Machine learning models have achieved stunning successes in the IID setting. Yet, beyond this setting, existing models still suffer from two grand challenges: brittle under distributional shift and inefficient for knowledge transfer. Our recent research tackles these challenges with three different approaches, namely self-supervised learning, causal representation learning, and test-time adaptation. More specifically, we propose to incorporate prior knowledge of negative examples into representation learning , promote causal invariance and structure by making use of data from multiple domains , and exploit extra information besides model parameters for effective test-time adaptation [3,4]. These techniques have enabled deep neural networks to more robustly generalize and efficiently adapt to new environments for perception, prediction, and planning problems.
 Social NCE: Contrastive Learning of Socially-aware Motion Representations, ICCV, 2021.
 Towards Robust and Adaptive Motion Forecasting: A Causal Representation Perspective, CVPR, 2022.
 Collaborative Sampling in Generative Adversarial Networks, AAAI, 2020.
 TTT++: When Does Self-Supervised Test-Time Training Fail or Thrive?, NeurIPS, 2021.