nSFT matches multimodal RLHF performance by converting rejected responses into corrective SFT data, without pairwise preference optimization.
GQA: A new dataset for real-world visual reasoning and compositional question answering
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2024 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Continual SFT Matches Multimodal RLHF with Negative Supervision
nSFT matches multimodal RLHF performance by converting rejected responses into corrective SFT data, without pairwise preference optimization.