Diffusion hypernetworks: Will a network similar to DALLE be able to generate "network weights" instead of images in 2023
Basic
15
Ṁ2735resolved Jan 3
Resolved
NO1D
1W
1M
ALL
Criterion: an arxiv paper or a git repo or an official release from a known group (openAI, deepmind, etc) that uses denoising to generate another network's weights
Edit: check this out :) https://twitter.com/liuzhuang1234/status/1760195922502312197
This question is managed and resolved by Manifold.
Get
1,000
and3.00
Related questions
Related questions
Is Diffusion Models all you need for image generation?
52% chance
Will there be a successful application of diffusion-like weight modification in LLMs before 2027?
50% chance
Between 2030 and 2035 there will be evidence of different models of neural network collaborating better with eachother
56% chance