SparseVLM uses text-guided attention to prune and recycle visual tokens in VLMs, delivering 54% FLOPs reduction and 37% lower latency with 97% accuracy retention on LLaVA.
A convnet for the 2020s
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CV 1years
2024 1verdicts
ACCEPT 1representative citing papers
citing papers explorer
-
SparseVLM: Visual Token Sparsification for Efficient Vision-Language Model Inference
SparseVLM uses text-guided attention to prune and recycle visual tokens in VLMs, delivering 54% FLOPs reduction and 37% lower latency with 97% accuracy retention on LLaVA.