paper-with-me

Papers

FocusLLaVA: A Coarse-to-Fine Approach for Efficient and Effective Visual Token Compression

2024-11-21 · Yuke Zhu, Chi Xie, Shuang Liang, Bo Zheng, Sheng Guo

Recent advances on Multi-modal Large Language Models have demonstrated that high-resolution image input is crucial for model capabilities, especially for fine-grained tasks. However, high-resolution images lead to a quadratic increase in the number of visual tokens input into LLMs, resulting in significant computational costs. Current work develop visual token compression methods to achieve efficiency improvements, often at the expense of performance. We argue that removing visual redundancy can simultaneously improve both efficiency and performance. We build a coarse-to-fine visual token compression method, with a vision-guided sampler for compressing redundant regions with low information density, and a text-guided sampler for selecting visual tokens that are strongly correlated with the user instructions.With these two modules, the proposed FocusLLaVA achieves improvements in both efficiency and performance. We validate the effectiveness of our approach on a wide range of evaluation datasets.

📄 PDF Abstract BibTeX arXiv:2411.14228

Code (0)

등록된 구현이 없습니다.

Tasks

Visual Question Answering

Similar Papers 제목 키워드 기반

Window Token Concatenation for Efficient Visual Large Language Models

2025-04-05 · YiFan Li, Wentao Bao, Botao Ye, Zhen Tan 외

To effectively reduce the visual tokens in Visual Large Language Models (VLLMs), we propose a novel approach called Window Token Concatenation (WiCo). Specifically, we employ a sliding window to concatenate spatially adj…

Token Reduction

MambaScope: Coarse-to-Fine Scoping for Efficient Vision Mamba

2025-11-29 · Shanhui Liu, Rui Xu, Yunke Wang arxiv

Vision Mamba has emerged as a promising and efficient alternative to Vision Transformers, yet its efficiency remains fundamentally constrained by the number of input tokens. Existing token reduction approaches typically …

TokenPacker: Efficient Visual Projector for Multimodal LLM

2024-07-02 · Wentong Li, Yuqian Yuan, Jian Liu, Dongqi Tang 외

The visual projector serves as an essential bridge between the visual encoder and the Large Language Model (LLM) in a Multimodal LLM (MLLM). Typically, MLLMs adopt a simple MLP to preserve all visual contexts via one-to-…

Language ModellingLarge Language ModelVisual Question AnsweringVisual Reasoning

SigLIP-HD by Fine-to-Coarse Supervision

2026-07-10 · Lihe Yang, Zhen Zhao, Hengshuang Zhao arxiv

High-quality visual representation is a long-standing pursuit in computer vision. In the context of multimodal LLMs (MLLMs), feeding higher-resolution images can produce more fine-grained visual tokens. However, it intro…

HiMTok: Learning Hierarchical Mask Tokens for Image Segmentation with Large Multimodal Model

2025-03-17 · Tao Wang, Changxu Cheng, Lingfeng Wang, Senda Chen 외

The remarkable performance of large multimodal models (LMMs) has attracted significant interest from the image segmentation community. To align with the next-token-prediction paradigm, current LMM-driven segmentation met…

Image SegmentationSegmentationSemantic SegmentationVisual Grounding