CORTEXA
← Browse
arxivcs.CV2026-07-15

CRISP: Pre-LLM Yet Text-Driven Visual Token Pruning for Efficient LVLM Inference

Xu Li, Yi Zheng, Mengyang Zhao, Yuxuan Liang, Zhe Liu, Rui Zhu, Xiaolei Chen, Wei Zhou, Baoquan Zhao, Juncen Guo

Large Vision-Language Models (LVLMs) typically require processing hundreds to thousands of visual tokens, leading to substantial inference overhead. Existing visual token pruning methods either operate before the LLM using text-agnostic heuristics or prune inside the LLM at the cost of efficiency and noisy cross-modal attention. To address these limitations, we propose CRISP, a pre-LLM yet text-driven visual token pruning framework that preserves both instruction-relevant evidence and essential scene context. CRISP works in a two-stage pipeline: Stage 1 first identifies text-aligned visual tokens, and Stage 2 enhances contextual completeness through semantic diversity. Extensive experiments on LLaVA-1.5 and LLaVA-NeXT demonstrate that CRISP achieves superior performance retention under aggressive pruning ratios, maintaining up to 99.5% accuracy while reducing inference cost and latency by more than 2 times. CRISP serves as a practical solution for efficient LVLM inference, especially in resource-constrained scenarios.

View free PDFSource page

Related papers

arxivcs.CVcs.AI2026-06-30

Attend, Transform, or Silence: Operator-Level Visual Skipping for Efficient Multimodal LLM Inference

Zhaoyang Luo, Runmin Dong, Miao Yang, Fan Wei, Yushan Lai, Bin Luo, et al.

Multimodal large language models (MLLMs) increasingly process long visual-token sequences, increasing the overall inference computation. Existing acceleration methods usually remove visual tokens or skip visual-token updates in entire layers, but these coarse strategies may disca…

View free PDFSource page
arxivcs.CV2026-07-17

Are All Tokens Necessary for Visual Place Recognition? An Empirical Study of Token Reduction for Efficient Inference

Tong Jin, Yunpeng Liu, Shuyu Hu, Qinghua Zhang, Ruize Han, Song Wang, et al.

Recent visual place recognition (VPR) methods based on vision transformers, particularly foundation models, have achieved remarkable recognition performance. However, these models process all visual tokens throughout the entire network, resulting in substantial computational over…

View free PDFSource page
arxivcs.CV2026-06-30

ERA: Entropy-Guided Visual Token Pruning with Rectified Attention for Efficient MLLMs

Yuhao Wang, Mu Qiao, Haiwen Diao, Yunzhi Zhuge, Pingping Zhang, Xindong Zhang, et al.

Multimodal Large Language Models (MLLMs) incur prohibitive inference costs due to long visual token sequences. Training-free visual token reduction provides an efficient solution. However, existing methods distort attention distributions, giving rise to a phenomenon we term Atten…

View free PDFSource page
arxivcs.CV2026-07-15

T3HG-Editor: Text-driven 3D Human Garment Editing with Body Priors Embedded in SMPL-X

Shaoru Sun, Xingtao Wang, Zihan Ma, Wenrui Li, Jiantao Zhou, Debin Zhao, et al.

While 3D Gaussian Editing (3DGE) has seen substantial progress, text-driven 3D human garment editing remains largely underexplored. Existing 3DGE works typically follow a paradigm that applies 2D editing techniques to multi-view rendered images and updates 3D Gaussians based on t…

View free PDFSource page