AI-SOVEREIGN
Home / AI Research / One Prior, Two Dynamics: Repurposing Video Diffusion Transformers for Self-Supervised Latent Action Learning
ONAI Research

One Prior, Two Dynamics: Repurposing Video Diffusion Transformers for Self-Supervised Latent Action Learning

by NationalUniversityofSingapore · Yuxin Jiang, Wenqiang Sun, Jiaqi Li, Yuchao Gu, Lvmin Zhang, Ivor Tsang

Videos reveal how the world changes, but rarely the actions that cause those changes. Latent action learning recovers such supervision from visual transitions, yet often learns the underlying dynamics largely from scratch. We ask whether a pretrained video generator can instead provide the prior for both inverse and forward dynamics. We introduce O^{2}LaF, built on a simple principle: one prior, two dynamics. We initialize both models from the same pretrained video DiT and adapt them to their distinct roles: a feed-forward transition encoder with learnable action queries for inverse dynamics, and a causal, action-conditioned video generator for forward dynamics. By controlling information…

Upvotes4
Comments2
Published18 Nov 2026

More from NationalUniversityofSingapore