| CARVIEW |
Biography
Guohao Li is an artificial intelligence researcher and an open-source contributor working on building intelligent agents that can perceive, learn, communicate, reason, and act. He is the core lead of the open source projects CAMEL-AI.org and DeepGCNs.org.
Guohao Li was a postdoctoral researcher at University of Oxford with Prof. Philip Torr. He obtained his PhD degree in Computer Science at King Abdullah University of Science and Technology (KAUST) advised by Prof. Bernard Ghanem. During his Ph.D. studies, he was fortunate to work at Intel ISL with Dr. Vladlen Koltun and Dr. Matthias Müller as a research intern. He visited ETHz CVL as a visiting researcher. He also worked at Kumo AI and PyG.org with Prof. Jure Leskovec and Dr. Matthias Fey as a PhD intern. His primary research interests include Autonomous Agents, Graph Machine Learning, Computer Vision, and Embodied AI. He has published related papers in top-tier conferences and journals such as ICCV, CVPR, ICML, NeurIPS, RSS, 3DV, and TPAMI.
We are actively looking for self-motivated research and engineering interns and open-source contributors at CAMEL-AI.org. Feel free to reach out via email guohao.li@eigent.ai if interested.
Interests
- Autonomous Agents
- Graph Machine Learning
- Computer Vision
- Embodied AI
Education
PhD in CS, 2018-2022
King Abdullah University of Science and Technology
MSE in EE, 2015-2018
University of Chinese Academy of Science
Joint MS in CS, 2015-2018
ShanghaiTech University
BE in EE, 2011-2015
Harbin Institute of Technology
Updates
- 2023/02/15: ~I will be joining Stanford University as a postdoc in April 2023.~ [Canceled]. I will explore something new.
- 2022/10/05: I defended my PhD dissertation on the Towards Structured Intelligence with Deep Graph Neural Networks! Sincerely thank everyone who has supported me on this journey!!!
- 2022/08/04: I received the CEMSE Dean’s List Award for academic year 2021-2022 at KAUST
- 2022/07/31: Paper LC-NAS accepted at CVPRW’22 and 3DV’22
- 2022/06/20 We organized a tutorial on Graph Machine Learning for Visual Computing at CVPR’22
- 2022/05/09 I joined KUMO.AI as the first intern. I worked with the PyG team as a core contributor
- 2022/03/01: Paper FLAG accepted at CVPR’22. Code is available on Github
- 2022/02/15: Tutorial Graph Machine Learning for Visual Computing accepted at CVPR’22. Stay tuned!
- 2022/03/01: Paper ASSANet accepted at NeurIPS’21 as Spotlight. Code is available on Github
- 2021/10/14: Our GNN1000 is on State of AI Report 2021 (page 67)
- 2021/05/08: Paper GNN1000 accepted at ICML’21. Code is available on Github
- 2021/04/07: I joined CVL at ETHz as a visiting researcher supervised by Prof. Fisher Yu
- 2021/04/05: Extension of Paper DeepGCNs accepted at TPAMI as a Regular Paper in the special issue on Graphs in Vision and Pattern Analysis
- 2021/03/03: Paper PU-GCN accepted at CVPR’21. Code is available on Github
- 2021/01/05 I was selected as one of the winning students of Yearly Student Awards in CS program, CEMSE, KAUST
- 2020/10/26 AI-sports team won the first place in NEOM AI challenge (Entertainment track)
- 2020/08/01 I joined Intel ISL as a PhD research intern hosted by Dr. Vladlen Koltun & Dr. Matthias Müller
- 2020/06/13: Preprint of DeeperGCN is on arXiv. The code of experiments on OGB can be found on our Github Repo
- 2020/02/23: Paper SGAS accepted at CVPR’20. Code is available on Github Repo
- 2019/11/26: I was invited to give a talk about DeepGCNs and its follow-up works at NVIDIA GTC China 2019 (Dec. 16-19)
- 2019/10/12: Additional experiments of DeepGCNs on PPI and PartNet are available on our Github Pytorch Repo. The preprint of our journal extension is on arxiv now
- 2019/08/01: Paper DeepGCNs accepted as Oral at ICCV’19. Code is available on Github
- 2019/04/30: Paper OIL accepted at RSS’19
Recent & Upcoming Talks
DeepGCNs for Representation Learning on Graphs
Stanford, Google AI, Oxford, Emory, Baidu PGL, Cerebras Systems ML, KAUST Conference AI (Best Spotlight Award), NeurIPS Meetup 2019, NVIDIA GTC China 2019, M2Lschool2021, Jiangmen Live Streaming
Selected Publications
CAMEL: Communicative Agents for ''Mind'' Exploration of Large Language Model Society
Robust Optimization as Data Augmentation for Large-scale Graphs
ASSANet: An Anisotropic Separable Set Abstraction for Efficient Point Cloud Representation Learning
University of Oxford
Kumo AI
ETH Zurich
Intel Intelligent Systems Lab