ALVA uses a frozen vision-language model to summarize action-conditioned visual transitions and rate them against an instruction, providing terminal feedback that outperforms embedding-based baselines in ALFRED/AI2-THOR.
Zero-shot reward specification via grounded natural language
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
citation-role summary
background 1
citation-polarity summary
fields
cs.RO 1years
2026 1verdicts
CONDITIONAL 1roles
background 1polarities
background 1representative citing papers
citing papers explorer
-
Action- and Language-Conditioned Video Assessment for Embodied Control
ALVA uses a frozen vision-language model to summarize action-conditioned visual transitions and rate them against an instruction, providing terminal feedback that outperforms embedding-based baselines in ALFRED/AI2-THOR.