About Me

Currently, I am a Research Intern at StepFun, mentored by Dr. Quan Sun. Before that, I was a Research Intern at MSRA, mentored by Dr. Dong Chen. I also closely work with Jingwei Wu, Guopeng Li, Ruichuan An.

My research interests focus on unified understanding and generation in MLLM. Please email me if you want to collaborate on academic research or have any questions.

🔥 News

• 2026.02: 🎉Two papers (UNIM and Draco) are accepted by CVPR 2026.

📝 Selected Publications Full Publications List

CoCo: Code as CoT for Text-to-Image Preview and Rare Concept Generation

Haodong Li, Chunmei Qing, Huanyu Zhang, Dongzhi Jiang, Yihang Zou, Hongbo Peng, Dingming Li, Yuhong Dai, ZePeng Lin, Juanxi Tian, Yi Zhou, Siqi Dai
ArXiv, 2026
[ArXiv] [Code]

GEBench: Benchmarking Image Generation Models as GUI Environments

Haodong Li, Juanxi Tian, Jingwei Wu, Quan Sun, Guopeng Li, Huanyu Zhang, Yanlin Lai, Ruichuan An, Hongbo Peng, Yuhong Dai, Chenxi Li, Chunmei Qing, Zheng Ge, Xiangyu Zhang, Daxin Jiang
ArXiv, 2026
[ArXiv] [Code] [Page]

Draco: Draft as CoT for Text-to-Image Preview and Rare Concept Generation

Dongzhi Jiang, Renrui Zhang, Haodong Li, Zhuofan Zong, Ziyu Guo, Jun He, Claire Guo, Junyan Ye, Rongyao Fang, Weijia Li, Rui Liu, †Hongsheng Li
CVPR 2026 Findings
[ArXiv] [Code]

UNIM: A Unified Any-to-Any Interleaved Multimodal Benchmark

Yanlin Li, Minghui Guo, Kaiwen Zhang, Shize Zhang, Yiran Zhao, Haodong Li, Congyue Zhou, Weijie Zheng, Yushen Yan, Shengqiong Wu, Wei Ji, Lei Cui, †Furu Wei, Hao Fei, Mong-Li Lee, Wynne Hsu
CVPR 2026
[Page]

💻 Experiences

2025.10 - Present, Research Intern, StepFun, Foundation Model Group

2025.03 - 2025.09, Research Intern, Microsoft Research Asia (MSRA), Visual Computing Group

🖼️ Gallery

You can zoom images by clicking 🤫