Pith. sign in

REVIEW 5 cited by

Feather the Throttle: Revisiting Visual Token Pruning for Vision-Language Model Acceleration

Not yet reviewed by Pith; the record is open.

Re-run · record.json Download PDF Read on arXiv ↗

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 2412.13180 v2 pith:TPLXSW2G submitted 2024-12-17 cs.CV

Mark Endo , Xiaohan Wang , Serena Yeung-Levy This is my paper · ORCID
classification cs.CV
keywords accelerationpruningapproachperformancevisualbenchmarksfeatherstrong
verification ladder T0 review T1 audit T2 compute T3 formal
0 comments
read the original abstract

Recent works on accelerating Vision-Language Models achieve strong performance across a variety of vision-language tasks despite highly compressing visual information. In this work, we examine the popular acceleration approach of early pruning of visual tokens inside the language model. Surprisingly, we find that while strong performance is maintained across many tasks, it exhibits drastically different behavior for a subset of vision-centric tasks such as localization. Upon further investigation, we uncover a core issue with the acceleration approach where most tokens towards the top of the image are pruned away. Yet, on many benchmarks aiming to evaluate vision-centric capabilities, strong performance persists with the flawed pruning strategy, highlighting these benchmarks' limited ability to assess fine-grained visual capabilities. Based on these findings, we propose FEATHER (Fast and Effective Acceleration wiTH Ensemble cRiteria), a straightforward approach that resolves the discovered early-layer pruning issue and further enhances the preservation of relevant tokens via multistage pruning with early uniform sampling to ensure broad image coverage. With comparable computational savings, we find that FEATHER achieves more than 5x performance improvement on the vision-centric localization benchmarks compared to the original acceleration approach.

Discussion (0). Continue with ORCID to comment.

Forward citations

Cited by 5 Pith papers

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

  1. Modelling Gas-Phase Reaction Kinetics with Guided Particle Diffusion Sampling

    physics.comp-ph 2026-04 unverdicted novelty 6.0 of 10

    HalfV decouples universal early visual redundancy from architecture-dependent late saturation and prunes accordingly, retaining 96.8% performance at 4.1× FLOPs on Qwen2.5-VL.

  2. Streamline Without Sacrifice -- Squeeze out Computation Redundancy in LMM

    cs.CV 2025-05 conditional novelty 6.0 of 10

    ProxyV introduces proxy vision tokens that take over expensive attention and feed-forward computation in later layers of decoder-only multimodal models, cutting FLOPs by 25-46% while retaining or improving accuracy on...

  3. SepPrune:A Separator-based Pruning Framework for Efficient Multimodal Large Language Models

    cs.CV 2026-07 conditional novelty 5.0 of 10

    Using the separator token as a position-free query, SepPrune prunes 80% of vision tokens while retaining 96.3% of Qwen2.5-VL-7B's original accuracy.

  4. GreedyPrune: Retenting Critical Visual Token Set for Large Vision Language Models

    cs.CV 2025-06 conditional novelty 5.0 of 10

    A training-free token pruning method that combines cosine-similarity saliency with greedy redundancy removal to preserve accuracy at high compression ratios.

  5. FlexSelect: Flexible Token Selection for Efficient Long Video Understanding

    cs.CV 2025-06 conditional novelty 5.0 of 10

    FlexSelect selects a small fraction of query-relevant visual tokens using attention from an intermediate layer, improving long-video accuracy and inference speed across multiple VideoLLMs.

Pith tools