Menu

Post image 1
Post image 2
Post image 3
Post image 4
Post image 5
Post image 6
Post image 7
Post image 8
Post image 9
Post image 10
Post image 11
Post image 12
Post image 13
Post image 14
Post image 15
Post image 16
Post image 17
Post image 18
Post image 19
Post image 20
Post image 21
Post image 22
Post image 23
Post image 24
Post image 25
Post image 26
Post image 27
Post image 28
Post image 29
Post image 30
Post image 31
Post image 32
Post image 33
Post image 34
Post image 35
Post image 36
Post image 37
Post image 38
1 / 38
0

Alexi Gladstone | Explorative Modeling -- Unlocking a Third Pretraining Axis and End-to-End Generation

Reading 0:00
15s threshold

Website: https://explorative-modeling.github.io/ GitHub: https://github.com/alexiglad/XM TLDR : We introduce Explorative Modeling, a new paradigm for generative modeling that acts as a third pretraining axis when added to existing generative models, and also enables end-to-end generation. Increasing exploration monotonically improves existing models across images, video, and language, and the gains grow with scale (7%→36% with data, 13%→23% with parameters). Concretely, Explorative Models (XMs) reach 6.2× sample efficiency, 4.1× FLOP efficiency, and 47% better parameter efficiency. Exploration also enables scaling generalization, and scaling how end-to-end existing models are. As end-to-end generative models, XMs match diffusion on control tasks with up to 256× less inference compute. Let me start with a question that sounds simple. If I ask a model to “generate a dog”, how many correct answers are there? It turns out there are a lot… likely billions or more images that we could count as dog images.…

Continue reading — create a free account

Join HashtagPLUS to read full articles, follow hashtags, vote, and join the conversation.

Read More