HMA is a masked autoregressive transformer that predicts future video and actions across many robot embodiments, running up to 15x faster than prior diffusion-based video simulators while matching or improving visual fidelity.
Maskgit: Masked generative image transformer
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.RO 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Learning Real-World Action-Video Dynamics with Heterogeneous Masked Autoregression
HMA is a masked autoregressive transformer that predicts future video and actions across many robot embodiments, running up to 15x faster than prior diffusion-based video simulators while matching or improving visual fidelity.