Target-Bench shows the best off-the-shelf video world model scores only 0.341 on semantic target-approaching and directional consistency, with fine-tuning on a small robot dataset yielding measurable gains.
Learning view-invariant world models for vi- sual robotic manipulation
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CV 1years
2025 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Target-Bench: Can Video World Models Achieve Mapless Path Planning with Semantic Targets?
Target-Bench shows the best off-the-shelf video world model scores only 0.341 on semantic target-approaching and directional consistency, with fine-tuning on a small robot dataset yielding measurable gains.