College, Cambridge (for outstanding academic performance), 2024.
- PhD Scholarship, Cambridge Trust, 2023.
- Master Scholarship, Cambridge Trust, 2022.
- National Scholarship (1%), Ministry of Education of China, 2019.