Explorative Modeling: Unlocking a Third Pretraining Axis and End-to-End Generation
The deep learning revolution, kicked off by AlexNet, taught us that end-to-end training beats decomposing a problem into hand-designed stages. Generative modeling, however, has remained the exception-despite generative models being remarkably capable, they are still not trained end-to-end. This is because, at its core, generative modeling is about handling distributions with many modes, and existing scalable approaches handle this the same way, by factoring the generation procedure, which prevents end-to-end generation. In this work, we introduce Explorative Modeling, a new paradigm that instead factors the training loop, exploring K candidate matches between model generations and data, a...
| Authors | Alexi Gladstone, Heng Ji, Yilun Du |
|---|---|
| Primary category | cs.LG |
| Published | 29 July 2026 |
| Last updated at source | 29 July 2026 |
Models and datasets referencing this paper
- F16/krea2-turbo-sdaModel
Silytics shows public metadata from arXiv and links to the original. Information may be incomplete or out of date. Last refreshed 17 October 2026. Licenses and terms of the original apply to the work itself. Not financial, legal or professional advice.