RAda attaches one lightweight attention layer to the end of a VLM to learn a mask that reweights the final fused image-text representation, improving fine-tuning across FFT, EFT, and TTT settings.
Domain generalization via rationale invariance
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CV 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
One Last Attention for Your Vision-Language Model
RAda attaches one lightweight attention layer to the end of a VLM to learn a mask that reweights the final fused image-text representation, improving fine-tuning across FFT, EFT, and TTT settings.