Flexible Diffusion Modeling of Long Videos abs: arxiv.org/abs/2205.11495 demonstrate improved video modeling over prior work on a number of datasets and sample temporally coherent videos over 25 minutes in length

Thanks for the shout out Frank Wood - the videos still have occasional glitches but are much better after scaling from training on 1 GPU to 4 GPUs. Simply scaling further might be the right direction to take

This paper is a goldmine for anyone training diffusion models, carefully picking apart theory and practice and showing which choices really matter. I was quite excited to see the authors of the StyleGAN series of papers tackle this topic, and boy do they deliver!

This was a lot of fun to work on! And works well with test-time guidance: we can train on varying-length RoboDesk videos and then, at test-time, fix the first and last frames and automatically figure out how far apart they are - i.e. how long the robot needs to move between them!

It is @NeurIPS time again! I am excited to present our trans-dimensional jump diffusion work with Andrew Campbell Will Harvey Valentin De Bortoli Tom Rainforth and Arnaud Doucet ! Come over on Thursday 2nd poster session, neurips.cc/virtual/2023/p…. arxiv.org/abs/2305.16261 #NeurIPS2023