Zhen Zou（邹振） |

About Me 👋

I am currently at ByteDance BandAI, working on Agent. Before joining ByteDance full-time, I received my master’s degree from the Department of Automation at the University of Science and Technology of China (USTC) in 2026, after completing my bachelor’s degree at USTC in June 2023.

My recent work has appeared in ECCV, CVPR, and ACM Multimedia. My previous work focused on AIGC, efficient video generation, and training/inference acceleration for video generation models. I am interested in building efficient, controllable AI systems that connect high-quality generation, multimodal reasoning, and practical tool use.

Research Interests 🔭

AIGC ✨ Efficient generation, controllable visual generation, and multimodal creation.

Efficient AI ⚡ Feature caching, single-step generation, and inference efficiency for practical generation systems.

Agent 🧭 Tool use, multimodal reasoning, and agent workflows for effect generation, evaluation, and iterative refinement.

News 🗞️

[Jul. 2026] Drift-AR was accepted by ECCV 2026.
[Jun. 2026] I graduated from USTC with a master’s degree and joined ByteDance.
[Jul. 2025] AB-Cache was accepted by ACM Multimedia 2025.
[Feb. 2025] Adaptive Dropout was accepted by CVPR 2025.
[Jul. 2024] FreqMamba was accepted by ACM Multimedia 2024.

Experience 💼

[Jun. 2026 - Present] ByteDance BandAI Working on Agent after graduating from USTC.
[Apr. 2025 - Jun. 2026] ByteDance, Intern Worked on inference acceleration for video generation models and agent-related systems.
[Dec. 2024 - Apr. 2025] TeleAI, Intern Participated in training and inference acceleration for VAST, a video generation model.

Publications

ECCV 2026

Drift-AR: Single-Step Visual Autoregressive Generation via Anti-Symmetric Drifting

Z. Zou, X. Ma, M. Yao, J. Huang, L. J. Huang, F. Zhao

European Conference on Computer Vision (ECCV), 2026.

PDF
ACM MM 2025

AB-Cache: Training-Free Acceleration of Diffusion Models via Adams-Bashforth Cached Feature Reuse

Z. Yu, Z. Zou, G. Shao, C. Zhang, S. Xu, J. Huang, F. Zhao, X. Cun, W. Zhang

Proceedings of the 33rd ACM International Conference on Multimedia, 2025.

PDF Code
CVPR 2025

Adaptive Dropout: Unleashing Dropout Across Layers for Generalizable Image Super-Resolution

H. Xu, J. Huang, W. Yu, J. Tan, Z. Zou, F. Zhao

Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2025.

PDF
arXiv 2025

FEB-Cache: Frequency-Guided Exposure Bias Reduction for Enhancing Diffusion Transformer Caching

Z. Zou, F. Zhao

arXiv preprint arXiv:2503.07120, 2025.

PDF Code
ACM MM 2024

FreqMamba: Viewing Mamba from a Frequency Perspective for Image Deraining

Z. Zou, H. Yu, J. Huang, F. Zhao

Proceedings of the 32nd ACM International Conference on Multimedia, 2024.

PDF Code
CVPRW 2024

Semantic Pre-Supplement for Exposure Correction

Z. Zou, W. Yu, J. Huang, F. Zhao

Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2024.

PDF

Education 🎓

[2023 - 2026] M.S., Department of Automation, University of Science and Technology of China.
[2019 - 2023] B.E., University of Science and Technology of China.