Image-LoRA selectively adapts only visual tokens and chosen attention heads in VLMs, matching standard LoRA performance with lower parameter count and FLOPs.
Are sixteen heads really better than one?Advances in neural information processing systems, 32
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CV 1years
2025 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Selective LoRA for Visual Tokens and Attention Heads
Image-LoRA selectively adapts only visual tokens and chosen attention heads in VLMs, matching standard LoRA performance with lower parameter count and FLOPs.