pith. machine review for the scientific record. sign in

Structured world models from human videos

1 Pith paper cite this work. Polarity classification is still indexing.

1 Pith paper citing it

fields

cs.RO 1

years

2025 1

verdicts

UNVERDICTED 1

representative citing papers

UniVLA: Learning to Act Anywhere with Task-centric Latent Actions

cs.RO · 2025-05-09 · unverdicted · novelty 6.0

UniVLA trains cross-embodiment vision-language-action policies from unlabeled videos via a latent action model in DINO space, beating OpenVLA on benchmarks with 1/20th pretraining compute and 1/10th downstream data.

citing papers explorer

Showing 1 of 1 citing paper.

  • UniVLA: Learning to Act Anywhere with Task-centric Latent Actions cs.RO · 2025-05-09 · unverdicted · none · ref 58

    UniVLA trains cross-embodiment vision-language-action policies from unlabeled videos via a latent action model in DINO space, beating OpenVLA on benchmarks with 1/20th pretraining compute and 1/10th downstream data.