Zhuokai Zhao
Research Scientist, Meta AI
PhD in Computer Science, University of Chicago
Email / Google Scholar / Semantic Scholar / Github / LinkedIn / X (Twitter) / Resume

Biography
I am currently a Senior Research Scientist at Meta AI. I got my PhD in Computer Science from the University of Chicago, where I was fortunate to have been working with Prof. Yuxin Chen, Prof. Bo Li, and Prof. Michael Maire. Prior to that, I received my Master's degree in Robotics from the Johns Hopkins University, under the supervision of Prof. Nassir Navab, and my Bachelor's degree with Honors in Electrical Engineering from the University of Illinois at Urbana-Champaign, where I was working with Prof. Seth Hutchinson.

My research focuses on developing novel algorithms to enhance the post-training effectiveness (e.g., improved reasoning, reduced hallucinations) and efficiency (e.g., lower data and compute requirements) of multimodal large language models (MLLMs), as well as multi-agent systems that leverage them.

News & Updates
Publications (* indicates co-first authorship, † indicates equal mentorship)
2025
CircuitProbe: Dissecting Spatiotemporal Visual Semantics with Circuit Tracing
Yiming Zhang*, Chengzhang Yu*, Zhuokai Zhao*, Kun Wang, Qiankun Li, Zihan Chen, Yang Liu, Zenghui Ding, and Yining Sun
In submission, 2025
PDF / Code
RankCLIP: Ranking-Consistent Language-Image Pretraining
Yiming Zhang*, Zhuokai Zhao*, Zhaorun Chen, Zhili Feng, Zenghui Ding, and Yining Sun
International Conference on Computer Vision (ICCV), 2025
PDF / Code
Beyond Training: Dynamic Token Merging for Zero-Shot Video Understanding
Yiming Zhang, Zhuokai Zhao, Zhaorun Chen, Zenghui Ding, Xianjun Yang, and Yining Sun
International Conference on Computer Vision (ICCV), 2025
PDF / Code
S'MoRE: Structural Mixture of Residual Experts for LLM Fine-tuning
Hanqing Zeng, Yinglong Xia, Zhuokai Zhao, Gilbert Jiang, Qiang Zhang, Jiayi Liu, Lizhu Zhang, Xiangjun Fan, and Benyu Zhang
In submission, 2025
PDF
CAFe: Unifying Representation and Generation with Contrastive-Autoregressive Finetuning
Hao Yu, Zhuokai Zhao, Shen Yan, Lukasz Korycki, Jianyu Wang, Baosheng He, Jiayi Liu, Lizhu Zhang, Xiangjun Fan, and Hanchao Yu
ICCV Findings, 2025
PDF / Project Page / Code
Autonomous Multimodal Reasoning via Implicit Chain-of-Vision
Yiqiao Huang*, He Qi*, Zhaorun Chen, Haopeng Zhang, Hanchao Yu, and Zhuokai Zhao
CVPR Workshop on Multimodal Algorithmic Reasoning (Oral Presentation), 2025
PDF
2024
From Uncertainty to Trust: Enhancing Reliability in Vision-Language Models with Uncertainty-Guided Selective Decoding
Yixiong Fang, Ziran Yang, Zhaorun Chen, Zhuokai Zhao†, and Jiawei Zhou†
In submission, 2024
PDF / Code
Direct Acquisition Optimization for Low-Budget Active Learning
Zhuokai Zhao, Yibo Jiang, and Yuxin Chen
38th NeurIPS Workshop on Bayesian Decision-making and Uncertainty (Spotlight Talk), 2024
PDF / Code
EscIRL: Evolving Self-Contrastive IRL for Trajectory Prediction in Autonomous Driving
Siyue Wang*, Zhaorun Chen*, Zhuokai Zhao, Chaoli Mao, Yiyang Zhou, Jiayu He, and Albert Sibo Hu
8th Annual Conference on Robot Learning (CoRL), 2024
PDF / Code
Multimodal Guidance Network for Missing-Modality Inference in Content Moderation
Zhuokai Zhao, Harish Palani, Tianyi Liu, Lena Evans, and Ruth Toner
IEEE International Conference on Multimedia and Expo (ICME), 2024
PDF / Code
MJ-BENCH: Is Your Multimodal Reward Model Really a Good Judge for Text-to-Image Generation?
Zhaorun Chen*, Yichao Du*, Zichen Wen*, Yiyang Zhou*, Chenhang Cui, Zhenzhen Weng, Haoqin Tu,
Chaoqi Wang, Zhengwei Tong, Qinglan Huang, Canyu Chen, Qinghao Ye, Zhihong Zhu, Yuqing Zhang, Jiawei Zhou,
Zhuokai Zhao, Rafael Rafailov, Chelsea Finn, and Huaxiu Yao
41st ICML Workshop on Foundation Models in the Wild, 2024
PDF / Project Page / Code
HALC: Object Hallucination Reduction via Adaptive Focal-Contrast Decoding
Zhaorun Chen*, Zhuokai Zhao*, Hongyin Luo, Huaxiu Yao, Bo Li, and Jiawei Zhou
41st International Conference on Machine Learning (ICML), 2024
Preliminary version appeared in 12th ICLR Workshop on Reliable and Responsible Foundation Models, 2024
PDF / Project Page / Code
AutoPRM: Automating Procedural Supervision for Multi-Step Reasoning via Controllable Question Decomposition
Zhaorun Chen*, Zhuokai Zhao*, Zhihong Zhu*, Ruiqi Zhang, Xiang Li, Bhiksha Raj, and Huaxiu Yao
Annual Conference of the North American Chapter of the Association for Computational Linguistics (NAACL), 2024
Preliminary version appeared in ICLR Workshop on Reliable and Responsible Foundation Models, 2024
PDF / Code
2023
RELAX: Reinforcement Learning Enabled 2D-LiDAR Autonomous System for Parsimonious UAVs
Guanlin Wu, Zhuokai Zhao, and Yutao He
39th AAAI Workshop on Planning and Reinforcement Learning (PRL), 2023
PDF / Code

Breaking the Curse of Quality Saturation with User-Centric Ranking
Zhuokai Zhao, Yang Yang, Wenjie Hu, and Shuang Yang
29th Conference on Knowledge Discovery and Data Mining (KDD), 2023
PDF / Code

2020
Dissertations
Enhanced Data Utilization for Efficient and Trustworthy Deep Learning
Zhuokai Zhao
Ph.D. in Computer Science, 2024
PDF
Utilizing Both Past and Future: Multi-Frame Memory Based Network in Solving Particle Image Velocimetry
Zhuokai Zhao
MS in Computer Science, 2021
PDF / Code
Other Projects
Trajectory Planning and Control for Nonholonomic Robot Among Onstacles
Zhuokai Zhao, Mengdi Xu, and Changxin Yan
Nonlinear Control and Planning in Robotics, 2018
PDF / Code
Service
Conference Reviewer Journal Reviewer





Last Updated: August 24, 2025