Image de couverture de livre

Vision-centric Token Compression in Large Language Model

Fuente: arXiv

Enregistré dans:

Détails bibliographiques
Auteurs principaux:	Xing, Ling, Wang, Alex Jinpeng, Yan, Rui, Shu, Xiangbo, Tang, Jinhui
Format:	Preprint
Publié:	2025
Sujets:	Computation and Language Computer Vision and Pattern Recognition
Accès en ligne:	Acceder al recurso
Tags:	Ajouter un tag Pas de tags, Soyez le premier à ajouter un tag!

Documents similaires

See the Text: From Tokenization to Visual Reading
par: Xing, Ling, et autres
Publié: (2025)

Locality-aware Cross-modal Correspondence Learning for Dense Audio-Visual Events Localization
par: Xing, Ling, et autres
Publié: (2024)

TLDR: Token-Level Detective Reward Model for Large Vision Language Models
par: Fu, Deqing, et autres
Publié: (2024)

FedMLLM: Federated Fine-tuning MLLM on Multimodal Heterogeneity Data
par: Xu, Binqian, et autres
Publié: (2024)

InfoMerge: Information-aware Token Compression for Efficient Video Large Language Models
par: Liu, Xinxin, et autres
Publié: (2026)

Vision Token Reduction via Attention-Driven Self-Compression for Efficient Multimodal Large Language Models
par: Deniz, Omer Faruk, et autres
Publié: (2026)

VScan: Rethinking Visual Token Reduction for Efficient Large Vision-Language Models
par: Zhang, Ce, et autres
Publié: (2025)

From Pixels to Tokens: Revisiting Object Hallucinations in Large Vision-Language Models
par: Shang, Yuying, et autres
Publié: (2024)

Spatio-temporal Decoupled Knowledge Compensator for Few-Shot Action Recognition
par: Qu, Hongyu, et autres
Publié: (2026)

Dynamic Token Reweighting for Robust Vision-Language Models
par: Jiang, Tanqiu, et autres
Publié: (2025)

PAINT: Paying Attention to INformed Tokens to Mitigate Hallucination in Large Vision-Language Model
par: Arif, Kazi Hasan Ibn, et autres
Publié: (2025)

Hybrid-Level Instruction Injection for Video Token Compression in Multi-modal Large Language Models
par: Liu, Zhihang, et autres
Publié: (2025)

Spatiotemporal-Untrammelled Mixture of Experts for Multi-Person Motion Prediction
par: Yin, Zheng, et autres
Publié: (2025)

EventCrab: Harnessing Frame and Point Synergy for Event-based Action Recognition and Beyond
par: Cao, Meiqi, et autres
Publié: (2024)

CoViPAL: Layer-wise Contextualized Visual Token Pruning for Large Vision-Language Models
par: Tang, Zicong, et autres
Publié: (2025)

The First to Know: How Token Distributions Reveal Hidden Knowledge in Large Vision-Language Models?
par: Zhao, Qinyu, et autres
Publié: (2024)

PUMGPT: A Large Vision-Language Model for Product Understanding
par: Xue, Wei, et autres
Publié: (2023)

Language-Guided Token Compression with Reinforcement Learning in Large Vision-Language Models
par: Cao, Sihan, et autres
Publié: (2026)

Diving into Mitigating Hallucinations from a Vision Perspective for Large Vision-Language Models
par: Wang, Weihang, et autres
Publié: (2025)

Learning Compact Vision Tokens for Efficient Large Multimodal Models
par: Tang, Hao, et autres
Publié: (2025)

IdealGPT: Iteratively Decomposing Vision and Language Reasoning via Large Language Models
par: You, Haoxuan, et autres
Publié: (2023)

NPHardEval4V: Dynamic Evaluation of Large Vision-Language Models with Effects of Vision
par: Li, Xiang, et autres
Publié: (2024)

FTMoMamba: Motion Generation with Frequency and Text State Space Models
par: Li, Chengjian, et autres
Publié: (2024)

LVLM-Compress-Bench: Benchmarking the Broader Impact of Large Vision-Language Model Compression
par: Kundu, Souvik, et autres
Publié: (2025)

No Tokens Wasted: Leveraging Long Context in Biomedical Vision-Language Models
par: Sun, Min Woo, et autres
Publié: (2025)

Text-Printed Image: Bridging the Image-Text Modality Gap for Text-centric Training of Large Vision-Language Models
par: Yamabe, Shojiro, et autres
Publié: (2025)

HyperGVL: Benchmarking and Improving Large Vision-Language Models in Hypergraph Understanding and Reasoning
par: Wei, Yanbin, et autres
Publié: (2026)

On Epistemic Uncertainty of Visual Tokens for Object Hallucinations in Large Vision-Language Models
par: Seo, Hoigi, et autres
Publié: (2025)

A Survey of Multimodal Large Language Model from A Data-centric Perspective
par: Bai, Tianyi, et autres
Publié: (2024)

MuDPT: Multi-modal Deep-symphysis Prompt Tuning for Large Pre-trained Vision-Language Models
par: Miao, Yongzhu, et autres
Publié: (2023)

Visual In-Context Learning for Large Vision-Language Models
par: Zhou, Yucheng, et autres
Publié: (2024)

AlignMMBench: Evaluating Chinese Multimodal Alignment in Large Vision-Language Models
par: Wu, Yuhang, et autres
Publié: (2024)

ASTRA: Let Arbitrary Subjects Transform in Video Editing
par: Shen, Fei, et autres
Publié: (2025)

Large Vision-Language Model Alignment and Misalignment: A Survey Through the Lens of Explainability
par: Shu, Dong, et autres
Publié: (2025)

Where do Large Vision-Language Models Look at when Answering Questions?
par: Xing, Xiaoying, et autres
Publié: (2025)

V-MAGE: A Game Evaluation Framework for Assessing Vision-Centric Capabilities in Multimodal Large Language Models
par: Zheng, Xiangxi, et autres
Publié: (2025)

Can Large Vision-Language Models Understand Multimodal Sarcasm?
par: Wang, Xinyu, et autres
Publié: (2025)

S-GRPO: Unified Post-Training for Large Vision-Language Models
par: Yan, Yuming, et autres
Publié: (2026)

CrossGET: Cross-Guided Ensemble of Tokens for Accelerating Vision-Language Transformers
par: Shi, Dachuan, et autres
Publié: (2023)

ViSpec: Accelerating Vision-Language Models with Vision-Aware Speculative Decoding
par: Kang, Jialiang, et autres
Publié: (2025)