Rob Cornish
@rob-cornish.bsky.social
Research fellow @ Oxford Statistics Department
jrmcornish.github.io
jrmcornish.github.io
A meta-point of this paper is that category theory has utility for reasoning about current problems of interest in mainstream machine learning. The theory is predictive, not just descriptive. 🧵(1/6)
In our new paper (accepted at ICLR), we propose the first framework for constructing equivariant diffusion models via symmetrisation
This allows us to ensure E(3)-equivariance with just highly scalable standard architectures such as Diffusion Transformers, instead of EGNNs, for molecular generation
This allows us to ensure E(3)-equivariance with just highly scalable standard architectures such as Diffusion Transformers, instead of EGNNs, for molecular generation
March 6, 2025 at 4:38 AM
A meta-point of this paper is that category theory has utility for reasoning about current problems of interest in mainstream machine learning. The theory is predictive, not just descriptive. 🧵(1/6)
Reposted by Rob Cornish
Awesome work by Kia @leoeleoleo1.bsky.social and @rob-cornish.bsky.social !
In our new paper (accepted at ICLR), we propose the first framework for constructing equivariant diffusion models via symmetrisation
This allows us to ensure E(3)-equivariance with just highly scalable standard architectures such as Diffusion Transformers, instead of EGNNs, for molecular generation
This allows us to ensure E(3)-equivariance with just highly scalable standard architectures such as Diffusion Transformers, instead of EGNNs, for molecular generation
March 4, 2025 at 4:04 PM
Awesome work by Kia @leoeleoleo1.bsky.social and @rob-cornish.bsky.social !