Author

Simar Kareer

1 paper indexed here

We haven’t gathered this author’s papers yet. Follow them and we’ll fetch their work.

Not the right person? Other researchers publish under this name.

Jul 2026

DeVA: Decoupled Video-Action Model with physical guidance for robot policy learning

DeVA is introduced, a Decoupled Video-Action model with specialized video and action experts, multi-level feature transfer, and physically salient guidance, enabling rich information exchange while making policy learning more tractable.

Mengqi Zhang, Sahil Khose, Simar Kareer et al. · arXiv.org · 2 citations