Zehuan Yuan

Venues

Frequent coauthors

Papers

1. FlashVideo: Flowing Fidelity to Detail for Efficient High-Resolution Video Generation
   AAAI 2026 ·

   Shilong Zhang

   DBLP profile ↗ORCID search ↗
2. Goku: Flow Based Video Generative Foundation Models
   CVPR 2025 ·

   Shoufa Chen

   DBLP profile ↗ORCID search ↗
3. Infinity: Scaling Bitwise AutoRegressive Modeling for High-Resolution Image Synthesis
   CVPR 2025 ·

   Jian Han

   DBLP profile ↗ORCID search ↗
4. InfinityStar: Unified Spacetime AutoRegressive Modeling for Visual Generation
   NeurIPS 2025 ·

   Jinlai Liu

   DBLP profile ↗ORCID search ↗
5. TokenFlow: Unified Image Tokenizer for Multimodal Understanding and Generation
   CVPR 2025 ·

   Liao Qu

   DBLP profile ↗ORCID search ↗
6. UniTok: a Unified Tokenizer for Visual Generation and Understanding
   NeurIPS 2025 ·

   Chuofan Ma

   DBLP profile ↗ORCID search ↗
7. EVE: Efficient Vision-Language Pre-training with Masked Prediction and Modality-Aware MoE
   AAAI 2024 ·

   Junyi Chen

   DBLP profile ↗ORCID search ↗
8. General Object Foundation Model for Images and Videos at Scale
   CVPR 2024 ·

   Junfeng Wu

   DBLP profile ↗ORCID search ↗
9. Generative Region-Language Pretraining for Open-Ended Object Detection
   CVPR 2024 ·

   Chuang Lin

   DBLP profile ↗ORCID search ↗
10. Groma: Localized Visual Tokenization for Grounding Multimodal Large Language Models
    ECCV 2024 ·

    Chuofan Ma

    DBLP profile ↗ORCID search ↗
11. MotionMAE: Self-supervised Video Representation Learning with Motion-Aware Masked Autoencoders
    BMVC 2024 ·

    Haosen Yang

    DBLP profile ↗ORCID search ↗
12. OmniTokenizer: A Joint Image-Video Tokenizer for Visual Generation
    NeurIPS 2024 ·

    Junke Wang

    DBLP profile ↗ORCID search ↗
13. Recognize Any Regions
    NeurIPS 2024 ·

    Haosen Yang

    DBLP profile ↗ORCID search ↗
14. Visual Autoregressive Modeling: Scalable Image Generation via Next-Scale Prediction
    NeurIPS 2024 ·

    Keyu Tian

    DBLP profile ↗ORCID search ↗