Fundamental AI

Representation, reinforcement, and multitask learning, and human-in-the-loop

OmniXAI

A one-stop comprehensive library that makes explainable AI easy for data scientists, ML researchers, and practitioners who need explanations for various types of data and models at different stages of ML process.

view project

Latest Publications

publication
CoMatch: Semi-supervised Learning with Contrastive Graph Regularization
read on arxiv
publication
Prototypical Contrastive Learning of Unsupervised Representations
read on arxiv
publication
MoPro: Webly Supervised Learning with Momentum Prototypes
read on arxiv