Imagen de Portada

ERASE: Eliminating Redundant Visual Tokens via Adaptive Two-Stage Token Pruning

Fuente: arXiv

Guardado en:

Detalles Bibliográficos
Autores principales:	Lee, Yuna, Min, Kyoungho, Kim, Yulhwa
Formato:	Preprint
Publicado:	2026
Materias:	Computer Vision and Pattern Recognition
Acceso en línea:	Acceder al recurso
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

Ejemplares similares

Cached Adaptive Token Merging: Dynamic Token Reduction and Redundant Computation Elimination in Diffusion Model
por: Saghatchian, Omid, et al.
Publicado: (2025)

TrimTokenator: Towards Adaptive Visual Token Pruning for Large Multimodal Models
por: Zhang, Hao, et al.
Publicado: (2025)

ToDRE: Effective Visual Token Pruning via Token Diversity and Task Relevance
por: Li, Duo, et al.
Publicado: (2025)

TrimTokenator-LC: Towards Adaptive Visual Token Pruning for Large Multimodal Models with Long Contexts
por: Zhang, Hao, et al.
Publicado: (2025)

Prune Redundancy, Preserve Essence: Vision Token Compression in VLMs via Synergistic Importance-Diversity
por: Fang, Zhengyao, et al.
Publicado: (2026)

Efficient Video Sampling: Pruning Temporally Redundant Tokens for Faster VLM Inference
por: Bagrov, Natan, et al.
Publicado: (2025)

Why and When Visual Token Pruning Fails? A Study on Relevant Visual Information Shift in MLLMs Decoding
por: Kim, Jiwan, et al.
Publicado: (2026)

DocPrune:Efficient Document Question Answering via Background, Question, and Comprehension-aware Token Pruning
por: Choi, Joonmyung, et al.
Publicado: (2026)

Multi-Cue Adaptive Visual Token Pruning for Large Vision-Language Models
por: Luan, Bozhi, et al.
Publicado: (2025)

RedundancyLens: Revealing and Exploiting Visual Token Processing Redundancy for Efficient Decoder-Only MLLMs
por: Li, Hongliang, et al.
Publicado: (2025)

When Token Pruning is Worse than Random: Understanding Visual Token Information in VLLMs
por: Wang, Yahong, et al.
Publicado: (2025)

OTPrune: Distribution-Aligned Visual Token Pruning via Optimal Transport
por: Chen, Xiwen, et al.
Publicado: (2026)

TAMP: Token-Adaptive Layerwise Pruning in Multimodal Large Language Models
por: Lee, Jaewoo, et al.
Publicado: (2025)

Superpixel Tokenization for Vision Transformers: Preserving Semantic Integrity in Visual Tokens
por: Lew, Jaihyun, et al.
Publicado: (2024)

CROP: Contextual Region-Oriented Visual Token Pruning
por: Guo, Jiawei, et al.
Publicado: (2025)

ZOO-Prune: Training-Free Token Pruning via Zeroth-Order Gradient Estimation in Vision-Language Models
por: Kim, Youngeun, et al.
Publicado: (2025)

IVC-Prune: Revealing the Implicit Visual Coordinates in LVLMs for Vision Token Pruning
por: Sun, Zhichao, et al.
Publicado: (2026)

PruneVid: Visual Token Pruning for Efficient Video Large Language Models
por: Huang, Xiaohu, et al.
Publicado: (2024)

FastVAR: Linear Visual Autoregressive Modeling via Cached Token Pruning
por: Guo, Hang, et al.
Publicado: (2025)

PixelPrune: Pixel-Level Adaptive Visual Token Reduction via Predictive Coding
por: Wang, Nan, et al.
Publicado: (2026)

TimeChat-Online: 80% Visual Tokens are Naturally Redundant in Streaming Videos
por: Yao, Linli, et al.
Publicado: (2025)

IWP: Token Pruning as Implicit Weight Pruning in Large Vision Language Models
por: Lee, Dong-Jae, et al.
Publicado: (2026)

Faster Parameter-Efficient Tuning with Token Redundancy Reduction
por: Kim, Kwonyoung, et al.
Publicado: (2025)

GridPrune: From "Where to Look" to "What to Select" in Visual Token Pruning for MLLMs
por: Duan, Yuxiang, et al.
Publicado: (2025)

Training Noise Token Pruning
por: Rao, Mingxing, et al.
Publicado: (2024)

Energy-Driven Adaptive Visual Token Pruning for Efficient Vision-Language Models
por: He, Jialuo, et al.
Publicado: (2026)

EvoPrune: Early-Stage Visual Token Pruning for Efficient MLLMs
por: Chen, Yuhao, et al.
Publicado: (2026)

Efficient Vision-Language Reasoning via Adaptive Token Pruning
por: Li, Xue, et al.
Publicado: (2025)

RedVTP: Training-Free Acceleration of Diffusion Vision-Language Models Inference via Masked Token-Guided Visual Token Pruning
por: Xu, Jingqi, et al.
Publicado: (2025)

OccamToken: Efficient VLM Inference with Training-Free and Budget-Adaptive Token Pruning
por: Li, Geng, et al.
Publicado: (2026)

EntropyPrune: Matrix Entropy Guided Visual Token Pruning for Multimodal Large Language Models
por: Wang, Yahong, et al.
Publicado: (2026)

HAWK: Head Importance-Aware Visual Token Pruning in Multimodal Models
por: Zhu, Qihui, et al.
Publicado: (2026)

v1: Learning to Point Visual Tokens for Multimodal Grounded Reasoning
por: Chung, Jiwan, et al.
Publicado: (2025)

UTPTrack: Towards Simple and Unified Token Pruning for Visual Tracking
por: Wu, Hao, et al.
Publicado: (2026)

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)

Evading Visual Aphasia: Contrastive Adaptive Semantic Token Pruning for Vision-Language Models
por: Ma, Jie, et al.
Publicado: (2026)

Focus-Scan-Refine: From Human Visual Perception to Efficient Visual Token Pruning
por: Tong, Enwei, et al.
Publicado: (2026)

Soft Tail-dropping for Adaptive Visual Tokenization
por: Chen, Zeyuan, et al.
Publicado: (2026)

Reg4Pru: Regularisation Through Random Token Routing for Token Pruning
por: Wyatt, Julian, et al.
Publicado: (2026)

CATP: Contextually Adaptive Token Pruning for Efficient and Enhanced Multimodal In-Context Learning
por: Li, Yanshu, et al.
Publicado: (2025)