搜索网站、位置和人员
“定乎内外之分。”
个人简介
王欢，安徽六安人，2016、2019年获浙江大学信息与通信工程专业学士、硕士学位，2024年4月获美国东北大学计算机工程专业博士学位，2024年6月全职加入西湖大学任助理教授，创立 “高效智能计算实验室（Efficient Neural Computing and Design Lab, ENCODE Lab）” ，担任PI、博士生导师。王欢博士专注于Efficient AI方向的理论、算法、应用研究，担任领域内众多顶会顶刊审稿人（如CVPR/ICCV/ECCV, ICML/NeurIPS/ICLR, AAAI/IJCAI, SIGGRAPH Asia, TPAMI/IJCV/TIP/TNNLS），曾在Google / Snap / MERL / Alibaba等著名业界研究机构实习。获CVPR’23 Outstanding Reviewer Award (3.3%), 2023 Snap Research Fellowship HM (<10%), 2022 & 2023 NeurIPS Scholar Award, ICLR’23 Travel Award, 2022 & 2023 NEU PhD Network Travel Award。
学术成果
王欢博士专注于Efficient AI相关的理论、算法、应用研究，致力于让前沿AI算法得以落地，以更低成本产出更高、更稳定的性能，惠及大众，推动社会进步。
其研究重点包括：
· 经典Effcient AI方法和理论：剪枝、蒸馏、量化、高效能网络结构设计、低秩分解等。
· 应用领域：
1. 生成式AI：文生图、扩散模型，大语言模型、多模态模型等；
2. 三维视觉：神经辐射场、神经光场、3DGS、神经渲染，数字人，talking head等；
3. 底层视觉：图像超分辨率、图像复原，风格迁移等。
研究成果发表论文30余篇（其中一作/共同一作论文10余篇），多数发表于领域内顶会顶刊（如CVPR/ICCV/ECCV, ICLR/NeurIPS, TPAMI/TIP）。部分成果已在业界应用，如：
· R2L（ECCV’22）、MobileR2L（CVPR’23）系列基于神经光场（NeLF）对神经辐射场（NeRF）进行蒸馏，实现了端上高保真、实时渲染（~60 FPS, iPhone13，768x1008分辨率）；成果亦发表美国专利。
· SnapFusion（NeurIPS’23）是世界上首个端上运行时间低于2s且维持和SD-v1.5性能相当的文生图模型；成果亦发表美国专利。
代表论文
（*代表同等贡献，†代表通讯作者）
1. Yitian Zhang, Yue Bai, Huan Wang, Yizhou Wang, Yun Fu. Don’t Judge by the Look: A Motion Coherent Augmentation for Video Recognition. In ICLR, 2024.
2. Yanyu Li*, Huan Wang*, Qing Jin*, Ju Hu, Pavlo Chemerys, Yun Fu, Yanzhi Wang, Sergey Tulyakov, Jian Ren*. SnapFusion: Text-to-Image Diffusion Model on Mobile Devices within Two Seconds. In NeurIPS, 2023.
3. Jiamian Wang, Huan Wang, Yulun Zhang, Yun Fu, Zhiqiang Tao. Iterative Soft Shrinkage Learning for Efficient Image Super-Resolution. In ICCV, 2023.
4. Huan Wang*, Yulun Zhang*, Can Qin, Yun Fu. Global Aligned Structured Sparsity Learning for Efficient Image Super-Resolution. TPAMI, 2023.
5. Junli Cao, Huan Wang, Pavlo Chemerys, Vladislav Shakhrai, Ju Hu, Yun Fu, Denys Makoviichuk, Sergey Tulyakov, Jian Ren. Real-Time Neural Light Field on Mobile Devices. In CVPR, 2023.
6. Yitian Zhang, Yue Bai, Chang Liu, Huan Wang, Sheng Li, Yun Fu. Frame Flexible Network. In CVPR, 2023.
7. Huan Wang, Yun Fu. Trainability Preserving Neural Pruning. In ICLR, 2023.
8. Xu Ma*, Yuqian Zhou*, Huan Wang, Can Qin, Bin Sun, Chang Liu, Yun Fu. Image as Set of Points. In ICLR (Oral, top-5%), 2023.
9. Huan Wang, Suhas Lohit, Michael Jones, Yun Fu. What Makes a “Good” Data Augmentation in Knowledge Distillation – A Statistical Perspective. In NeurIPS, 2022.
10. Yue Bai, Huan Wang, Xu Ma, Yitian Zhang, Zhiqiang Tao, Yun Fu. Parameter Efficient Masking Networks. In NeurIPS, 2022.
11. Yitian Zhang, Yue Bai, Huan Wang, Yi Xu, Yun Fu. Look More but Care Less in Video Recognition. In NeurIPS, 2022.
12. Huan Wang, Jian Ren, Zeng Huang, Kyle Olszewski, Menglei Chai, Yun Fu, Sergey Tulyakov. R2L: Distilling Neural Radiance Field to Neural Light Field for Efficient Novel View Synthesis. In ECCV, 2022.
13. Huan Wang, Can Qin, Yue Bai, Yulun Zhang, Yun Fu. Recent Advances on Neural Network Pruning at Initialization. In IJCAI, 2022.
14. Huan Wang*, Yulun Zhang*, Can Qin, Yun Fu. Learning Efficient Image Super-Resolution Networks via Structure-Regularized Pruning. In ICLR, 2022.
15. Yue Bai, Huan Wang, Kunpeng Li, Zhiqiang Tao, Yun Fu. Dual Lottery Ticket Hypothesis. In ICLR, 2022.
16. Huan Wang*, Yulun Zhang*, Can Qin, Yun Fu. Aligned Structured Sparsity Learning for Efficient Image Super-Resolution. In NeurIPS (Spotlight, <3%), 2021.
17. Huan Wang, Can Qin, Yulun Zhang, Yun Fu. Neural Pruning via Growing Regularization. In ICLR, 2021.
18. Huan Wang, Yijun Li, Yuehai Wang, Haoji Hu, Ming-Hsuan Yang. Collaborative Distillation for Ultra-Resolution Universal Style Transfer. In CVPR, 2020.
19. Xiaotang Jiang, Huan Wang, Yiliu Chen, Ziqi Wu, et al. MNN: A Universal and Efficient Inference Engine. In Machine Learning and Systems (MLSys), 2020 (accept rate: 19.2%, Oral).
20. Huan Wang, Xinyi Hu, Qiming Zhang, Yuehai Wang, Lu Yu, Haoji Hu. Structured Pruning for Efficient Convolutional Neural Networks via Incremental Regularization. IEEE Journal of Selected Topics in Signal Processing (JSTSP), 2019.
21. Huan Wang, Qiming Zhang, Yuehai Wang, Lu Yu, Haoji Hu. Structured Pruning for Efficient ConvNets via Incremental Regularization. In NeurIPS Workshop, 2018; In IJCNN, 2019 (Oral).
22. Huan Wang*, Qiming Zhang*, Yuehai Wang, Haoji Hu. Structured Probabilistic Pruning for Convolutional Neural Network Acceleration. In BMVC, 2018 (Oral, 4.3%).
联系方式
王欢实验室2025 Fall计划招聘3～4名博士生，实验室长期招聘博后、助研、访问学生，具体请参见知乎招生贴（https://zhuanlan.zhihu.com/p/691403133）和英文版招生贴（https://huanwang.tech/files/to_prospective_students_huan_westlake.pdf）。
