Image de couverture de livre

An Image is Worth 1/2 Tokens After Layer 2: Plug-and-Play Inference Acceleration for Large Vision-Language Models

Fuente: arXiv

Enregistré dans:

Détails bibliographiques
Auteurs principaux:	Chen, Liang, Zhao, Haozhe, Liu, Tianyu, Bai, Shuai, Lin, Junyang, Zhou, Chang, Chang, Baobao
Format:	Preprint
Publié:	2024
Sujets:	Computer Vision and Pattern Recognition Artificial Intelligence Computation and Language
Accès en ligne:	Acceder al recurso
Tags:	Ajouter un tag Pas de tags, Soyez le premier à ajouter un tag!

Documents similaires

A Spark of Vision-Language Intelligence: 2-Dimensional Autoregressive Transformer for Efficient Finegrained Image Generation
par: Chen, Liang, et autres
Publié: (2024)

Multimodal Representation Alignment for Image Generation: Text-Image Interleaved Control Is Easier Than You Think
par: Chen, Liang, et autres
Publié: (2025)

Looking Beyond Text: Reducing Language bias in Large Vision-Language Models via Multimodal Dual-Attention and Soft-Image Guidance
par: Zhao, Haozhe, et autres
Publié: (2024)

VLCache: Computing 2% Vision Tokens and Reusing 98% for Vision-Language Inference
par: Qin, Shengling, et autres
Publié: (2025)

Turbo: Informativity-Driven Acceleration Plug-In for Vision-Language Large Models
par: Ju, Chen, et autres
Publié: (2024)

Global Compression Commander: Plug-and-Play Inference Acceleration for High-Resolution Large Vision-Language Models
par: Liu, Xuyang, et autres
Publié: (2025)

Vote&Mix: Plug-and-Play Token Reduction for Efficient Vision Transformer
par: Peng, Shuai, et autres
Publié: (2024)

PCA-Bench: Evaluating Multimodal Large Language Models in Perception-Cognition-Action Chain
par: Chen, Liang, et autres
Publié: (2024)

Rethinking Semantic Parsing for Large Language Models: Enhancing LLM Performance with Semantic Hints
par: An, Kaikai, et autres
Publié: (2024)

Video Compression Commander: Plug-and-Play Inference Acceleration for Video Large Language Models
par: Liu, Xuyang, et autres
Publié: (2025)

Mitigating Language-Level Performance Disparity in mPLMs via Teacher Language Selection and Cross-lingual Self-Distillation
par: Zhao, Haozhe, et autres
Publié: (2024)

Revisiting Multimodal Positional Encoding in Vision-Language Models
par: Huang, Jie, et autres
Publié: (2025)

Prune2Drive: A Plug-and-Play Framework for Accelerating Vision-Language Models in Autonomous Driving
par: Xiong, Minhao, et autres
Publié: (2025)

G1: Bootstrapping Perception and Reasoning Abilities of Vision-Language Model via Reinforcement Learning
par: Chen, Liang, et autres
Publié: (2025)

Plug-and-Play Grounding of Reasoning in Multimodal Large Language Models
par: Chen, Jiaxing, et autres
Publié: (2024)

LLM-KT: Aligning Large Language Models with Knowledge Tracing using a Plug-and-Play Instruction
par: Wang, Ziwei, et autres
Publié: (2025)

MMICL: Empowering Vision-language Model with Multi-Modal In-Context Learning
par: Zhao, Haozhe, et autres
Publié: (2023)

V2Flow: Unifying Visual Tokenization and Large Language Model Vocabularies for Autoregressive Image Generation
par: Zhang, Guiwei, et autres
Publié: (2025)

Can Large Language Models Always Solve Easy Problems if They Can Solve Harder Ones?
par: Yang, Zhe, et autres
Publié: (2024)

Score-Based Turbo Message Passing for Plug-and-Play Compressive Imaging
par: Cai, Chang, et autres
Publié: (2025)

DynaMo: Accelerating Language Model Inference with Dynamic Multi-Token Sampling
par: Tuli, Shikhar, et autres
Publié: (2024)

An Image is Worth 32 Tokens for Reconstruction and Generation
par: Yu, Qihang, et autres
Publié: (2024)

Variator: Accelerating Pre-trained Models with Plug-and-Play Compression Modules
par: Xiao, Chaojun, et autres
Publié: (2023)

Memory Decoder: A Pretrained, Plug-and-Play Memory for Large Language Models
par: Cao, Jiaqi, et autres
Publié: (2025)

Aligning Large Language Models to Follow Instructions and Hallucinate Less via Effective Data Filtering
par: Si, Shuzheng, et autres
Publié: (2025)

UltraEdit: Instruction-based Fine-Grained Image Editing at Scale
par: Zhao, Haozhe, et autres
Publié: (2024)

Qwen2-VL: Enhancing Vision-Language Model's Perception of the World at Any Resolution
par: Wang, Peng, et autres
Publié: (2024)

Score-Based Turbo Message Passing for Plug-and-Play Compressive Image Recovery
par: Cai, Chang, et autres
Publié: (2025)

Interactive Text-to-Image Retrieval with Large Language Models: A Plug-and-Play Approach
par: Lee, Saehyung, et autres
Publié: (2024)

Improving the Robustness of Distantly-Supervised Named Entity Recognition via Uncertainty-Aware Teacher Learning and Student-Student Collaborative Learning
par: Si, Shuzheng, et autres
Publié: (2023)

Accelerating Inference in Large Language Models with a Unified Layer Skipping Strategy
par: Liu, Yijin, et autres
Publié: (2024)

Text-to-Image Rectified Flow as Plug-and-Play Priors
par: Yang, Xiaofeng, et autres
Publié: (2024)

Accelerating Multimodal Large Language Models by Searching Optimal Vision Token Reduction
par: Zhao, Shiyu, et autres
Publié: (2024)

S2MDF: A Plug-And-Play Layer for Intersection-Free Multi-Object Signed Distance Fields
par: Mercadier, Deniz Sayin, et autres
Publié: (2026)

Next Token Prediction Towards Multimodal Intelligence: A Comprehensive Survey
par: Chen, Liang, et autres
Publié: (2024)

Predicting Rewards Alongside Tokens: Non-disruptive Parameter Insertion for Efficient Inference Intervention in Large Language Model
par: Yuan, Chenhan, et autres
Publié: (2024)

Self-Checker: Plug-and-Play Modules for Fact-Checking with Large Language Models
par: Li, Miaoran, et autres
Publié: (2023)

FasterVAR: Plug-and-Play Acceleration for Visual Autoregressive Models
par: Li, Senmao, et autres
Publié: (2025)

Enhanced Motion Forecasting with Plug-and-Play Multimodal Large Language Models
par: Luo, Katie, et autres
Publié: (2025)

Diffusion Sampling Path Tells More: An Efficient Plug-and-Play Strategy for Sample Filtering
par: Wang, Sixian, et autres
Publié: (2025)