This page collects some of the talk recordings available online over the years, from my PhD thesis defense to recent invited talks at workshops and seminars. They give an overview of our research at different stages. Learning Generalizable and Interpretable Embodied AI from Humans UT Austin's Forum for AI, Sep 8, 2023 Large-scale Scene Generation and Simulation from Bird-Eye's View BIRS Workshop, Aug 15, 2023 From Network Dissection to Policy Dissection - Discovering Intepretable Concepts in Deep Representations IPAM Workshop, Jan 9, 2023 Safe and Generalizable Embodied AI for Driving Decision-Making NeurIPS'22 Workshop, Dec 3, 2022 Interpretable Human-AI Interaction for Content Creation and Machine Autonomy AI for Good, Oct 3, 2022 Toward Generalizable Embodied AI for Machine Autonomy Stanford Graphics, Sep 5, 2022 Human-AI Interaction for Computer Vision CVPR22 Tutorial, Jun 19, 2022 The Rejected behind the Accepted ICCV'21 Share Stories, Sep 26, 2021 Interpreting Deep Generative Models for Interactive AI Content Creation CVPR21 Tutorial, Jun 19, 2021 Inverting Latent Space of GANs for Real Image Editings MIT Vision Seminar, Oct 27, 2020 Exploring and Exploiting Interpretable Semantics in GANs CVPR20 Tutorial, Jun 20, 2020 强化学习纲要 (In Chinese) Intro to RL, Mar 16, 2020 On the Importance of Individual Units in CNNs CVPR18 Tutorial, Jun 30, 2018 Interpretable Representation Learning for Visual Intelligence MIT PhD Defense, May 3, 2018 Interpreting Deep Visual Representations CVPR17 Tutorial, Jul 22, 2017 Network Dissection (Oral paper) CVPR17, Jul 22, 2017
