Curriculum Vitae

Download CV (Chinese, PDF)

Research Interests

Embodied intelligence; World Action Models; efficient generative AI; diffusion model architectures; model distillation and reinforcement learning.

Education

• Shanghai Jiao Tong University, Ph.D. in Artificial Intelligence, Sep. 2024 - Jun. 2029 (expected)
  School of Information and Electronic Engineering. Advisor: Professor Yu Cheng.
• Nanjing University, B.S. in Computer Science and Technology, Sep. 2020 - Jun. 2024
  Department of Computer Science and Technology. Top 5% of the program.

Research Experience

• Skywork, Remain Dynamic, Research Intern, Jul. 2026 - Present
  World Action Models for embodied intelligence.
• The Chinese University of Hong Kong, Research Assistant, Nov. 2025 - Feb. 2026
  Elastic routing, sparsity enhancement, expert-parallel load balancing, and parameter pruning for mixture-of-experts models.
• Tencent, Hunyuan, Research Intern, Jun. 2025 - Nov. 2025
  Efficient image, video, and 3D generation through distillation, caching, and reinforcement learning; developed Flash-DMD.
• Shanghai AI Laboratory, Research Intern, Oct. 2023 - Jun. 2025
  Efficient DiT architectures, autoregressive video representation compression, and reliable mixture-of-experts models; developed Skip-DiT, VRC, and MoE-RBench.
• Nanjing University, Reasoning and Learning Lab, Research Intern, Jun. 2022 - Jun. 2023
  Semi-supervised and weakly supervised learning for medical image segmentation.

Publications

Flash-DMD: Towards High-Fidelity Few-Step Image Generation with Efficient Distillation and Joint Reinforcement Learning

Guanjie Chen, Shirui Huang, Kai Liu, Jianchen Zhu, Xiaoye Qu, Peng Chen, Yu Cheng, and Yifu Sun. Flash-DMD: Towards High-Fidelity Few-Step Image Generation with Efficient Distillation and Joint Reinforcement Learning. CVPR, 2026.

Less is More: Vision Representation Compression for Efficient Video Generation with Large Language Models

Yucheng Zhou, Jihai Zhang, Guanjie Chen, Jianbing Shen, and Yu Cheng. Less is More: Vision Representation Compression for Efficient Video Generation with Large Language Models. AAAI, 2026.

Skip-DiT: Towards Stabilized and Efficient Diffusion Transformers through Long-Skip-Connections with Spectral Constraints

Guanjie Chen, Xinyu Zhao, Yucheng Zhou, Xiaoye Qu, Tianlong Chen, and Yu Cheng. Skip-DiT: Towards Stabilized and Efficient Diffusion Transformers through Long-Skip-Connections with Spectral Constraints. ICCV, 2025.

OpenThinkIMG: Learning to Think with Images via Visual Tool Reinforcement Learning

Zhaochen Su, Liang Li, Mingyang Song, Yuning Hao, Zhengyuan Yang, Jihai Zhang, Guanjie Chen, et al. OpenThinkIMG: Learning to Think with Images via Visual Tool Reinforcement Learning. arXiv:2505.08617, 2025.

MoE-RBench: Towards Building Reliable Language Models with Sparse Mixture-of-Experts

Guanjie Chen, Xinyu Zhao, Tianlong Chen, and Yu Cheng. MoE-RBench: Towards Building Reliable Language Models with Sparse Mixture-of-Experts. ICML, 2024.

Honors

• ICML Top Reviewer
• Global finalist, Citi Financial Innovation Application Competition
• Outstanding Student, Nanjing University
• National Encouragement Scholarship and People’s Scholarship