Full-Atom Protein Pocket Design via Iterative Refinement

1 code implementation • NeurIPS 2023 • Zaixi Zhang, Zepu Lu, Zhongkai Hao, Marinka Zitnik, Qi Liu

In the initial stage, the residue types and backbone coordinates are refined using a hierarchical context encoder, complemented by two structure refinement modules that capture both inter-residue and pocket-ligand interactions.

Backdoor Defense via Deconfounded Representation Learning

1 code implementation • CVPR 2023 • Zaixi Zhang, Qi Liu, Zhicai Wang, Zepu Lu, Qingyong Hu

The other clean model dedicates to capturing the desired causal effects by minimizing the mutual information with the confounding representations from the backdoored model and employing a sample-wise re-weighting scheme.

Backdoor Attack backdoor defense +1