https://eyes.mit.edu/

What if Eye...?

We created a virtual petri dish where digital creatures evolve eyes
from scratch, replaying millions of years of evolution.

V

Computationally Recreating the Cambrian Explosion of Vision

Starting with a single light-detecting cell, our digital creatures
face challenges that shaped real eyes over millions of years:
navigating the world, discerning food from poison, and evading
predators.

Orientation & Navigation
Food & Poison Discrimination
Prey Tracking

Emergence of eyes from single light-sensitive photoreceptors

Our digital creatures evolve different eyes based on survival needs -
compound-like eyes for navigation, camera-like eyes for food and
poison discrimination.

Generation 0
Arrow
Generation 50

Why do eyes have lenses?

Our creatures independently discover solutions that nature found -
like lenses that focus light - emerging naturally to balance survival
pressures and physical constraints of their environment.

Random Mutations to Creature's Optical Gene
Arrow
Generation 150

Projects / Papers / Visual Exhibits

What if Eye...? Computationally Recreating Vision Evolution

Kushagra Tiwary*, Aaron Young*, Zaid Tasneem, Tzofi Klinghoffer,
Akshat Dave, Tomaso Poggio, Dan-Eric Nilsson, Brian Cheung **, Ramesh
Raskar **

We computationally recreate the vision evolution to study what-if
scenarios that never happened in nature and understand the principles
behind biological vision evolution.

* Equal contribution     ** Equal advising

Paper (arXiv Preprint) Blog TEDx Talk

Artificial Cambrian Intelligence: Evolve your own creatures in our
simulator!

We've created a simulator where you can define and evolve your own
embodied agents. You can define your own task, or use existing ones,
and evolve agent's eyes or brains.

Documentation Examples

A Roadmap for Generative Design of Visual Intelligence

Kushagra Tiwary, Tzofi Klinghoffer*, Aaron Young*, Siddharth
Somasundaram, Nikhil Behari, Akshat Dave, Brian Cheung, Dan-Eric
Nilsson, Tomaso Poggio, Ramesh Raskar

Can we use biological principles (natural evolution) to study the
evolution of vision and design more intelligent artificial vision,
i.e. enable a Cambrian Explosion of artificial vision.

MIT Press Impact Paper

MIT Museum Exhibit After Dark Event: Evolving Animals Eyes in Virtual
Reality!

Cathy Chang, Aaron Young, Kushagra Tiwary

We are exhibiting evolving eyes at an After Dark Event at the MIT
Museum! Stay tuned for more details.

Coming Soon!
MIT Media Lab, Camera Culture
Center for Brains Minds and Machines, MIT
InfoLab, MIT CSAIL
Lund Vision Group
Rice University

Copyright 2025 MIT Media Lab. All rights reserved.

Contact GitHub Twitter
MIT Accessibility