Zikai Zhou

Zikai Zhou

Iā€™m interested in Model Efficiency and AIGC.

šŸ”„ News

  • Reviewer: ICML, NeurIPS, ICLR, CVPR, ICCV, ECCV, AAAI, MM, IJCAI etc.
  • Session Chair: IJCAI 2024.

šŸ“– Internships

  • 2022.03 - 2022.09, Research Intern at BIT. Advised by Prof. Xiqian Wang
  • 2022.11 - 2023.09, Research Intern at BIT. Advised by Prof. Kun Qian
  • 2024.04 - 2025.09, Research Assistant at HKUST-GZ. Advised by Prof. Zeke Xie
  • 2024.06 - present, Algorithm Engineer at Fuguang AI.

šŸ“ Research Publications

(*: Equal Contribution; ${}^\dagger$: Corresponding Author)

Golden noise for diffusion models: A learning framework

Zikai Zhou, Shitong Shao, Lichen Bai, Zhiqiang Xu, Bo Han, ${Zeke Xie}^\dagger$

  • [[ICCV 2025]]

IV-Mixed Sampler: Leveraging Image Diffusion Models for Enhanced Video Synthesis

Shitong Shao$^*$, ${Zikai Zhou}^*$, Lichen Bai, Haoyi Xiong, ${Zeke Xie}^\dagger$

  • [[ICLR 2025]]

Zigzag Diffusion Sampling: The Path to Success Is Zigzag

Lichen Bai, Shitong Shao, Zikai Zhou, Zipeng Qi, Zhiqiang Xu, Haoyi Xiong, ${Zeke Xie}^\dagger$

  • [[ICLR 2025]]

Rethinking Centered Kernel Alignment in Knowledge Distillation

Zikai Zhou, Yunhang Shen, Shitong Shao, Linrui Gong, ${Shaohui Lin}^\dagger$

  • [[IJCAI 2024]] (_orally presented_)

Elucidating the Design Space of Dataset Condensation

Shitong Shao, Zikai Zhou, Huanran Chen, ${Zhiqiang Shen}^\dagger$

  • [[NeurIPS 2024]]

Improved and Accelerated Text-to-Image Generation with Collect, Reflect, and Refine

Shitong Shao, Zikai Zhou, Dian Xie, Yuetong Fang, Tian Ye, Lichen Bai, Bo Han, ${Zeke Xie}^\dagger$

  • [[TPAMI 2026]]

Guidance Matters: Rethinking the Evaluation Pitfall for Text-to-Image Generation

Dian Xie$^$, Shitong Shao$^$, Lichen Bai, Zikai Zhou, Bojun Cheng, Shuo Yang, Wu Jun, ${Zeke Xie}^\dagger$

  • [[ICLR 2026]]

Optimizing Few-Step Generation with Adaptive Matching Distillation

Lichen Bai$^*$, ${Zikai Zhou}^*$, Wenliang Zhong, Shitong Shao, Shuo Yang, Shuo Chen, Bojun Cheng, ${Zeke Xie}^\dagger$

  • [[ICML 2026 Under Review]]

Lightning Unified Video Editor via In-Context Sparse Attention

Shitong Shao$^*$, ${Zikai Zhou}^*$, Haopeng Li, Yingwei Song, Wenliang Zhong, Lichen Bai, ${Zeke Xie}^\dagger$

  • [[ICML 2026 Under Review]]

Exploring the Design Space for Inference Enhancement and Acceleration of Masked Generative Transformer

Shitong Shao$^*$, ${Zikai Zhou}^*$, Ye Tian, Lichen Bai, Zhiqiang Xu, Shuo Yang, Bo Han, ${Zeke Xie}^\dagger$

  • [[IJCV Under Review]]

Reflective Flow Sampling Enhancement

*${Zikai Zhou}^$*, Muyao Wang$^$, Shitong Shao, Dian Xie, Lichen Bai, ${Zeke Xie}^\dagger$

  • [[TPAMI 2026 Under Review]]

Exploring LoRA Transferrability for Video Diffusion Models

Yuchen Wang, Wenliang Zhong, Lichen Bai, Zikai Zhou, Shitong Shao, Bojun Cheng, Shuo Chen, Shuo Yang, ${Zeke Xie}^\dagger$

  • [[ICML 2026 Under Review]]

PISA: Piecewise Sparse Attention Is Wiser for Efficient Diffusion Transformers

Hao Peng Li, Shitong Shao, Lichen Bai, Zikai Zhou, Wenliang Zhong, Hui Xiong, ${Zeke Xie}^\dagger$

  • [[ICML 2026 Under Review]]

Diffusion Dataset Condensation: Training Your Diffusion Model Faster with Less Data

Rui Huang$^$, Shitong Shao$^$, Zikai Zhou, Tian Ye, Lichen Bai, Shuo Yang, ${Zeke Xie}^\dagger$

  • [[CVPR 2026 Under Review]]

The Blessing of Smooth Initialization for Video Diffusion Models

Shitong Shao, Lichen Bai, Zikai Zhou, Tian Ye, Yunfeng Cai, Kaishun Wu, ${Zeke Xie}^\dagger$

  • [[TPAMI Under Review]]

šŸ’¼ Academic Service

  • [Invited Talk] Invited by the Qingke Community to present research on inference optimization for diffusion models.