韡 Biography

I have been at SenseTime since August 2019, where I currently serve as a senior algorithm researcher and lead a team focused on the advancement and application of universal multimodal embedding and retrieval to real-world applications. Previously, I specialized in representation learning, implementing it in practical applications across various industries.

Before that, I earned my Master's degree in Computer Science from the Computer Games and Intelligence (CGI) Lab at National Chiao Tung University in June 2019, where my research focused on combining deep reinforcement learning with Computer Game AI (e.g., 2048 Game AI, Chinese Chess AI, AlphaGo/AlphaZero), under the supervision of Professor I-Chen Wu.

I am originally from Fujian, China, a land of rolling hills and mountains, known for its pristine natural beauty and fresh, clean air.
My name, 韡 (wěi), symbolizes brightness and beauty, reflecting my approach to both life and work. I aim to leverage technology to enhance human happiness and well-being. I'm also active on GitHub and Zhihu, feel free to connect with me!

News

[2024/05/31] My team has 1 paper (EMAE) accepted to TPAMI'24.
[2023/12/31] My team has 4 papers (BLV, MIAD, SpecularDefect9, SAIM) published in CVPR/ICCV/OLEN/AAAI in 2023.
[2022/12/31] My team has 4 papers (U2PL, UniVIP, Obj2Seq, FST) published in CVPR/NeurIPS in 2022.
[2021/09/28] My team has 1 paper (MST) accepted to NeurIPS'21.
[2020/05/10] 😸 A Chi's (Ice Cream) broke into my life.
[2019/12/04] 👻 I received the SenseTime 2019 Outstanding Award (杰出个人奖).
[2019/08/08] I formally joined SenseTime as a Researcher.
[2019/06/30] 🌈🌈 I successfully defended my thesis and graduated. I am profoundly thankful to my advisor and classmates for their invaluable guidance and support; my time here was both intellectually enriching and memorable. Our paper, MPV-MCTS, was accepted to IJCAI'19. This research introduced a scalable AlphaGo Zero/AlphaZero (AGZ/AZ) framework and a novel training method leveraging multiple neural networks, which contributed to WahahaNoGo's triumphs at the TAAI 2018 and ICGA 2019 NoGo championships.
[2019/03/28] I started an internship at SenseTime, where I primarily focused on large-scale training and face anti-spoofing.
[2018/11/05] I worked on Project-Theta, focusing on defect inspection and automated optical inspection, and contributed to open-source projects. One paper HTD was accepted to WACV'19.
[2017/11/10] 👻 I received the NCTU Academic Excellence Award (書卷獎, ranked 5/267, Top 1.87%).
[2017/09/01] I served as a TA (teaching assistant) for MediaTek's Deep Learning Training Program.
[2016/09/01] I joined the Computer Games and Intelligence (CGI) Lab at National Chiao Tung University to pursue my master's degree, under the supervision of Professor I-Chen Wu (the inventor of Connect6).

Projects

Industrial Applications @SenseTime
  • 智慧城市多模态预警/多模态检索 [News]
  • 智能矿山AI感知系统 [News]
  • 星空高铁4C智能分析系统 [News]
  • 人脸活体检测/大规模分类训练 [Product]
Efficient and Flexible Framework for AlphaZero-Like Applications @CGI Lab, NCTU
  • Developed a lightweight, scalable AGZ/AZ framework(called CFZ) on Caffe2 with C++ inference and Python training, extendable to any board game and adaptable to algorithms beyond AGZ/AZ. CZF Guide (2MB)
  • Co-proposed a training algorithm, MPV-MCTS, based on CFZ by combining multiple NN networks. Slides (6MB)
  • Co-developed WahahaNoGo, the successor to HaHaNoGo, with a 99% win rate against.
  • WahahaNoGo won the TAAI 2018 and ICGA 2019 NoGo Championships.
Project-Theta @NCTU, Academia Sinica
  • distribuuuu:
  • CIFAR-ZOO:
  • cifar-10-cnn: