Imagen de Portada

Efficient Vision-Language Reasoning via Adaptive Token Pruning

Fuente: arXiv

Guardado en:

Detalles Bibliográficos
Autores principales:	Li, Xue, Song, Xiaonan, Hu, Henry
Formato:	Preprint
Publicado:	2025
Materias:	Computer Vision and Pattern Recognition Computation and Language Machine Learning
Acceso en línea:	Acceder al recurso
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

Ejemplares similares

AgilePruner: An Empirical Study of Attention and Diversity for Adaptive Visual Token Pruning in Large Vision-Language Models
por: Baek, Changwoo, et al.
Publicado: (2026)

Hierarchical Safety Realignment: Lightweight Restoration of Safety in Pruned Large Vision-Language Models
por: Li, Yue, et al.
Publicado: (2025)

Mostly Text, Smart Visuals: Asymmetric Text-Visual Pruning for Large Vision-Language Models
por: Li, Sijie, et al.
Publicado: (2026)

AdaptVision: Efficient Vision-Language Models via Adaptive Visual Acquisition
por: Lin, Zichuan, et al.
Publicado: (2025)

Prioritizing Image-Related Tokens Enhances Vision-Language Pre-Training
por: Chen, Yangyi, et al.
Publicado: (2025)

TLDR: Token-Level Detective Reward Model for Large Vision Language Models
por: Fu, Deqing, et al.
Publicado: (2024)

ECoFLaP: Efficient Coarse-to-Fine Layer-Wise Pruning for Vision-Language Models
por: Sung, Yi-Lin, et al.
Publicado: (2023)

Zebra-CoT: A Dataset for Interleaved Vision Language Reasoning
por: Li, Ang, et al.
Publicado: (2025)

Sherlock: Self-Correcting Reasoning in Vision-Language Models
por: Ding, Yi, et al.
Publicado: (2025)

TopViewRS: Vision-Language Models as Top-View Spatial Reasoners
por: Li, Chengzu, et al.
Publicado: (2024)

Measuring and Improving Chain-of-Thought Reasoning in Vision-Language Models
por: Chen, Yangyi, et al.
Publicado: (2023)

VisionThink: Smart and Efficient Vision Language Model via Reinforcement Learning
por: Yang, Senqiao, et al.
Publicado: (2025)

Vision-Language Models Can Self-Improve Reasoning via Reflection
por: Cheng, Kanzhi, et al.
Publicado: (2024)

MANZANO: A Simple and Scalable Unified Multimodal Model with a Hybrid Vision Tokenizer
por: Li, Yanghao, et al.
Publicado: (2025)

A Survey on Hallucination in Large Vision-Language Models
por: Liu, Hanchao, et al.
Publicado: (2024)

Towards Grounded Visual Spatial Reasoning in Multi-Modal Vision Language Models
por: Rajabi, Navid, et al.
Publicado: (2023)

Progressive Multi-granular Alignments for Grounded Reasoning in Large Vision-Language Models
por: Le, Quang-Hung, et al.
Publicado: (2024)

Fast-Slow Efficient Training for Multimodal Large Language Models via Visual Token Pruning
por: Zhang, Dingkun, et al.
Publicado: (2026)

Learning Self-Correction in Vision-Language Models via Rollout Augmentation
por: Ding, Yi, et al.
Publicado: (2026)

VLA-Cache: Efficient Vision-Language-Action Manipulation via Adaptive Token Caching
por: Xu, Siyu, et al.
Publicado: (2025)

Multimodal Latent Language Modeling with Next-Token Diffusion
por: Sun, Yutao, et al.
Publicado: (2024)

Matryoshka Query Transformer for Large Vision-Language Models
por: Hu, Wenbo, et al.
Publicado: (2024)

Memory-Space Visual Prompting for Efficient Vision-Language Fine-Tuning
por: Jie, Shibo, et al.
Publicado: (2024)

S-GRPO: Unified Post-Training for Large Vision-Language Models
por: Yan, Yuming, et al.
Publicado: (2026)

How Vision-Language Tasks Benefit from Large Pre-trained Models: A Survey
por: Qi, Yayun, et al.
Publicado: (2024)

Towards Efficient Vision-Language Tuning: More Information Density, More Generalizability
por: Hao, Tianxiang, et al.
Publicado: (2023)

FlashVID: Efficient Video Large Language Models via Training-free Tree-based Spatiotemporal Token Merging
por: Fan, Ziyang, et al.
Publicado: (2026)

A General and Efficient Training for Transformer via Token Expansion
por: Huang, Wenxuan, et al.
Publicado: (2024)

Towards Efficient Large Vision-Language Models: A Comprehensive Survey on Inference Strategies
por: Pathak, Surendra, et al.
Publicado: (2026)

SpatialVLM: Endowing Vision-Language Models with Spatial Reasoning Capabilities
por: Chen, Boyuan, et al.
Publicado: (2024)

Efficient Pruning of Text-to-Image Models: Insights from Pruning Stable Diffusion
por: Ramesh, Samarth N, et al.
Publicado: (2024)

The Neglected Tails in Vision-Language Models
por: Parashar, Shubham, et al.
Publicado: (2024)

DRESS: Instructing Large Vision-Language Models to Align and Interact with Humans via Natural Language Feedback
por: Chen, Yangyi, et al.
Publicado: (2023)

Vision-Language Model Fine-Tuning via Simple Parameter-Efficient Modification
por: Li, Ming, et al.
Publicado: (2024)

The Better You Learn, The Smarter You Prune: Towards Efficient Vision-language-action Models via Differentiable Token Pruning
por: Jiang, Titong, et al.
Publicado: (2025)

Aligning Modalities in Vision Large Language Models via Preference Fine-tuning
por: Zhou, Yiyang, et al.
Publicado: (2024)

Enhancing Vision-Language Model Pre-training with Image-text Pair Pruning Based on Word Frequency
por: Liang, Mingliang, et al.
Publicado: (2024)

Fine-Grained Alignment in Vision-and-Language Navigation through Bayesian Optimization
por: Song, Yuhang, et al.
Publicado: (2024)

Vision-R1: Incentivizing Reasoning Capability in Multimodal Large Language Models
por: Huang, Wenxuan, et al.
Publicado: (2025)

Dynamic-LLaVA: Efficient Multimodal Large Language Models via Dynamic Vision-language Context Sparsification
por: Huang, Wenxuan, et al.
Publicado: (2024)