 |
|
About me
I am an associate professor in EECS at MIT studying computer vision, machine learning, and AI.
Previously, I spent a year as a visiting research scientist at OpenAI, and before that I was a postdoctoral scholar with Alyosha Efros in the EECS department at UC Berkeley. I completed my Ph.D. in Brain & Cognitive Sciences at MIT, under the supervision of Ted Adelson, where I also frequently worked with Aude Oliva. I received my undergraduate degree in Computer Science from Yale, where I got my start on research working with Brian Scholl.
⭐
It's PhD applications season! Please see info about my group's openings here.
Come see our stuff at NeurIPS 2022!
→ Competition: NeurIPS 2022 Neural MMO Challenge
→ Paper: Semantic uncertainty intervals for disentangled latent spaces
→ Paper: Procedural Image Programs for Representation Learning
→ Paper: Offline Multi-Agent Reinforcement Learning with Knowledge Distillation
→ Workshop Paper (NeurReps workshop): Improved Representation of Asymmetrical Distances with Interval Quasimetric Embeddings
→ Workshop Paper (TSRML workshop): Real world relevance of generative counterfactual explanations
→ Workshop Talk (SSL workshop): When faking your data actually helps - Self-supervised learning from GANs, NeRFs, and Noise
→ Workshop Talk (SVRHM workshop): Generating Imagery Optimized for Human Consumption
News
⭐It's PhD applications season! Please see info about my group's openings here.
Come see our stuff at NeurIPS 2022!
→ Competition: NeurIPS 2022 Neural MMO Challenge
→ Paper: Semantic uncertainty intervals for disentangled latent spaces
→ Paper: Procedural Image Programs for Representation Learning
→ Paper: Offline Multi-Agent Reinforcement Learning with Knowledge Distillation
→ Workshop Paper (NeurReps workshop): Improved Representation of Asymmetrical Distances with Interval Quasimetric Embeddings
→ Workshop Paper (TSRML workshop): Real world relevance of generative counterfactual explanations
→ Workshop Talk (SSL workshop): When faking your data actually helps - Self-supervised learning from GANs, NeRFs, and Noise
→ Workshop Talk (SVRHM workshop): Generating Imagery Optimized for Human Consumption
Research Group
Our group studies how to make artificial intelligence more like natural intelligence. We are especially interested in intelligence that is embodied, emergent, and general-purpose, all of which are properties that we see in humans and animals.Topics we currently focus on include representation learning, generative modeling, and multiagent systems. We also enjoy eclectic applications on top of these systems, often in vision and graphics, and also study the misuse of these systems, especially toward spreading misinformation.
The lab is part of the broader Embodied Intelligence and Visual Computing research communities at MIT.
|
PhD Students Yen-Chen Lin Caroline Chan Lucy Chai Tongzhou Wang Joseph Suarez Minyoung (Jacob) Huh Hyojin Bahng Akarsh Kumar Shobhita Sundaram |
MEng Students Kevin Frans Stephanie Fu Sage Simhon |
|
Postdocs Swami Sankaranarayanan Undergraduates Jeff Li |
|
|
Former Members and Visitors Yonglong Tian (PhD 2022), Dillon Dupont (UROP 2021), Kate Xu (UROP 2021), Maxwell Jiang (UROP 2021), Toru Lin (MEng 2021), Kenny Derek (MEng 2021), Stephanie Fu (UROP 2021), Yilun Du (UROP 2019), Zhongxia Yan (Rotation 2019) |
|
| Interested in joining the group? Please see info about applying here. | |
Recent Courses
6.s898: Deep Learning (Fall 2022)6.819/6.869: Advances in Computer Vision (Spring 2022)
6.s898: Deep Learning (Fall 2021)
6.036: Introduction to Machine Learning (Fall 2020)
6.882: Embodied Intelligence (Spring 2020)
Recent papers
| Powderworld: A Platform for Understanding Generalization via Rich Task Distributions Kevin Frans, Phillip Isola arXiv 2022. [Paper][Blog + Demo][Code] | |
| MIRA: Mental Imagery for Robotic Affordances Lin Yen-Chen, Pete Florence, Andy Zeng, Jonathan T. Barron, Yilun Du, Wei-Chiu Ma, Anthony Simeonov, Alberto Rodriguez Garcia, Phillip Isola CoRL 2022. [Paper][Website][Video] | |
| Semantic uncertainty intervals for disentangled latent spaces Swami Sankaranarayanan, Anastasios Angelopoulos, Stephen Bates, Yaniv Romoano, Phillip Isola NeurIPS 2022. [Paper][Website][Code][Video] | |
| Procedural Image Programs for Representation Learning Manel Baradad, Chun-Fu (Richard) Chen, Jonas Wulff, Tongzhou Wang, Rogerio Feris, Antonio Torralba, Phillip Isola NeurIPS 2022. [Paper][Website][Code & Datasets] | |
| Offline Multi-Agent Reinforcement Learning with Knowledge Distillation Wei-Cheng Tseng, Tsun-Hsuan Wang, Lin Yen-Chen, Phillip Isola NeurIPS 2022. [Paper] | |
| Totems: Physical Objects for Verifying Visual Integrity Jingwei Ma, Lucy Chai, Minyoung Huh, Tongzhou Wang, Sernam Lim, Phillip Isola, Antonio Torralba ECCV 2022. [Paper][Website][Code][Video] | |
| Any-resolution Training for High-resolution Image Synthesis Lucy Chai, Michaël Gharbi, Eli Shechtman, Phillip Isola, Richard Zhang ECCV 2022. [Paper][Website][Code][Video] | |
| Denoised MDPs: Learning World Models Better Than The World Itself Tongzhou Wang, Simon S. Du, Antonio Torralba, Phillip Isola, Amy Zhang, Yuandong Tian ICML 2022. [Paper][Website][Code] | |
| Exploring Visual Prompts for Adapting Large-Scale Models Hyojin Bahng, Ali Jahanian*, Swami Sankaranarayanan*, Phillip Isola arXiv 2022. [Paper][Website][Code] | |
| Learning to generate line drawings that convey geometry and semantics Caroline Chan, Frédo Durand, Phillip Isola CVPR 2022. [Paper][Website][Code][Demo] | |
| On the Learning and Learnability of Quasimetrics Tongzhou Wang, Phillip Isola ICLR 2022. [Paper][Website][Code] | |
| Generative Models as a Data Source for Multiview Representation Learning Ali Jahanian, Xavier Puig, Yonglong Tian, Phillip Isola ICLR 2022. [Paper][Website][Code][News article] | |
| NeRF-Supervision: Learning Dense Object Descriptors from Neural Radiance Fields Lin Yen-Chen, Pete Florence, Jonathan T. Barron, Tsung-Yi Lin, Alberto Rodriguez, Phillip Isola ICRA 2022. [Paper][Website][Video][Code][Colab] |
