Pith. sign in

REVIEW 4 cited by

Rethinking Visual Dependency in Long-Context Reasoning for Large Vision-Language Models

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 2410.19732 v2 pith:VTKHOGO3 submitted 2024-10-25 cs.CL cs.CV

Yucheng Zhou , Zhi Rao , Jun Wan , Jianbing Shen This is my paper
classification cs.CLcs.CV
keywords long-contextdependencyreasoningvisualcontextlvlmspruningtextual
verification ladder T0 review T1 audit T2 compute T3 formal
0 comments
read the original abstract

Large Vision-Language Models (LVLMs) excel in cross-model tasks but experience performance declines in long-context reasoning due to overreliance on textual information and reduced visual dependency. In this study, we empirically analyze LVLMs in long-context reasoning, revealing that increased context length leads to a higher dependence on language at the expense of visual dependency. To address this issue, we propose a novel training-free context pruning method that selectively removes less critical textual information. Our approach enhances visual dependency and reduces textual noise, thereby improving LVLM performance in long-context reasoning. We validate our method by constructing a long-context dataset, demonstrating its effectiveness across various LVLMs. Moreover, further analysis confirms the robustness of different token pruning strategies and preliminary explores scaling laws between pruning rates and context length.

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. AuroraLong: Bringing RNNs Back to Efficient Open-Ended Video Understanding

    cs.CV 2025-07 conditional novelty 6.0 of 10

    A 2B-parameter video-language model using an RWKV linear-RNN backbone and sorted token merging achieves competitive long-video QA accuracy with far lower memory cost than transformer-based models.

  2. Harnessing RLHF for Robust Unanswerability Recognition and Trustworthy Response Generation in LLMs

    cs.CL 2025-07 reject novelty 4.0 of 10

    SALU, a multi-task fine-tuning and confidence-guided RLHF method, reduces hallucinated answers on unanswerable Chinese CIR questions to 1.3 percent on the authors' private dataset.

  3. VisuCraft: Enhancing Large Vision-Language Models for Complex Visual-Guided Creative Content Generation via Structured Information Extraction

    cs.CV 2025-08 reject novelty 3.0 of 10

    A prompt-wrapper framework for vision-language models reports improved story and poetry generation on a private benchmark, without releasing code, data, or models.

  4. Revolutionizing Radiology Workflow with Factual and Efficient CXR Report Generation

    cs.CV 2025-06 reject novelty 2.0 of 10

    CXR-PathFinder claims to outperform much larger medical vision-language models on chest X-ray reporting, using adversarial fine-tuning with clinician feedback and knowledge graph verification, but the evidence is not ...

Pith tools