Pith. sign in

REVIEW 2 cited by

Beyond Intermediate States: Explaining Visual Redundancy through Language

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 2503.20540 v1 pith:MTOQ2BKG submitted 2025-03-26 cs.CV

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

Multi-modal Large Langue Models (MLLMs) often process thousands of visual tokens, which consume a significant portion of the context window and impose a substantial computational burden. Prior work has empirically explored visual token pruning methods based on MLLMs' intermediate states (e.g., attention scores). However, they have limitations in precisely defining visual redundancy due to their inability to capture the influence of visual tokens on MLLMs' visual understanding (i.e., the predicted probabilities for textual token candidates). To address this issue, we manipulate the visual input and investigate variations in the textual output from both token-centric and context-centric perspectives, achieving intuitive and comprehensive analysis. Experimental results reveal that visual tokens with low ViT-[cls] association and low text-to-image attention scores can contain recognizable information and significantly contribute to images' overall information. To develop a more reliable method for identifying and pruning redundant visual tokens, we integrate these two perspectives and introduce a context-independent condition to identify redundant prototypes from training images, which probes the redundancy of each visual token during inference. Extensive experiments on single-image, multi-image and video comprehension tasks demonstrate the effectiveness of our method, notably achieving 90% to 110% of the performance while pruning 80% to 90% of visual tokens.

Discussion (0). Continue with ORCID to comment.

Forward citations

Cited by 2 Pith papers

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

  1. Grounding-Driven Attack: Improving Encoder-based Adversarial Transferability against Large Vision-Language Models

    cs.CR 2026-02 conditional novelty 6.0 of 10

    A grounding-guided attack that concentrates perturbation on text-matched image regions and disrupts global and local semantic alignment consistently improves adversarial transferability across multiple vision-language models.

  2. A Comprehensive Study on Visual Token Redundancy for Discrete Diffusion-based Multimodal Large Language Models

    cs.CV 2025-11 conditional novelty 6.0 of 10

    Visual token pruning causes severe loss in discrete diffusion MLLMs; only from-scratch models on long-answer tasks recover via late denoising, so redundancy is recoverability, not dispensability.

Pith tools