Jinyuan Mao
Portrait of Jinyuan Mao

Undergraduate Researcher · Zhejiang University

Jinyuan Mao 茅晋源

I am a senior undergraduate at Zhejiang University, pursuing a dual degree in Statistics and Information Management & Information Systems. My research is on generative models and efficient AI in computer vision. I am interested in making image and video generators more efficient, more controllable, and simply better at what they model. Lately I have been working on improving pixel-space diffusion transformers (JiT).

Most recently, I was a research intern at PixAI, working with Chenxi Liu (University of Victoria) on interactive image generation. Before that, I spent eight months at the ZIP Lab advised by Prof. Bohan Zhuang, working on sparse attention and KV-cache design for long video generation.

I also enjoy high-performance computing: our team placed 1st globally at the SC25 IndySCC, and I look after the GPU infrastructure at ZJU X-Lab.

  • Generative Models
  • Diffusion Models
  • Efficient AI
  • Image & Video Generation
jymao@zju.edu.cn CV GitHub Notes
1/20Major rank · GPA 92.5
3×National Scholarship
3Papers, all first / co-first
#1SC25 IndySCC, global

News

Publications

* equal contribution

SIGGRAPH Asia 2026

BIFE: Better Interaction, Fewer Errors for Minute-Long Video Generation

Zeyu Zhang*, Jinyuan Mao*, Shuning Chang, Yuanyu He, Yizeng Han, Jiasheng Tang, Fan Wang, Bohan Zhuang

SIGGRAPH Asia 2026, Technical Communications

A semantic sparse KV cache retrieves the long-range context that minute-long generation needs, cutting error accumulation and improving VDE-Subject by 22.2%.

arXiv PDF
NeurIPS 2026 · Reviewed

WorldAttention: An Efficient Attention Architecture for Interactive Video World Models

Zeyu Zhang*, Jinyuan Mao*, Dakai An*, Wangbo Zhao, Hanfeng Lu, Jiasheng Tang, Yinghao Yu, Wei Wang, Bohan Zhuang

NeurIPS 2026 Reviewed 5/5/5 · Accept / Accept / Accept

Attention heads in video diffusion transformers are sparse in very different ways. Hybrid Sparse Attention pairs a linear global branch with head-adaptive block-sparse attention for a 2.21× end-to-end speedup at matched quality.

arXiv PDF
Eurographics 2027

HimmBO: High-Dimensional Interactive Model-Merging Bayesian Optimization for Image Generation

Jinyuan Mao, Zhihao Shen, Chenxi Liu

Under review at Eurographics 2027

Two-stage preferential Bayesian optimization scales interactive LoRA merging from a few dozen to 1,080 adapters. A style-aware kernel shares preferences across similar adapters, so it needs under 1/10 of the image generations used by prior work.

Paper coming soon

Research Experience

  1. PixAI Research Intern

    Jun 2026 – Oct 2026

    Interactive image generation · Advised by Chenxi Liu (University of Victoria)

    • Led HimmBO as first author: method design, implementation, experiments and writing.
    • Built a two-stage preferential Bayesian optimization framework that scales interactive LoRA merging to 1,080 adapters. Its level-set screening stage generates no images during interaction.
    • Designed a style-aware kernel that transfers preference information across visually similar adapters, reaching a target similarity with under 1/10 of the image generations prior work needs.

  2. ZIP Lab, Zhejiang University Research Intern

    Oct 2025 – Jun 2026

    Efficient video generation & world models · Advised by Prof. Bohan Zhuang

    • Worked on sparse attention and KV-cache design for video generation, as co-first author of WorldAttention and BIFE.

  3. Provincial SRTP Project Project Leader

    Apr 2024 – Jun 2025

    Database agent framework · Zhejiang University

    • Proposed a two-stage trial-and-error learning framework that improves how database agents interact, with clear gains on research benchmarks. Filed one national invention patent.

Education

Zhejiang University

Sep 2023 – Jun 2027

B.S. in Statistics & B.Mgt. in Information Management and Information Systems (dual degree) · Hangzhou, China

GPA 92.5/100Rank 1/20

Honors & Awards

Other Experience

  1. ZJU X-Lab Operations & Infrastructure Lead

    Jun 2025 – Present

    Student-run innovation organization

    • Run the GPU clusters with Docker-isolated environments for 10+ projects. Built the private Overleaf, NAS storage, VPN and the organization's website.

  2. Nodesk AI AI Engineering Intern

    Jun 2025 – Aug 2025

    Industry internship · Hangzhou

    • Built a smart-reply cross-validation module and fine-tuned it for a 15% accuracy gain. Co-authored a patent on a guardrail that combines reranking models with scenario recognition.

Skills

Languages
PythonC/C++SQLLaTeX
ML & Systems
PyTorchDiffusersMPIOpenMPDockerLinux