Pith. sign in

REVIEW 2 cited by

ToSA: Token Merging with Spatial Awareness

Not yet reviewed by Pith; the record is open.

This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.

SPECIMEN: schema-true, not a live event

T0 review · schema-true

One-sentence machine reading of the paper's core claim.

pith:XXXXXXXX · record.json · timestamp

arxiv 2506.20066 v1 pith:VULPCMSO submitted 2025-06-24 cs.CV

classification cs.CV
keywords mergingtokenspatialtosavisualawarenessinformationmethods
verification ladder T0 review T1 audit T2 compute T3 formal
0 comments
read the original abstract

Token merging has emerged as an effective strategy to accelerate Vision Transformers (ViT) by reducing computational costs. However, existing methods primarily rely on the visual token's feature similarity for token merging, overlooking the potential of integrating spatial information, which can serve as a reliable criterion for token merging in the early layers of ViT, where the visual tokens only possess weak visual information. In this paper, we propose ToSA, a novel token merging method that combines both semantic and spatial awareness to guide the token merging process. ToSA leverages the depth image as input to generate pseudo spatial tokens, which serve as auxiliary spatial information for the visual token merging process. With the introduced spatial awareness, ToSA achieves a more informed merging strategy that better preserves critical scene structure. Experimental results demonstrate that ToSA outperforms previous token merging methods across multiple benchmarks on visual and embodied question answering while largely reducing the runtime of the ViT, making it an efficient solution for ViT acceleration. The code will be available at: https://github.com/hsiangwei0903/ToSA

Discussion (0). Sign in to comment.

Forward citations

Cited by 2 Pith papers

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score.

  1. WaveZip: Wavelet-Driven Space-Time Decoupling for Video Token Condensation

    cs.CV 2026-07 conditional novelty 6.0 of 10

    WaveZip, a training-free wavelet method for video token condensation, reports about 10x token reduction while retaining roughly 98-99% accuracy on multi-benchmark LVLM evaluation.

  2. WaveZip: Wavelet-Driven Space-Time Decoupling for Video Token Condensation

    cs.CV 2026-07 conditional novelty 6.0 of 10

    Wavelet-based temporal and spatial token condensation preserves 99.6% of full-token video question-answering accuracy at 10x compression without retraining.

Pith tools