Cover Image

Filter, Correlate, Compress: Training-Free Token Reduction for MLLM Acceleration

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Han, Yuhang, Liu, Xuyang, Zhang, Zihan, Ding, Pengxiang, Chen, Junjie, Wang, Donglin, Chen, Honggang, Yan, Qingsen, Huang, Siteng
Format:	Preprint
Published:	2024
Subjects:	Computer Vision and Pattern Recognition
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

Global Compression Commander: Plug-and-Play Inference Acceleration for High-Resolution Large Vision-Language Models
by: Liu, Xuyang, et al.
Published: (2025)

Variation-aware Vision Token Dropping for Faster Large Vision-Language Models
by: Chen, Junjie, et al.
Published: (2025)

VGDiffZero: Text-to-image Diffusion Models Can Be Zero-shot Visual Grounders
by: Liu, Xuyang, et al.
Published: (2023)

VisionTrim: Unified Vision Token Compression for Training-Free MLLM Acceleration
by: Yu, Hanxun, et al.
Published: (2026)

PiTe: Pixel-Temporal Alignment for Large Video-Language Model
by: Liu, Yang, et al.
Published: (2024)

Cobra: Extending Mamba to Multi-Modal Large Language Model for Efficient Inference
by: Zhao, Han, et al.
Published: (2024)

DARA: Domain- and Relation-aware Adapters Make Parameter-efficient Tuning for Visual Grounding
by: Liu, Ting, et al.
Published: (2024)

Accelerating Diffusion Transformers with Token-wise Feature Caching
by: Zou, Chang, et al.
Published: (2024)

ProFD: Prompt-Guided Feature Disentangling for Occluded Person Re-Identification
by: Cui, Can, et al.
Published: (2024)

M2IST: Multi-Modal Interactive Side-Tuning for Efficient Referring Expression Comprehension
by: Liu, Xuyang, et al.
Published: (2024)

SSR: Enhancing Depth Perception in Vision-Language Models via Rationale-Guided Spatial Reasoning
by: Liu, Yang, et al.
Published: (2025)

QUAR-VLA: Vision-Language-Action Model for Quadruped Robots
by: Ding, Pengxiang, et al.
Published: (2023)

CARP: Visuomotor Policy Learning via Coarse-to-Fine Autoregressive Prediction
by: Gong, Zhefei, et al.
Published: (2024)

Token Transforming: A Unified and Training-Free Token Compression Framework for Vision Transformer Acceleration
by: Zeng, Fanhu, et al.
Published: (2025)

QUART-Online: Latency-Free Large Multimodal Language Model for Quadruped Robot Learning
by: Tong, Xinyang, et al.
Published: (2024)

IPCV: Information-Preserving Compression for MLLM Visual Encoders
by: Chen, Yuan, et al.
Published: (2025)

Accelerating Streaming Video Large Language Models via Hierarchical Token Compression
by: Wang, Yiyu, et al.
Published: (2025)

Semantic-Geometric Dual Compression: Training-Free Visual Token Reduction for Ultra-High-Resolution Remote Sensing Understanding
by: Li, Yueying, et al.
Published: (2026)

STaR-KV: Spatio-Temporal Adaptive Re-weighting for KV Cache Compression in GUI Vision-Language Models
by: Han, Yuhang, et al.
Published: (2026)

Fast-dVLA: Accelerating Discrete Diffusion VLA to Real-Time Performance
by: Song, Wenxuan, et al.
Published: (2026)

TRIO: Token Reduction via Inference-Objective Guidance for Efficient Vision-Language Models
by: Zhang, Haokui, et al.
Published: (2026)

Rethinking Target Label Conditioning in Adversarial Attacks: A 2D Tensor-Guided Generative Approach
by: Liu, Hangyu, et al.
Published: (2025)

TAP: A Token-Adaptive Predictor Framework for Training-Free Diffusion Acceleration
by: Zhu, Haowei, et al.
Published: (2026)

Focus-Consistent Multi-Level Aggregation for Compositional Zero-Shot Learning
by: Dai, Fengyuan, et al.
Published: (2024)

Exploring the Evolution of Physics Cognition in Video Generation: A Survey
by: Lin, Minghui, et al.
Published: (2025)

Sparse-Tuning: Adapting Vision Transformers with Efficient Fine-tuning and Inference
by: Liu, Ting, et al.
Published: (2024)

Prompt-based Distribution Alignment for Unsupervised Domain Adaptation
by: Bai, Shuanghao, et al.
Published: (2023)

Learning Disentangled Identifiers for Action-Customized Text-to-Image Generation
by: Huang, Siteng, et al.
Published: (2023)

Beyond Filtering: Adaptive Image-Text Quality Enhancement for MLLM Pretraining
by: Huang, Han, et al.
Published: (2024)

Training-free Token Reduction for Vision Mamba
by: Ma, Qiankun, et al.
Published: (2025)

D2Pruner: Debiased Importance and Structural Diversity for MLLM Token Pruning
by: Zhang, Evelyn, et al.
Published: (2025)

Enhancing Adversarial Transferability via Component-Wise Transformation
by: Liu, Hangyu, et al.
Published: (2025)

Check, Locate, Rectify: A Training-Free Layout Calibration System for Text-to-Image Generation
by: Gong, Biao, et al.
Published: (2023)

Flash-Unified: A Training-Free and Task-Aware Acceleration Framework for Native Unified Models
by: Ke, Junlong, et al.
Published: (2026)

CG-MLLM: Captioning and Generating 3D content via Multi-modal Large Language Models
by: Huang, Junming, et al.
Published: (2026)

FreeVA: Offline MLLM as Training-Free Video Assistant
by: Wu, Wenhao
Published: (2024)

Token-level Correlation-guided Compression for Efficient Multimodal Document Understanding
by: Zhang, Renshan, et al.
Published: (2024)

Revisiting MLLM Token Technology through the Lens of Classical Visual Coding
by: Liu, Jinming, et al.
Published: (2025)

OpenHelix: A Short Survey, Empirical Analysis, and Open-Source Dual-System VLA Model for Robotic Manipulation
by: Cui, Can, et al.
Published: (2025)

ReconVLA: Reconstructive Vision-Language-Action Model as Effective Robot Perceiver
by: Song, Wenxuan, et al.
Published: (2025)