Skip-Vision: Efficient and Scalable Acceleration of Vision-Language Models via Adaptive Token Skipping
Journal:
arXiv
Published Date:
Mar 26, 2025
Abstract
Transformer-based models have driven significant advancements in Multimodal
Large Language Models (MLLMs), yet their computational costs surge drastically
when scaling resolution, training data, and model parameters. A key bottleneck
stems from the proliferation of visual tokens required for fine-grained image
understanding. We propose Skip-Vision, a unified framework addressing both
training and inference inefficiencies in vision-language models. On top of
conventional token compression approaches, our method introduces two
complementary acceleration strategies. For training acceleration, we observe
that Feed-Forward Network (FFN) computations on visual tokens induce marginal
feature updates. This motivates our Skip-FFN strategy, which bypasses FFN
layers for redundant visual tokens. For inference acceleration, we design a
selective KV-cache removal mechanism that prunes the skipped key-value pairs
during decoding while preserving model performance. Experimental results
demonstrate that Skip-Vision reduces training time by up to 35\%, inference
FLOPs by 75\%, and latency by 45\%, while achieving comparable or superior
performance to existing methods. Our work provides a practical solution for
scaling high-performance MLLMs with enhanced efficiency.