Phillip Isola

p h i l l i p i @ m i t . e d u
Google Scholar / GitHub / Social media

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. A longer bio is here.

Quick links: Papers / Courses / Talks / Writing / Research Group

⭐

News

⭐

• Quanta magazine published a very nice, general audience article covering the platonic representation hypothesis: link

•

We have released a free online copy of our computer vision textbook here: visionbook.mit.edu

Research Group

The goal of our group is to understand fundamental principles of intelligence. We are especially interested in human-like intelligence, which to us means intelligence that is built out of neural nets, is highly adaptive and general-purpose, and is emergent from embodied interactions in rich ecosystems.

Questions we are currently studying include the following, which you can click on to expand:

▸ Representational universals: To what extent do different models, trained on different datasets and modalities, learn similar representations of the world? What are the commonalities between different kinds of intelligence?

Representative projects: The Platonic Representation Hypothesis, Words That Make Language Models Perceive, Unpaired Multimodal Representation Learning

▸ Emergent intelligence: How can intelligence emerge from "scratch", without imitating another intelligence's cultural artifacts?

Representative projects: Search for artificial life, Learning from procedural programs, Neural MMO

Our goal in studying these questions is to help equip the world with the tools necessary to bring about a positive integration of AI into society; to understand intelligence so we can prevent its harms and to reap its benefits.

The lab is part of the broader Embodied Intelligence and Visual Computing research communities at MIT.

PhD Students Caroline Chan Hyojin Bahng Akarsh Kumar Shobhita Sundaram Sharut Gupta Ishaan Preetam-Chandratreya Kaiya (Ivy) Zhao Yulu Gan Adam Rashid Ching Lam Choi	Postdocs Prafull Sharma Undergraduates Sophie Wang Cheuk Hei Chu

Former Members and Visitors
Interested in joining the group? Please see info about applying here.

Recent Courses

6.s058: Advances in Computer Vision (Spring 2025)
6.7960: Deep Learning (Fall 2024)
6.s953: Embodied Intelligence (Spring 2024)

New papers (All papers)

	Digital Red Queen: Adversarial Program Evolution in Core War with LLMs Akarsh Kumar, Ryan Bahlous-Boldi, Prafull Sharma, Phillip Isola, Sebastian Risi, Yujin Tang, David Ha arXiv 2026. [Paper (web)][Paper (pdf)][Code][Blog]
	Words That Make Language Models Perceive Sophie L. Wang, Phillip Isola, Brian Cheung arXiv 2025. [Paper][Website][Code]
	Better Together: Leveraging Unpaired Multimodal Data for Stronger Unimodal Models Sharut Gupta, Shobhita Sundaram, Chenyu Wang, Stefanie Jegelka, Phillip Isola arXiv 2025. [Paper][Website][Code]
	Training Transformers with Enforced Lipschitz Constants Laker Newhouse, R. Preston Hess, Franz Cesista, Andrii Zahorodnii, Jeremy Bernstein, Phillip Isola arXiv 2025. [Paper][Code]
	Single-pass Adaptive Image Tokenization for Minimum Program Search Shivam Duggal, Sanghyun Byun, William T. Freeman, Antonio Torralba, Phillip Isola NeurIPS 2025. [Paper][Code]
	LucidXR: A Framework for Learning Dexterous Manipulation from Human Demonstrations Yajvan Ravan, Adam Rashid, Alan Yu, Kai McClennen, Gio Huh, Kevin Yang, Zhutian Yang, Qinxi Yu, Xiaolong Wang, Phillip Isola, Ge Yang CoRL 2025. [Paper][Website][Video]
	Automating the Search for Artificial Life with Foundation Models Akarsh Kumar, Chris Lu, Louis Kirsch, Yujin Tang, Kenneth O. Stanley, Phillip Isola, David Ha Artificial Life 2025. [Paper (web)][Paper (pdf)][Code][Blog]
	Cycle Consistency as Reward: Learning Image-Text Alignment without Human Preferences Hyojin Bahng, Caroline Chan, Frédo Durand, Phillip Isola ICCV 2025. [Paper][Website][Code]
	Separating Knowledge and Perception with Procedural Data Adrián Rodríguez-Muñoz, Manel Baradad, Phillip Isola, Antonio Torralba ICML 2025. [Paper][Website][Code]
	Intrinsically Memorable Words Have Unique Associations With Their Meanings Greta Tuckute, Kyle Mahowald, Phillip Isola, Aude Oliva, Edward Gibson, Evelina Fedorenko Journal of Experimental Psychology: General 2025 (Editor's Choice article). [Paper]

...

All papers