Introducing Un-0: Generating Images with Coupled Oscillators - Unconventional AI
TL;DR. Executing deep neural networks on GPUs has dominated AI for a decade, but we think the next jump in energy efficiency demands a fundamentally different computer, one where physics does the computing. We built Un-0, an image generator powered
Skip to content grant careers TL;DR. Executing deep neural networks on GPUs has dominated AI for a decade, but we think the next jump in energy efficiency demands a fundamentally different computer, one where physics does the computing. We built Un-0, an image generator powered by a simulated system of coupled oscillators, an example of an emerging physical computing substrate. On ImageNet 64×64 it reaches FID 6.74, matching the quality of leading conventional image generation methods when they were first published. Weights, training, and ablation code are all open. Join us on an…
saved by
related reading
- Unconventional AIunconv.ai
- A Unified Model for Motion-Conditioned Robot Co-designtransformer-transformer.github.io
- Ushering in the Thermodynamic Future | Extropicextropic.ai
- Generalist - GEN-0 / Embodied Foundation Models That Scale with Physical Interactiongeneralistai.com
- Energy-Based Modelsenergy-based-model.github.io
- [2006.11239] Denoising Diffusion Probabilistic Modelsarxiv.org
- https://arxiv.org/pdf/2006.11239arxiv.org
- How to Make the Universe Think for Us | Quanta Magazinequantamagazine.org
- Generative Modeling via Driftingarxiv.org
- Home | Physics Of Learningphysicsoflearning.org
- Elucidating the Design Space of Diffusion-Based Generative Models | PDFarxiv.org
- Generative Image Dynamicsgenerative-dynamics.github.io