Reposted by John Ryan
Here it is: arxiv.org/abs/2412.15129
Jet: A Modern Transformer-Based Normalizing Flow
In the past, normalizing generative flows have emerged as a promising class of generative models for natural images. This type of model has many modeling advantages: the ability to efficiently compute...
arxiv.org
December 20, 2024 at 2:33 PM
Here it is: arxiv.org/abs/2412.15129
The normalizing flow architecture they cite is from a paper which isn't yet published. Excited to read it though because JetFormer seems to have the largest normalising flows I've even, and they claim to have minimal issues with training stability 👀
December 3, 2024 at 10:20 PM
The normalizing flow architecture they cite is from a paper which isn't yet published. Excited to read it though because JetFormer seems to have the largest normalising flows I've even, and they claim to have minimal issues with training stability 👀
Reposted by John Ryan
DeMo was created in March 2024 by Bowen Peng and Jeffrey Quesnelle and has been published on arXiv in collaboration with Diederik P. Kingma, co-founder of OpenAI and inventor of the Adam optimizer and VAEs.
The paper is available here: arxiv.org/abs/2411.19870
And code: github.com/bloc97/DeMo
The paper is available here: arxiv.org/abs/2411.19870
And code: github.com/bloc97/DeMo
DeMo: Decoupled Momentum Optimization
Training large neural networks typically requires sharing gradients between accelerators through specialized high-speed interconnects. Drawing from the signal processing principles of frequency decomp...
arxiv.org
December 2, 2024 at 4:46 PM
DeMo was created in March 2024 by Bowen Peng and Jeffrey Quesnelle and has been published on arXiv in collaboration with Diederik P. Kingma, co-founder of OpenAI and inventor of the Adam optimizer and VAEs.
The paper is available here: arxiv.org/abs/2411.19870
And code: github.com/bloc97/DeMo
The paper is available here: arxiv.org/abs/2411.19870
And code: github.com/bloc97/DeMo
The moderation lists you can subscribe to are an interesting mechanism, to make a good one will probably require a decent amount of resources so I hope bluesky will provide some solid ones / fund people who will build & maintain community trusted lists.
November 24, 2024 at 8:36 PM
The moderation lists you can subscribe to are an interesting mechanism, to make a good one will probably require a decent amount of resources so I hope bluesky will provide some solid ones / fund people who will build & maintain community trusted lists.