About Me

I am a Master’s student at Zhejiang University, advised by Prof. Shengyu Zhang. My research focuses on 3D content generation and efficient inference for visual generative models.

Specifically, I work on Speech-driven Talking Face & Text/Image-to-3D Generation, as well as Step Distillation & Training-free Acceleration Methods for Diffusion and Visual Autoregressive (VAR) models.

My goal is to make high-fidelity visual generation—spanning 3D, images, and video— more practical and efficient for real-world and real-time applications.

🔥 News

2026.07: 🎉🎉 1 paper accepted to ACM MM 2026.
2025.02: 🎉🎉 1 paper accepted to ICLR 2025.

📝 Publications

ACM MM 2026

PruneVAR: Training-Free Acceleration of Visual Autoregressive Modeling via Two-Stage Redundancy Reduction.

Jiajian Xie, Jie Yang, Shengyu Zhang

ICLR 2025

Ecoface: Audio-visual emotional co-disentanglement speech-driven 3d talking face generation.

Jiajian Xie, Shengyu Zhang, Mengze Li, Chengfei Lv, Zhou Zhao, Fei Wu

ETC: training-free diffusion models acceleration with Error-aware Trend Consistency.

Jiajian Xie, Hubery Yin, Chen Li, Zhou Zhao, Shengyu Zhang
EC-Diff: Fast and High-Quality Edge-Cloud Collaborative Inference for Diffusion Models.

Jiajian Xie, Shengyu Zhang, Zhou Zhao, Fan Wu, Fei Wu

🎖 Honors and Awards

2025.10, National Scholarship (P.R. China).
2023.10, National Scholarship (P.R. China).

📖 Educations

2024.09 - 2027.06, Master, Artificial Intelligence, Zhejiang University.
2020.09 - 2024.06, Undergraduate, Electronic Business and Computer Science (Dual Degree), SouthChina University of Technology.

💻 Internships