Yinxiao Li
Yinxiao Li is a staff researcher with Google DeepMind, focusing on Google's imagen foundation models, and GenAI for Ads. His team won Google 2023 Tech Impact Award (1 out of ~10 projects company-wide), the best paper finalist in CVPR 2022, and the 1st place of the ActivityNet challenge 2020. He has been the area chairs of AAAI2022, NIPS2024, and ICLR2025. He received the PhD degree from Columbia University.
Research Areas
Authored Publications
Sort By
DVMark: A Deep Multiscale Network for Video Watermarking
Huiwen Chang
Ce Liu
IEEE Transactions on Image Processing (2023)
SVDiff: Compact Parameter Space for Diffusion Fine-Tuning
Ligong Han
Han Zhang
Dimitris Metaxas
IEEE/CVF International Conference on Computer Vision (ICCV) (2023)
MaxViT: Multi-Axis Vision Transformer
Zhengzhong Tu
Han Zhang
Alan Bovik
European Conference on Computer Vision (ECCV) (2022)
MAXIM: Multi-Axis MLP for Image Processing
Zhengzhong Tu
Han Zhang
Alan Bovik
IEEE/CVF Conference on Computer Vision and Pattern Recognition (2022)
COMISR: Compression-Informed Video Super-Resolution
Ce Liu
IEEE/CVF International Conference on Computer Vision (ICCV) (2021)
PERF-Net: Pose Empowered RGB-Flow Net
Zhichao Lu
Xuehan Xiong
Jonathan Huang
IEEE Winter Conference on Applications of Computer Vision (2021)
Looking Fast and Slow: Memory-Guided Mobile Video Object Detection
Mason Liu
Menglong Zhu
Marie White
Dmitry Kalenichenko
https://arxiv.org/abs/1903.10172 (2019)
Model-driven feedforward prediction for manipulation of deformable objects
Yan Wang
Yonghao Yue
Danfei Xu
Michael Case
Shih-Fu Chang
Eitan Grinspun
Peter K. Allen
IEEE Transactions on Automation Science and Engineering (2018)
Articulated Pose Estimation Using Hierarchical Exemplar-Based Models
Jiongxin Liu
Peter Allen
Peter Belhumeur
AAAI Conference on Artificial Intelligence (2016)
