Yuang Peng (彭雨昂)

Master Student at ITML Group, Tsinghua University.

Research Intern,
Foundation Model Group, Megvii Research (Face++).

Research: As a researcher and engineer specializing in large language model, my primary focus on the development of efficient and scalable methods for multimodal data modeling, with particular emphasis on text, images, and videos. My interest spans multiple ares, including generative modeling, representation learning, reinforcement learning, and embodied AI. My ultimate ambition is to cultivate multimodal perception, reasoning, and generation capabilities for Artificial General Intelligence (AGI), with the goal of creating fully intelligent systems and robots that can enhance human lives.

Experience: I am currently pursuing my Master’s degree in Computer Science at Tsinghua University, advised by Shutao Xia and Bin Chen. I was a research intern at Foundation Model Group, Megvii Research, and Shanghai Artificial Intelligence Laboratory. I was a short-term visiting scholar at the Artificial Intelligence Group, University of Cambridge, advised by Pietro Liò. I obtained my Bachelor’s degree in Computer Science from Wuhan University, where I was recognized as a distinguished graduate and graduated summa cum laude.


Jun 25, 2024 Introduce DreamBench++: A Human-Aligned Benchmark for Personalized Image Generation
Sep 20, 2023 Introduce multimodal LLM: DreamLLM

Selected Publications

  1. arXiv
    DreamBench++: A Human-Aligned Benchmark for Personalized Image Generation
    Yuang Peng*, Yuxin Cui*, Haomiao Tang*, Zekun Qi, Runpei Dong, Jing Bai, Chunrui Han, Zheng GeXiangyu Zhang, and Shu-Tao Xia
    arXiv preprint arXiv:2307.09474, 2024
  2. ICLR
    Dreamllm: Synergistic multimodal comprehension and creation
    Runpei Dong*, Chunrui Han*, Yuang Peng, Zekun Qi, Zheng Ge, Jinrong Yang, Liang Zhao, Jianjian Sun, Hongyu Zhou, Haoran Wei, Xiangwen Kong, Xiangyu Zhang, Kaisheng Ma, and Yi Li
    ICLR Spotlight Presentation (4.96%), 2023
  3. IJCAI
    Chatspot: Bootstrapping multimodal llms via precise referring instruction tuning
    Liang Zhao*, En Yu*, Zheng Ge, Jinrong Yang, Haoran Wei, Hongyu Zhou, Jianjian Sun, Yuang PengRunpei Dong, Chunrui Han, and Xiangyu Zhang
    IJCAI Long Oral Presentation (4%), 2023
  4. IEEE RA-L
    Exploring recurrent long-term temporal fusion for multi-view 3d perception
    Chunrui Han, Jianjian Sun, Zheng Ge, Jinrong Yang, Runpei Dong, Hongyu Zhou, Weixin Mao, Yuang Peng, and Xiangyu Zhang
    IEEE Robotics and Automation Letters, 2023