An autoregressive latent world model with a monotone cost ranking loss outperforms four baselines on GNM image-goal navigation, including a 2.7x orientation-error cut over a reimplemented DINO-WM baseline.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.RO 1years
2026 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Latent World Models with Monotone Planning Costs for Image-Goal Navigation
An autoregressive latent world model with a monotone cost ranking loss outperforms four baselines on GNM image-goal navigation, including a 2.7x orientation-error cut over a reimplemented DINO-WM baseline.