Explorative Modeling: A Third Pretraining Axis Boosting Efficiency Up to 6.2×

_akhaliq · x · 2026-08-01

The paper introduces Explorative Modeling, a new generative modeling paradigm that acts as a third pretraining axis for existing models and enables end-to-end generation.

Experiments show that increasing exploration monotonically improves performance across images, video, and language, with gains scaling alongside data (7%→36%) and parameters (13%→23%).

Concretely, Explorative Models (XMs) achieve 6.2× sample efficiency, 4.1× FLOP efficiency, and 47% better parameter efficiency. On control tasks, XMs match diffusion models while requiring up to 256× less inference compute.

Related event: Explorative Modeling Introduces Third Pretraining Axis, Questioned as avataRL Reinvention(8 posts)→

Original post →

More from Research

Research channel →