Learning Representations for Few-Shot Behavior Cloning

Title: Learning Representations for Few-Shot Behavior Cloning

Abstract: Representation learning, whether supervised or unsupervised, has been widely studied and applied in visual perception, where latent features encode high-level semantic information, capturing correspondences and correlations between different visual contents. Can similar paradigms be designed to encode actions and interactions? – this is an active question asked by the ongoing research in robot learning.
In this talk, I will present my work on learning representations for encoding, understanding, and generalizing robotic actions and interactions, with a particular focus on few-shot generalization under limited data. I will explore different approaches to robotic representation learning, discussing their connections to and distinctions from visual representation learning. Through this lens, I will also discuss the challenges and opportunities in developing efficient and generalizable robotic learning systems.

Bio: Congyue is a fifth-year Ph.D. student in computer science at Stanford University advised by Leonidas Guibas. Congyue's research interests include 3D computer vision and geometric deep learning. Congyue is particularly interested in designing feature representations for visual understanding with the awareness of symmetries and geometric relations.

Congyue also had the pleasure of collaborating with Kaiming He (MIT), Kostas Daniilidis (UPenn), and Jeannette Bohg (Stanford) and obtained a B.S. in mathematics from Tsinghua University in 2020 with a GPA ranking 1/114.