COAST prunes 77.8% of visual tokens in LVLMs with a 2.15x speedup while keeping 98.64% of original performance by adaptively routing semantic and spatial context via contrastive scores.
An image is worth 16x16 words: Transformers for image recognition at scale
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
citation-role summary
background 1
citation-polarity summary
roles
background 1polarities
background 1representative citing papers
λ-Orthogonality regularization enables distribution-specific adaptation of representations via affine transformations while retaining original learned structures.
citing papers explorer
-
Evading Visual Aphasia: Contrastive Adaptive Semantic Token Pruning for Vision-Language Models
COAST prunes 77.8% of visual tokens in LVLMs with a 2.15x speedup while keeping 98.64% of original performance by adaptively routing semantic and spatial context via contrastive scores.
-
$\boldsymbol{\lambda}$-Orthogonality Regularization for Compatible Representation Learning
λ-Orthogonality regularization enables distribution-specific adaptation of representations via affine transformations while retaining original learned structures.