PyramidDrop accelerates LVLMs by staged, similarity-based dropping of visual tokens that become redundant in deeper layers, delivering 40% faster training and 55% lower inference cost with comparable accuracy.
Vicuna: An open-source chatbot impressing gpt-4 with 90%* chatgpt quality
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
-
PyramidDrop: Accelerating Your Large Vision-Language Models via Pyramid Visual Redundancy Reduction
PyramidDrop accelerates LVLMs by staged, similarity-based dropping of visual tokens that become redundant in deeper layers, delivering 40% faster training and 55% lower inference cost with comparable accuracy.