pith. sign in

Title resolution pending

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

1 Pith paper citing it

fields

cs.CV 1

years

2026 1

verdicts

UNVERDICTED 1

representative citing papers

DEVIS-GRPO: Unleashing GRPO on Dynamic Extreme View Synthesis

cs.CV · 2026-05-16 · unverdicted · novelty 7.0

DEVIS-GRPO applies online policy gradients with an accumulative small-to-large view sampling strategy and multi-level rewards to improve trajectory-controlled extreme view video generation, reporting gains on Kubric-4D, iPhone, and DL3DV datasets.

citing papers explorer

Showing 1 of 1 citing paper.

  • DEVIS-GRPO: Unleashing GRPO on Dynamic Extreme View Synthesis cs.CV · 2026-05-16 · unverdicted · none · ref 63

    DEVIS-GRPO applies online policy gradients with an accumulative small-to-large view sampling strategy and multi-level rewards to improve trajectory-controlled extreme view video generation, reporting gains on Kubric-4D, iPhone, and DL3DV datasets.