ASAP: Attention Sink Anchored Pruning

Abstract:Vision Transformers (ViTs) face severe computational bottlenecks due to the quadratic complexity of self-attention at high resolutions. Existing token reduction methods rely on local metrics -- such as single-layer attention scores -- that are inherently vulnerable to the attention sink phenomenon, where uninformative tokens are paradoxically preserved over salient foreground objects. We propose ASAP (Attention Sink Anchored Pruning), a training-free framework that recasts this sink as a feature. Modeling ViT information flow as a Lazy Random Walk, ASAP identifies the sink as a dominant accumulator of probability mass. By computing the diffusion distance to the sink within the cumulative transition matrix, ASAP partitions tokens via Radial Diffusion Clustering and compresses background redundancy through Transition Weight Pooling in a single shot. Extensive experiments across image, video, and vision-language tasks demonstrate ASAP outperforms state-of-the-art methods, accelerating throughput by up to 48% while maintaining or even exceeding baseline accuracy.

Machine Learning (cs.LG)

arXiv:2605.22372 [cs.LG]

(or arXiv:2605.22372v2 [cs.LG] for this version)

https://doi.org/10.48550/arXiv.2605.22372 Focus to learn more arXiv-issued DOI via DataCite

arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website.

Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them.

Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs.