pith. sign in

Video diffusion models

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

1 Pith paper citing it

fields

cs.RO 1

years

2026 1

verdicts

UNVERDICTED 1

representative citing papers

WorldVLN: Autoregressive World Action Model for Aerial Vision-Language Navigation

cs.RO · 2026-05-15 · unverdicted · novelty 7.0

WorldVLN proposes the first autoregressive world action model for aerial vision-language navigation that predicts short-horizon latent world states, decodes them to waypoints in closed loop, and uses two-stage training with Action-aware GRPO to achieve over 12% success-rate gains on benchmarks plus零

citing papers explorer

Showing 1 of 1 citing paper.

  • WorldVLN: Autoregressive World Action Model for Aerial Vision-Language Navigation cs.RO · 2026-05-15 · unverdicted · none · ref 16

    WorldVLN proposes the first autoregressive world action model for aerial vision-language navigation that predicts short-horizon latent world states, decodes them to waypoints in closed loop, and uses two-stage training with Action-aware GRPO to achieve over 12% success-rate gains on benchmarks plus零