DreamX uses video diffusion models to learn transferable latent actions

Researchers introduce DreamX, a method that turns a pretrained video diffusion model into a learner of compact latent actions. The resulting latent space is presented as a shared action interface across human and robot embodiments, environments, and action parameterizations. DreamX reports state-of-the-art results among latent action models on LARY-Bench and supports any-to-any video transfer, zero-shot action transfer, and policy learning with lower computational cost. The work is described in an arXiv paper; no code or model release is stated in the abstract.