Chenyu Yang

About Me

I am a Ph.D. student at Tsinghua University, advised by Jifeng Dai.

I aim to build general-purpose intelligent systems that can reason, learn from experience, and solve complex tasks in open-ended environments. My current research focuses on:

• Large Language Models (LLMs)
• AI Agents and Reinforcement Learning

Previously, I worked on multimodal learning, including vision-language models and visual representation learning.

Education

• Ph.D. · Tsinghua University

  2023–2028 (expected)

  Department of Electronic Engineering

• B.E. · Tsinghua University

  2019–2023

  Institute for Interdisciplinary Information Sciences (Yao Class)

Projects

• 

  MiroThinker: Deep Research through Interactive Scaling

  MiroMind · Research Intern

  • Agentic RL: Scaling tool interactions to improve long-horizon deep research agents.

  • Context management: Managing agent context for extended reasoning and tool interactions.

  Report Code
• 

  ZeroGUI: Automating Online GUI Learning at Zero Human Cost

  Shanghai AI Lab · Research Intern

  • Online RL: Enabling GUI agents to learn and improve via interactions with environments.

  • Automated learning framework: Removing manual task annotations for scalable GUI training.

  Report Code

Publications

1. CVPR

   PVC: Progressive Visual Token Compression for Unified Image and Video Processing in Large Vision-Language Models

   Chenyu Yang, Xuan Dong, Xizhou Zhu, Weijie Su, Jiahao Wang, Hao Tian, Zhe Chen, Wenhai Wang, Lewei Lu, Jifeng Dai

   CVPR 2025

   Paper Code
2. NeurIPS

   Vision Model Pre-training on Interleaved Image-Text Data via Latent Compression Learning

   Chenyu Yang, Xizhou Zhu, Jinguo Zhu, Weijie Su, Junjie Wang, Xuan Dong, Wenhai Wang, Lewei Lu, Bin Li, Jie Zhou, Yu Qiao, Jifeng Dai

   NeurIPS 2024

   Paper Code
3. CVPR

   BEVFormer v2: Adapting Modern Image Backbones to Bird’s-Eye-View Recognition via Perspective Supervision

   Chenyu Yang, Yuntao Chen, Hao Tian, Chenxin Tao, Xizhou Zhu, Zhaoxiang Zhang, Gao Huang, Hongyang Li, Yu Qiao, Lewei Lu, Jie Zhou, Jifeng Dai

   CVPR 2023 Highlight

   Paper Code
4. ECCV

   EleGANt: Exquisite and Locally Editable GAN for Makeup Transfer

   Chenyu Yang, Wanrong He, Yingqing Xu, Yang Gao

   ECCV 2022

   Paper Code

Powered by Jekyll and Minimal Light theme.