Entity Abstraction in Visual Model-Based Reinforcement Learning

The Object-centric perception, prediction, and planning (OP3) framework demonstrates strong generalization to novel configurations in block stacking tasks by symmetrically processing entity representations extracted from raw visual observations.

Learning Physical Graph Representations from Visual Scenes

Introduces a novel hierarchical representation of visual scenes, Physical Scene Graphs (PSGs), as well as a network for learning them from RGB movies, PSGNet, which outperforms other unsupervised methods in scene segmentation.

Stanford EE PhD Quals

Note: This article is now outdated as the Stanford EE Quals moved to an entirely committee-based quals format in 2018. However, I’ll leave this here for those that are curious about the old format I just finished the Stanford EE quals last week and passed! After a month of frenzied studying and stressing, it’s finally over. During this time, I’ve read countless articles about quals: failing quals, passing quals, quals advice, quals statistics - venturing deep into the pages of Google results. As such, I’m writing this article to provide my experience and advice, with the hope that it will help future students preparing for this exam. While my top two areas were linear systems and probabilistic systems, most of this advice should be relevant for other areas too.