Yu Liu's academic page

Yu Liu's academic page 

Executive Director & General Manager, SenseTime
PI, Shanghai AI Lab
Industrial doctoral supervisor, SJTU
liuyuisanai@gmail.com

Google Scholar

News

  • Job positions and PhD program are open for talents interested in AIGC, Large model and RL.

  • [2024] My team have 19 papers published on NeurIPS/CVPR/TMLR/ICML/ECCV in 2024

  • [2024] Our AIGC product MiaoHua has garnered users over 3,000,000, with a DAU exceeding 530,000, all within a remarkable 9-day post-launch.

  • [2024] We are granted the 吴文俊奖 - 科技进步一等奖

  • [2024] Our OpenDILab achieves 21,000+ stars on GitHub!

  • [2023] My team have 20 papers published on TPAMI/ICCV/ICLR/NeurIPS/IROS/AAAI in 2023

  • [2023] My team won the championship of CARLA Autonomous Driving Challenge

  • [2022] My team have 9 papers published on ECCV/CoRL/NeurIPS/AAAI in 2022

  • [2022] We release DI-Star, an implementation of AlphaStar in pyTorch, beating pro players with 6000+ MMR.

  • [2021] My team won the best paper of ICCV21 MFR workshop

  • [2021] My team won 3 championships of ICCV21 The Masked Face Recognition Challenge

  • [2021] We release OpenDILab, an open source decision intelligence platform

  • [2020] 5 papers with 1 oral got published on CVPR/ECCV 2020

  • [2020] My team won 2 championships of ActivityNet on the Spatio-temporal Action Localization (AVA) track and the Trimmed Activity Recognition (Kinetics) track

  • [2020] My team won the championship of NIST FRVT 1:N, a 12-million-level commercial facial recognition benchmark held by US government.

  • [2019] 7 papers with 4 oral presentations published on ICCV/CVPR/AAAI in 2019

  • [2019] I won 4 champions in 4 ICCV AI challenges:MMIT (solutions), OpenImage Instance Segmentation Challenge (solutions), OpenImage Object Detection Challenge (solutions), LFR 2019 (model and report)

  • [2019] I was granted the Google PhD Fellowship 2019.

  • [2018] 4 papers published by CVPR/ECCV/IJCV/AAAI in 2018.

  • [2017] 6 papers published on CVPR/ICCV/NIPS/AAAI/T-PAMI in 2017.

  • [2016] We win the 1st place in ECCV-MOT16 Challenge! code

  • [2016] We win the 1st place in ImageNet Challenge 2016! code

About me

I am the Executive Director of Research and GM at SenseTime Group, spearheading large-scale AIGC and multi-modal interactive models. I lead a team of approximately 100 top-tier researchers and developers, utilizing over 4,000 GPUs to drive innovative technology and products. I hold a PhD from MMLab, CUHK, supervised by Prof. Xiaogang Wang, and have won multiple international AI competitions, along with a Google PhD Fellowship.

Working Experience

Publications

See full list at Google Scholar.
*equal contribution +corresponding author

Large model for Multi-modal generation, AIGC

Large-scale Reinforcement Learning, Embodied AI

Large-scale Optimiation, Computer Vision

Honors and Awards

  • Won the 1st prize for scientific and technological progress, CAAI, 2024

  • Won the 1th place in CARLA Autonomous Driving Challenge 2022

  • Won the 1th place in ActivityNet 2020, AVA track

  • Won the 1th place in ActivityNet 2020, Kinetics track

  • Won the 1th place in NIST FRVT held by US government in 2020, 2021 and 2022

  • Won the 1th place in ICCV19 Multi-Moments in Time (MIT) Challenge

  • Won the 1th place in Google OpenImage Object Detection Challenge 2019

  • Won the 1th place in Google OpenImage Instance Segmentation Challenge 2019

  • Google PhD Fellowship in 2019 (1/China, 50/world)

  • Won the 1th place in ICCV19 Lightweight Face Recognition Challenge

  • Won the 1th place in NIST-FRVT threshold based 1:N track 2018

  • Won the 1th place in Multiple Objects Tracking Challenge (MOT16) in 2016

  • Won the 1th place in detection track of ImageNet (ILSVRC) in 2016

  • Won the best undergraduate dissertation in 2016 (1/230)

  • IEEE-Microsoft Undergraduate Fellowship in 2016 (40/world)

  • The Outstanding Winner of Challenge Cup in 2015 (top 1/China)

Projects & Datasets

GitHub

  • OpenDILab, a generalized Decision Intelligence engine.

  • X-Temporal, Easily implement SOTA video understanding methods with PyTorch on multiple machines and GPUs

  • CaffeMex v2.3, a multi-GPU & memory-reduced MAT-Caffe on LINUX and WINDOWS

  • Labeled Pedestrains in the Wild, a large scale pedestrain re-identification benchmark