ARFM adaptively adjusts a scaling factor in the flow-matching loss so that offline RL advantage signals are preserved while gradient variance is controlled, improving VLA robot policy fine-tuning.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.RO 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Balancing Signal and Variance: Adaptive Offline RL Post-Training for VLA Flow Models
ARFM adaptively adjusts a scaling factor in the flow-matching loss so that offline RL advantage signals are preserved while gradient variance is controlled, improving VLA robot policy fine-tuning.