Scholar
Chengzu Li
Google Scholar ID: t_Bwt70AAAAJ
University of Cambridge
Citations & Impact
Citations
745
H-index
8
i10-index
7
Publications
13
Co-authors
10
list available
Publications
Resume (English only)
Academic Achievements
- Preprints:
- - 11Plus-Bench: Demystifying Multimodal LLM Spatial Reasoning with Cognitive-Inspired Analysis
- - Visual Planning: Let's Think Only with Images
- - Scaling and Beyond: Advancing Spatial Reasoning in MLLMs Requires New Recipes
- - Reinforcement Learning for Better Verbalized Confidence in Long-Form Generation
- 2025 Publications:
- - Imagine while Reasoning in Space: Multimodal Visualization-of-Thought
- - Large Language Models are Miscalibrated In-Context Learners
- - Enriching Patent Claim Generation with European Patent Dataset
- - Lost in Embeddings: Information Loss in Vision-Language Models
- 2024 Publications:
- - TopViewRS: Vision-Language Models as Top-View Spatial Reasoners
- - Semantic Map-based Generation of Navigation Instructions
- 2023 Publications:
- - Generating Data for Symbolic Language with Large Language Models
- - Binding Language Models in Symbolic Languages
- 2022 Publications:
- - UnifiedSKG: Unifying and Multi-Ta
Research Experience
- Current research focuses on:
- - Evaluation with explanatory and predictive power
- - Paradigm and methods for multimodal reasoning
- - Potential downstream application scenarios of multimodal reasoning
Education
- - PhD (Probationary) in Computation, Cognition and Language, Language Technology Lab, University of Cambridge, 2023 - present
- - 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)
Background
- Research interests include language grounding and multimodal reasoning (e.g., images, structural knowledge, etc.), especially spatial reasoning. Currently a third-year PhD student in Computation, Cognition and Language at the Language Technology Lab, University of Cambridge, supervised by Dr. Ivan Vulić, Prof. Anna Korhonen, and Prof. Serge Belongie.
