Pith. sign in

REVIEW 4 cited by

AdaReTaKe: Adaptive Redundancy Reduction to Perceive Longer for Video-language Understanding

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 2503.12559 v2 pith:7UUAU57O submitted 2025-03-16 cs.CV cs.CLcs.MM

Xiao Wang , Qingyi Si , Jianlong Wu , Shiyu Zhu , Li Cao , Liqiang Nie This is my paper
classification cs.CVcs.CLcs.MM
keywords adaretakeredundancycompressionlayerslvbenchmethodsmllmsmodels
verification ladder T0 review T1 audit T2 compute T3 formal
0 comments
read the original abstract

Multimodal Large Language Models (MLLMs) have revolutionized video understanding, yet are still limited by context length when processing long videos. Recent methods compress videos by leveraging visual redundancy uniformly, yielding promising results. Nevertheless, our quantitative analysis shows that redundancy varies significantly across time and model layers, necessitating a more flexible compression strategy. We propose AdaReTaKe, a training-free method that flexibly reduces visual redundancy by allocating compression ratios among time and layers with theoretical guarantees. Integrated into state-of-the-art MLLMs, AdaReTaKe improves processing capacity from 256 to 2048 frames while preserving critical information. Experiments on VideoMME, MLVU, LongVideoBench, and LVBench datasets demonstrate that AdaReTaKe outperforms existing methods by 2.3% and 2.8% for 7B and 72B models, respectively, with even greater improvements of 5.9% and 6.0% on the longest LVBench. Our code is available at https://github.com/SCZwangxiao/video-FlexReduc.git.

Discussion (0). Sign in to comment.

Forward citations

Cited by 4 Pith papers

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

  1. Searching Videos as Trees: Self-Correcting Agents for Grounded Long Video QA

    cs.CV 2026-07 conditional novelty 6.0 of 10

    An agent that searches a long video by navigating an adaptive temporal tree with zoom-in/zoom-out/shift actions improves grounded long-video QA, but the headline CG-Bench result is measured on a heavily filtered subset.

  2. DATE: Dynamic Absolute Time Enhancement for Long Video Understanding

    cs.CV 2025-09 conditional novelty 6.0 of 10

    DATE combines inference-time timestamp token injection with a caption-rewritten, temporally regularized CLIP sampling strategy to improve absolute time reasoning and event localization in long videos.

  3. HumanPCR: Probing MLLM Capabilities in Diverse Human-Centric Scenes

    cs.CV 2025-08 conditional novelty 6.0 of 10

    A hierarchical benchmark for multimodal models on human-centric visual understanding finds frontier models average under 60% and miss question-uncued visual evidence, with test-time scaling helping only marginally.

  4. CoTasks: Chain-of-Thought based Video Instruction Tuning Tasks

    cs.CV 2025-07 reject novelty 4.0 of 10

    Adding ground-truth object localization, tracking, and relation annotations as context improves VideoLLM answers, but the models never generate these steps themselves in the experiments.

Pith tools