What if Eye...?
We created a virtual petri dish where digital creatures evolve eyes from scratch, replaying millions of years of evolution. 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. Our digital creatures evolve different eyes based on survival needs - compound-like eyes for navigation, camera-like eyes for food and poison discrimination. 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. 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. * Eq
Computationally recreating vision evolution A What-if Eye... Universe? Kushagra Tiwary*1, Aaron Young*1, Zaid Tasneem*2, Tzofi Klinghoffer1,6, Akshat Dave1, Tomaso Poggio3, Dan-Eric Nilsson4, Brian Cheung**3,6, Ramesh Raskar**1 Evolution happened once. We build a video-game universe to replay evolution. This allows us to computationally study principles behind biological intelligence and create new forms of artificial intelligence. Agents begin with a single light-sensing cell and evolve their visual intelligence by facing real physics, embodied constraints, and survival pressures. The…
saved by
related reading
- Blaise Agüera y Arcas | What is Intelligence? | Long Now Talksyoutube.com
- Playing optical tweezers with deep reinforcement learning: in virtual, physical and augmented environmentsarxiv.org
- The worminator project postpreprintarxiv.org
- Using Artificial Intelligence to Augment Human Intelligencedistill.pub
- [2607.02954] Microcosmos: Reimagining Artificial Life for the GPU Eraarxiv.org
- Artificial Lifeyoutube.com
- The Limits of Computer Vision, and of Our Own | Harvard Medicine Magazinemagazine.hms.harvard.edu
- EPIC: What if… | Microsoft Researchmsrepic.github.io
- We spent 2 hours working in the future - METRmetr.org
- Yufeng Zhaoyufengzhao.com
- The AI Picbreeder Experiment: In Search of Automatic Open-Endednesspub.sakana.ai
- The Electrostatic Brain: How a Web of Neurons Generates the World-Simulation that is Youqri.org