Leo Zhang
@leoeleoleo1.bsky.social
📤 10
📥 12
📝 17
PhD student at
@oxfordstatistics.bsky.social
working on generative models
pinned post!
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
9 months ago
1
3
2
reposted by
Leo Zhang
Rob Cornish
9 months ago
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)
add a skeleton here at some point
1
5
1
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
9 months ago
1
3
2
you reached the end!!
feeds!
log in
