Chengqi Duan

PhD Candidate at The University of Hong Kong

I am currently a second-year PhD Candidate in the Institute of Data Science at The University of Hong Kong, supervised by Prof. Xihui Liu and Prof. Yi Ma. Prior to joining HKU, I received my Bachelor's degree in Department of Computer Science and Technology from Tsinghua University in 2024, where I was fortunate to work closely with Prof. Hang Su and Prof. Jun Zhu.

My research interests primarily lie in AIGC, Reinforcement Learning and Unified Models.

GitHub Google Scholar Semantic Scholar

Education

The University of Hong Kong (HKU)

Sep 2024 - Present

PhD in Institute of Data Science

Supervised by Prof. Xihui Liu and Prof. Yi Ma.

Hong Kong

Tsinghua University

Sep 2020 - Jul 2024

Bachelor of Computer Science

Worked closely with Prof. Hang Su and Prof. Jun Zhu.

GPA: 3.75/4.0

Beijing, China

Selected Publications (* denotes equal contribution)

Citation counts are given by Semantic Scholar.

GoT-R1: Unleashing Reasoning Capability of MLLM for Visual Generation with Reinforcement Learning

Chengqi Duan*, Rongyao Fang*, Yuqing Wang*, Kun Wang, Linjiang Huang, Xingyu Zeng, Hongsheng Li, Xihui Liu.

ICLR 2026

CodePlot-CoT: Mathematical Visual Reasoning by Thinking with Code-Driven Images

Chengqi Duan*, Kaiyue Sun*, Rongyao Fang*, Manyuan Zhang, Yan Feng, Ying Luo, Yufang Liu, Ke Wang, Peng Pei, Xunliang Cai, Hongsheng Li, Yi Ma, Xihui Liu.

CVPR 2026 Findings

T2I-CompBench++: An Enhanced and Comprehensive Benchmark for Compositional Text-to-image Generation

Kaiyi Huang, Chengqi Duan, Kaiyue Sun, Enze Xie, Zhenguo Li, and Xihui Liu.

TPAMI

Got: Unleashing reasoning capability of multimodal large language model for visual generation and editing

Rongyao Fang*, Chengqi Duan*, Kun Wang, Linjiang Huang, Hao Li, Hao Tian, Shilin Yan, Weihao Yu, Xingyu Zeng, Jifeng Dai, Xihui Liu, Hongsheng Li.

NeurIPS 2025

FLUX-Reason-6M & PRISM-Bench: A Million-Scale Text-to-Image Reasoning Dataset and Comprehensive Benchmark

Rongyao Fang*, Aldrich Yu*, Chengqi Duan*, Linjiang Huang, Shuai Bai, Yuxuan Cai, Kun Wang, Si Liu, Xihui Liu, Hongsheng Li.

ICLR 2026

PUMA: Empowering Unified MLLM with Multi-granular Visual Generation

Rongyao Fang*, Chengqi Duan*, Kun Wang, Hao Li, Hao Tian, Xingyu Zeng, Rui Zhao, Jifeng Dai, Hongsheng Li, Xihui Liu.

ICCV 2025

T2I-ReasonBench: Benchmarking Reasoning-Informed Text-to-Image Generation

Kaiyue Sun, Rongyao Fang, Chengqi Duan, Xian Liu, Xihui Liu.

Preprint

Robust Classification via Single Diffusion Model

Huanran Chen, Yinpeng Dong, Zhengyi Wang, Xiao Yang, Chengqi Duan, Hang Su, Jun Zhu.

ICML 2024

Internship Experience

Meituan (美团)

Jun 2025 - Present

Research Intern

SenseTime (商汤科技)

Sep 2024 - Jun 2025