Zhuowan Li

Zhuowan Li (李卓婉)

I am a software engineer at Google Deepmind. I am currently working on LLM post-training, with a specific focus on LLM personalization.

I finished my Ph.D. in Feb 2024 from Johns Hopkins University, co-advised by Prof. Alan Yuille and Benjamin Van Durme. I am a member of the CCVL lab. I received my B.E. degree from Tsinghua Univeristy in 2018, where I double major in Electronic Engineering and Journalism and Communication. I have also interned at Amazon AWS, Meta AI, Adobe Research and Sensetime.

In part time, I am a big fan of outdoor sports including rock climbing, snowboarding, skiing, hiking, mountaineering, etc. I am learning tennis recently.

CV / Google Scholar / Twitter / Github

Email: lizhuowan14 at gmail dot com

News

[Nov 2024] I will attend EMNLP 2024 in person at Miami. Happy to connect!

[June 2024] I will attend CVPR 2024 in person at Seattle. Happy to chat!

[Feb 2024] I graduated from JHU and joined Google as a software engineer!

[June 2023] I will attend CVPR 2023 in person at Vancouver. Let me know if you want to talk with me!

[May 2023] Started as as applied scentist intern at Amazon AWS.

[May 2023] Invited talk at the Computational Cognitive Science Lab at MIT.

[February 2023] Super-CLEVR is accepted by CVPR 2023 as Highlight.

Last updated: 2025/07/28.

Publications

	Gemini 2.5: Pushing the Frontier with Advanced Reasoning, Multimodality, Long Context, and Next Generation Agentic Capabilities Gemini Team, Google Technical Report, 2025 arXiv
	Retrieval Augmented Generation or Long-Context LLMs? A Comprehensive Study and Hybrid Approach Zhuowan Li, Cheng Li, Mingyang Zhang, Qiaozhu Mei, Michael Bendersky EMNLP Industry Track, 2024 arXiv / poster
	ExoViP: Step-by-step Verification and Exploration with Exoskeleton Modules for Compositional Visual Reasoning Yuxuan Wang, Alan Yuille, Zhuowan Li, Zilong Zheng COLM, 2024 arXiv / code
	Synthesize Step-by-Step: Tools, Templates and LLMs as Data Generators for Reasoning-Based Chart VQA Zhuowan Li, Bhavan Jasani, Peng Tang, Shabnam Ghadar CVPR, 2024 arXiv
	Causal-CoG: A Causal-Effect Look at Context Generation for Boosting Multi-modal Language Models Shitian Zhao, Zhuowan Li, Yadong Lu, Alan Yuille, Yan Wang CVPR (Highlight, top 2.8%), 2024 arXiv / code
	On the Diagnosis and Generalization of Compositional Visual Reasoning Zhuowan Li Ph.D. thesis, 2024 pdf
	Localization vs. Semantics: How Can Language Benefit Visual Representation Learning? Zhuowan Li, Cihang Xie, Benjamin Van Durme, Alan Yuille EACL, 2024 arXiv / code (to be released)
	3D-Aware Visual Question Answering about Parts, Poses and Occlusions Xingrui Wang, Wufei Ma, Zhuowan Li, Adam Kortylewski, Alan Yuille NeurIPS, 2023 arXiv / code and dataset
	Super-CLEVR: A Virtual Benchmark to Diagnose Domain Robustness in Visual Reasoning Zhuowan Li, Xingrui Wang, Elias Stengel-Eskin, Adam Kortylewski, Wufei Ma, Benjamin Van Durme, Alan Yuille CVPR (Highlight, top 2.5%), 2023 project page / arXiv / code and dataset
	Visual Commonsense in Pretrained Unimodal and Multimodal Models Chenyu Zhang Benjamin Van Durme, Zhuowan Li, Elias Stengel-Eskin, NAACL (Oral), 2022 arXiv / code and dataset
	SwapMix: Diagnosing and Regularizing the Over-Reliance on Visual Context in Visual Question Answering Vipul Gupta, Zhuowan Li, Adam Kortylewski, Chenyu Zhang, Yingwei Li, Alan Yuille CVPR, 2022 arXiv / code
	Calibrating Concepts and Operations: Towards Symbolic Reasoning on Real Images Zhuowan Li, Elias Stengel-Eskin, Yixiao Zhang, Cihang Xie, Quan Tran, Benjamin Van Durme, Alan Yuille ICCV, 2021 arXiv / code
	Context-Aware Group Captioning via Self-Attention and Contrastive Features Zhuowan Li, Quan Tran, Long Mai, Zhe Lin, Alan Yuille CVPR, 2020 arXiv / project page
	FD-GAN: Pose-guided Feature Distilling GAN for Robust Person Re-identification Yixiao Ge, Zhuowan Li, Haiyu Zhao, Guojun Yin, Shuai Yi, Xiaogang Wang, Hongsheng Li NeurIPS, 2018 arXiv / project page / code

Website theme stolen from Jon Barron.