SAFT adds self-supervised structure-aware losses (invariance and proportionality) via LoRA adapters to VLM rewards, improving RL policy learning and reward alignment across four control tasks.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2026 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Enhancing VLM Reward Models Through Structure-Aware Fine-Tuning
SAFT adds self-supervised structure-aware losses (invariance and proportionality) via LoRA adapters to VLM rewards, improving RL policy learning and reward alignment across four control tasks.