I am a researcher at ByteDance, working on medical multimodal large language models and agentic medical AI systems. My recent research focuses on medical image caption generation, complex disease diagnosis, and optimizing medical agent capabilities for understanding and reasoning over heterogeneous clinical data.

From April 2020 to April 2025, I worked at Tencent Youtu Lab, where I developed computer vision and generative AI models for virtual try-on, image generation, video understanding, frame interpolation, and image colorization. I received my M.A. from Zhejiang University in 2020 and my B.A. from Harbin Institute of Technology in 2017.

News

  1. Joined ByteDance as a researcher working on medical multimodal large language models.
  2. Released FitDiT, a high-fidelity virtual try-on system based on SD3.
  3. Released FluxFit, a virtual try-on project based on FLUX.1-dev.
  4. One paper on fast identity-preserved personalization was accepted by CVPR 2024.
  5. One paper on video action recognition was accepted by AAAI 2024.
  6. One paper on video frame interpolation was published in IEEE Transactions on Image Processing.
  7. One paper on image colorization was accepted by ECCV 2022.

Publications

Full list on Scholar

Selected Publications

Group-wise Data Ordering Figure 2 pipeline

Group-wise Data Ordering: Enhancing Instruction Tuning of Large Language Models via Embedding Proximity

Yiwen Ye, Boyuan Jiang, Xiaobin Hu, Shengzhi Wang, Xiaozhong Ji, Jinghao Lin, Deli Yu, Jiale Chen, Kai Wu, Haihua Yang, Yong Xia

ICML 2026

MedXIAOHE framework teaser

MedXIAOHE: A Comprehensive Recipe for Building Medical MLLMs

Baorong Shi, Bo Cui, Boyuan Jiang, Deli Yu, Fang Qian, Haihua Yang, Huichao Wang, Jiale Chen, Jianfei Pan, Jieqiong Cao, Jinghao Lin, Kai Wu, Lin Yang, Shengsheng Yao, Tao Chen, Xiaojun Xiao, Xiaozhong Ji, Xu Wang, Yijun He, Zhixiong Yang

arXiv 2026

Full Publication List 20 more publications
Oracle bone inscriptions dataset teaser

Oracle Bone Inscriptions Multi-modal Dataset

Bang Li*, Donghao Luo*, Yujie Liang, Jing Yang, Zengmao Ding, Xu Peng, Boyuan Jiang, Shengwei Han, Dan Sui, Peichao Qin, Pian Wu, Chaoyang Wang, Yun Qi, Taisong Jin, Chengjie Wang, Xiaoming Huang, Zhan Shu, Rongrong Ji, Yongge Liu, Yunsheng Wu

arXiv 2024

Awards & Honors

  • First Place, CURE-Bench @ NeurIPS 2025. Therapeutic reasoning benchmark competition.
  • Winner, CVPR NTIRE 2021 Challenge on Video Spatial-Temporal Super-Resolution. Team Imagination.