I am now an associate professor working in Shenzhen Institute of Advanced Technology (SIAT), Chinese Academy of Science (CAS). My research interests mainly concentrates around fundamental AI, including robust learning and graph representation with their practical applications in the fields of fundamental science.
I am now working closely with Prof. Pheng Ann Heng from CUHK, and we are now looking for PhD/Mphil/RA/Postdoc interested in developing advanced artificial intelligence algorithms, as well as their practical applications on AI-aided drug discovery. Feel free to drop me an email for more information or apply through the official website (CUHK PhD Summer Workshop / HKPFS ).
[11/2021] One paper that proposes a machine learing paradigm for the rational design and fast screening of SAAs for various electrocatalytic reactions has been accepted by Green Energy & Environment(JCR 1).
[09/2021] One paper about investigating loss landscape to improve the continual learning performance has been accepted by Neurips 2021 (CCF A).
[07/2021] One paper about adopting adversarial guidance for monocular depth estimation has been accepted by the ACM Multimedia 2021 (ACMMM) (CCF A).
[06/2021] One paper about developing a rotation invariant framework for point cloud analysis has been accepted by the IEEE Transactions on Visualization and Computer Graphics (TVCG) (JCR 1).
[04/2021] One paper about adopting Transformer for single-step retrosynthesis predictions has been accepted to Chemical Engineering Journal (JCR 1).
[03/2021] One paper about adopting GCN for QSAR has been accepted to Briefings in Bioinformatics(JCR 1).
[02/2021] One survey paper about adopting GCN to discover new drugs has been accepted to Journal of Cheminformatics (JCR 1).
[01/2021] One paper about robust learning aganist noisy label has been accepted to ICLR2021 (Top Conference @ AI) as spotlight .
[12/2020] Three papers about robust learning aganist noisy label and reinforcement learning have been accepted to AAAI2021 (CCF A).
[06/2020] One paper about multi-agent reinforcement learning has been accepted to ICML2020 (CCF A).