Li Ang
Co-Founder and CEO @ Simular
Bio
I am a startup founder in artificial intelligence, with a variety of research and product experiences on autonomous driving, videos, cameras, maps, advertisements, etc. My research aims at building lifelong autonomous agents. Previously, I worked at Google DeepMind, Baidu Apollo, Facebook AI Research, CMU Robotics, Apple, Google Streetview, and Comcast Labs DC. I received my Ph.D. in computer science from the University of Maryland College Park. My PhD thesis is spatial perception from visual and linguisitc information.
Publications
- Building an open-vocabulary video CLIP model with better architectures, optimization and data. PAMI 2024. bib Zuxuan Wu, Zejia Weng, Wujian Peng, Xitong Yang, Ang Li, Larry S. Davis, Yu-Gang Jiang
- Transforming CLIP to an Open-vocabulary Video Model via Interpolated Weight Optimization. ICML 2023. bib Zejia Weng, Xitong Yang, Ang Li, Zuxuan Wu, Yu-Gang Jiang
- Information-theoretic Online Memory Selection for Continual Learning. ICLR 2022. bibtex Shengyang Sun, Daniele Calandriello, Huiyi Hu, Ang Li, Michalis Titsias.
- One Pass ImageNet. NeurIPS 2021 Workshop on ImageNet. bibtex Huiyi Hu, Ang Li, Daniele Calandriello, Dilan Gorur.
- Task-agnostic Continual Learning with Hybrid Probabilistic Models. ICML 2021 workshop. bibtex Polina Kirichenko, Mehrdad Farajtabar, Dushyant Rao, Balaji Lakshminarayanan, Nir Levine, Ang Li, Huiyi Hu, Andrew Gordon Wilson, Razvan Pascanu.
- The Effectiveness of Memory Replay in Large Scale Continual Learning. CVPR 2021 Workshop on Continual Learning. bibtex Yogesh Balaji, Mehrdad Farajtabar, Dong Yin, Alex Mott, Ang Li.
- SOLA: Continual Learning with Second-Order Loss Approximation. ICML 2020 Workshop on Continual Learning. bibtex Dong Yin, Mehrdad Farajtabar, Ang Li.
- Orthogonal Gradient Descent for Continual Learning. AISTATS 2020. bibtex Mehrdad Farajtabar, Navid Azizan, Alex Mott, Ang Li.
Press Coverage
- Baidu Apollo Day: Expanded robotaxi operations and new autonomous driving software and hardware. Autonomous Driving International.
- An algorithm that evolved Starcraft bots is also training self-driving cars. MIT Technology Review
- Traffic prediction with advanced Graph Neural Networks. DeepMind Blog
Academic Servicet
- Journal Reviewer:
- IEEE Transaction on Pattern Analysis and Machine Intelligence (TPAMI)
- IEEE Transactions on Neural Networks and Learning Systems (TNNLS)
- IEEE Transaction on Image Processing (TIP)
- The Visual Computer Journal (TVCJ)
- SPIE Journal of Electronic Imaging (JEI)
- IEEE Transaction on Cybernetics
- Robotics and Autonomous Systems
- Machine Learning
- Session Chair:
- International Joint Conference on Artificial Intelligence (IJCAI) 2021
- Area Chair:
- NeurIPS Workshop on Meta Learning 2021
- NeurIPS Workshop on Meta Learning 2022
- Senior Program Committee:
- AAAI Conference on Artificial Intelligence (AAAI) 2021
- International Joint Conference on Artificial Intelligence (IJCAI) 2020, 2021
- International Conference on Autonomous Agents and Multi-Agent Systems (AAMAS) 2020
- Program Committee:
- International Conference on Learning Representations (ICLR)
- Annual Conference on Neural Information Processing Systems (NeurIPS)
- IEEE Conference on Computer Vision and Pattern Recognition (CVPR)
- International Conference on Machine Learning (ICML)
- IEEE International Conference on Computer Vision (ICCV)
- European Conference on Computer Vision (ECCV)
- International Joint Conference on Artificial Intelligence (IJCAI)
- International Conference on Artificial Intelligence and Statistics (AISTATS)
- ACM International Conference on Multimedia (MM)