Typical VLMs con- vert images into discrete vision tokens via a vision encoder and process these tokens sequentially alongside text through an LLM decoder

INTRODUCTION The rapid advancement of Large Language Models (LLMs) has driven remarkable progress in Vision-Language Models (VLMs), which integrate visual, textual modalities to

1 Pith paper cite this work. Polarity classification is still indexing.

1 Pith paper citing it

browse 1 citing papers

representative citing papers

Beyond Attention Scores: SVD-Based Vision Token Pruning for Efficient Vision-Language Models

cs.CV · 2026-04-13 · unverdicted · novelty 6.0 · 2 refs

SVD-Prune selects vision tokens via SVD leverage scores to outperform attention-based pruning at extreme budgets of 32 or 16 tokens.

citing papers explorer

Showing 1 of 1 citing paper.

Beyond Attention Scores: SVD-Based Vision Token Pruning for Efficient Vision-Language Models cs.CV · 2026-04-13 · unverdicted · none · ref 1 · 2 links
SVD-Prune selects vision tokens via SVD leverage scores to outperform attention-based pruning at extreme budgets of 32 or 16 tokens.

Typical VLMs con- vert images into discrete vision tokens via a vision encoder and process these tokens sequentially alongside text through an LLM decoder

fields

years

verdicts

representative citing papers

citing papers explorer