Portrait of Zanlin Ni

Zanlin Ni

Tsinghua University

Beijing, China

nzl22@mails.tsinghua.edu.cn

I am a Ph.D. student at Tsinghua University, advised by Prof. Gao Huang at LeapLab. I am also a research intern at DeepSeek, working on model architectures.

I study parallel sampling for generative AI, particularly for image generation and diffusion language models. My work The Flexibility Trap received the ICML 2026 Outstanding Paper Award.

news

Oct 24, 2026 Research updates: Co-GRPO and UNO are accepted at NeurIPS 2026. InsightTok received the LoViF @ ECCV 2026 Workshop Outstanding Paper Award and an Oral presentation!
Oct 24, 2026 Honored to receive the National Scholarship for Doctoral Students for the second consecutive year (2025 and 2026)!
Jul 06, 2026 πŸŽ‰ Our paper The Flexibility Trap received the ICML 2026 Outstanding Paper Award!
Jan 13, 2026 πŸŽ‰ New preprint The Flexibility Trap is out! Check out our project page.
Oct 27, 2025 πŸŽ‰ Our paper AdaGen is accepted by TPAMI (published online in 2025; volume publication in 2026)!

selected publications

  1. ICML
    FlexibilityTrap.png
    The Flexibility Trap: Rethinking the Value of Arbitrary Order in Diffusion Language Models
    Zanlin Ni, Shenzhi Wang, Yang Yue, and 8 more authors
    In International Conference on Machine Learning (ICML), 2026
    Outstanding Paper Β· Oral2/23918
    arXiv PDF Code Model Website
  2. NeurIPS
    CO_GRPO.png
    Co-GRPO: Co-Optimized Group Relative Policy Optimization for Masked Image Generation
    Renping Zhou*, Zanlin Ni*, Tianyi Chen, and 6 more authors
    In Advances in Neural Information Processing Systems (NeurIPS), 2026
    HTML
  3. ECCV Workshop
    InsightTok.png
    InsightTok: Improving Text and Face Fidelity in Discrete Tokenization for Autoregressive Image Generation
    Yang Yue, Fangyun Wei, Tianyu He, and 10 more authors
    In LoViF Workshop at the European Conference on Computer Vision (ECCV), 2026
    Outstanding Paper Β· Oral
    arXiv Code
  4. TPAMI
    AdaGen.png
    AdaGen: Learning Adaptive Policy for Image Synthesis
    Zanlin Ni*, Yulin Wang*, Yeguo Hua, and 5 more authors
    IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI) (published online in 2025) , 2026
    arXiv
  5. ICCV
    CODA.png
    CODA: Repurposing Continuous VAEs for Discrete Tokenization
    Zeyu Liu*, Zanlin Ni*, Yeguo Hua, and 4 more authors
    In IEEE/CVF International Conference on Computer Vision (ICCV), 2025
    arXiv Code
  6. NeurIPS
    ENAT.png
    ENAT: Rethinking Spatial-Temporal Interactions in Token-Based Image Synthesis
    Zanlin Ni*, Yulin Wang*, Renping Zhou, and 5 more authors
    In Advances in Neural Information Processing Systems (NeurIPS), 2024
    HTML Code
  7. ECCV
    AdaNAT.png
    AdaNAT: Exploring Adaptive Policy for Token-Based Image Generation
    Zanlin Ni*, Yulin Wang*, Renping Zhou, and 6 more authors
    In European Conference on Computer Vision (ECCV), 2024
    arXiv Code
  8. CVPR
    AutoNAT.png
    AutoNAT: Revisiting Non-Autoregressive Transformers for Efficient Image Synthesis
    Zanlin Ni*, Yulin Wang*, Renping Zhou, and 6 more authors
    In IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2024
    HTML Code
  9. NMI
    AdaptiveNN.png
    Emulating Human-like Adaptive Vision for Efficient and Flexible Machine Visual Perception
    Yulin Wang*, Yang Yue* (乐洋), Yang Yue* (乐阳), and 12 more authors
    Nature Machine Intelligence (NMI), 2025
    HTML Code
  10. IJCV
    InfoPro_IJCV.png
    InfoPro: Locally Supervised Deep Learning by Maximizing Information Propagation
    Yulin Wang*, Zanlin Ni*, Yifan Pu, and 4 more authors
    International Journal of Computer Vision (IJCV), 2025
    DOI Code
  11. ECCV
    LLaVA-UHD: An LMM Perceiving Any Aspect Ratio and High-Resolution Images
    Zonghao Guo, Ruyi Xu, Yuan Yao, and 6 more authors
    In European Conference on Computer Vision (ECCV), 2024
    PDF Code
  12. ICCV
    DeepIncubation.png
    Deep Incubation: Training Large Models by Divide-and-Conquering
    Zanlin Ni*, Yulin Wang*, Jiangwei Yu, and 3 more authors
    In IEEE/CVF International Conference on Computer Vision (ICCV), 2023
    HTML Code
  13. ICLR
    InfoPro_ICLR.png
    Revisiting Locally Supervised Learning: An Alternative to End-to-End Training
    Yulin Wang, Zanlin Ni, Shiji Song, and 2 more authors
    In International Conference on Learning Representations (ICLR), 2021
    arXiv Code
  14. CVPR
    USDL.png
    Uncertainty-Aware Score Distribution Learning for Action Quality Assessment
    Yansong Tang*, Zanlin Ni*, Jiahuan Zhou, and 4 more authors
    In IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2020
    Oral
    HTML Code