Hi, I am a student at Tsinghua University. Currently, my research centers on multi-modal learning and generative models, with the ultimate goal of building a unified perception–generation engine that can understand, predict, and interact with the physical world. I am especially interested in how these models can be distilled into efficient engines that enable systems to perform robust visual reasoning and generative modeling in complex, unstructured environments. I now focus more on rethinking problems and offering simple, effective solutions. If you have any use cases you would like to share, please feel free to contact me!
Email: xuzn3(at)outlook.com
Links:
[Publication]
[Github]
- One paper is accepted to NeurIPS 2025.
- Two papers are accepted to ICCV 2025.
- I received an Outstanding Reviewer Award at CVPR 2025.
- Three papers are accepted to CVPR 2025.
- One paper is accepted to EMNLP 2024.
- We won the 3rd prize in CVPR 2024 OVD challenge.
- Two papers are accepted to ICML 2024.
- One paper is accepted to NeurIPS 2024.
- One paper is accepted to ICCV 2023.
- Complex Visual Reasoning: Referring image segmentation, visual grounding, semantic segmentation, and general object detection.
- Generative Models: Image/Video generation and 3D Motion/Mesh synthesis.
- Efficient Transfer Learning
- Self-supervised Learning
Program Committee Member / Reviewer for:
- IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI)
- IEEE Transactions on Image Processing (TIP)
- IEEE International Conference on Computer Vision and Pattern Recognition (CVPR)
- IEEE International Conference on Computer Vision (ICCV)
- Neural Information Processing Systems (NeurIPS)
- International Conference on Machine Learning (ICML)
- International Conference on Learning Representations (ICLR)
- Association for Computational Linguistics (ACL)