Imagen de Portada

Efficient Visual Transformer by Learnable Token Merging

Fuente: arXiv

Guardado en:

Detalles Bibliográficos
Autores principales:	Wang, Yancheng, Yang, Yingzhen
Formato:	Preprint
Publicado:	2024
Materias:	Computer Vision and Pattern Recognition Machine Learning
Acceso en línea:	Acceder al recurso
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

Ejemplares similares

Compact Vision Transformer by Reduction of Kernel Complexity
por: Wang, Yancheng, et al.
Publicado: (2025)

Learning Informative Attention Weights for Person Re-Identification
por: Wang, Yancheng, et al.
Publicado: (2025)

RNAS-CL: Robust Neural Architecture Search by Cross-Layer Knowledge Distillation
por: Nath, Utkarsh, et al.
Publicado: (2023)

Learning Low-Rank Feature for Thorax Disease Classification
por: Goel, Rajeev, et al.
Publicado: (2024)

CubistMerge: Spatial-Preserving Token Merging For Diverse ViT Backbones
por: Gong, Wenyi, et al.
Publicado: (2025)

Beyond Training: Dynamic Token Merging for Zero-Shot Video Understanding
por: Zhang, Yiming, et al.
Publicado: (2024)

Adaptive Token Merging for Efficient Transformer Semantic Communication at the Edge
por: Erak, Omar, et al.
Publicado: (2025)

TORE: Token Recycling in Vision Transformers for Efficient Active Visual Exploration
por: Olszewski, Jan, et al.
Publicado: (2023)

Segformer++: Efficient Token-Merging Strategies for High-Resolution Semantic Segmentation
por: Kienzle, Daniel, et al.
Publicado: (2024)

AdaMerging: Adaptive Model Merging for Multi-Task Learning
por: Yang, Enneng, et al.
Publicado: (2023)

StructSAM: Structure- and Spectrum-Preserving Token Merging for Segment Anything Models
por: Nguyen, Duy M. H., et al.
Publicado: (2026)

On the Role of Discrete Tokenization in Visual Representation Learning
por: Du, Tianqi, et al.
Publicado: (2024)

Subtractive Modulative Network with Learnable Periodic Activations
por: Wang, Tiou, et al.
Publicado: (2026)

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

Transformers with Joint Tokens and Local-Global Attention for Efficient Human Pose Estimation
por: Kinfu, Kaleab A., et al.
Publicado: (2025)

ToFe: Lagged Token Freezing and Reusing for Efficient Vision Transformer Inference
por: Zhang, Haoyue, et al.
Publicado: (2025)

BTC-LLM: Efficient Sub-1-Bit LLM Quantization via Learnable Transformation and Binary Codebook
por: Gu, Hao, et al.
Publicado: (2025)

Efficient Multi-Source Knowledge Transfer by Model Merging
por: Osial, Marcin, et al.
Publicado: (2025)

Uncertainty-Aware Token Importance Estimation in Spiking Transformers
por: Liu, Wenxuan, et al.
Publicado: (2026)

Introducing Visual Perception Token into Multimodal Large Language Model
por: Yu, Runpeng, et al.
Publicado: (2025)

Efficient and Effective Weight-Ensembling Mixture of Experts for Multi-Task Model Merging
por: Shen, Li, et al.
Publicado: (2024)

Stay Unique, Stay Efficient: Preserving Model Personality in Multi-Task Merging
por: Guo, Kuangpu, et al.
Publicado: (2025)

Token Caching for Diffusion Transformer Acceleration
por: Lou, Jinming, et al.
Publicado: (2024)

Unified Autoregressive Visual Generation and Understanding with Continuous Tokens
por: Fan, Lijie, et al.
Publicado: (2025)

On the Learnability of Out-of-distribution Detection
por: Fang, Zhen, et al.
Publicado: (2024)

Your Image is Secretly the Last Frame of a Pseudo Video
por: Chen, Wenlong, et al.
Publicado: (2024)

CodeMerge: Codebook-Guided Model Merging for Robust Test-Time Adaptation in Autonomous Driving
por: Yang, Huitong, et al.
Publicado: (2025)

Compressor-VLA: Instruction-Guided Visual Token Compression for Efficient Robotic Manipulation
por: Gao, Juntao, et al.
Publicado: (2025)

SPoT: Subpixel Placement of Tokens in Vision Transformers
por: Hjelkrem-Tan, Martine, et al.
Publicado: (2025)

DC-Merge: Improving Model Merging with Directional Consistency
por: Zhang, Han-Chen, et al.
Publicado: (2026)

Model Debiasing by Learnable Data Augmentation
por: Morerio, Pietro, et al.
Publicado: (2024)

MergeTok: Unified Continuous and Discrete Visual Tokenization via Token Merging
por: Zhang, Luyuan, et al.
Publicado: (2026)

D$^{3}$ToM: Decider-Guided Dynamic Token Merging for Accelerating Diffusion MLLMs
por: Chang, Shuochen, et al.
Publicado: (2025)

Merging and Disentangling Views in Visual Reinforcement Learning for Robotic Manipulation
por: Almuzairee, Abdulaziz, et al.
Publicado: (2025)

EMR-Merging: Tuning-Free High-Performance Model Merging
por: Huang, Chenyu, et al.
Publicado: (2024)

AdaPerceiver: Transformers with Adaptive Width, Depth, and Tokens
por: Jajal, Purvish, et al.
Publicado: (2025)

H$_{2}$OT: Hierarchical Hourglass Tokenizer for Efficient Video Pose Transformers
por: Li, Wenhao, et al.
Publicado: (2025)

Hourglass Tokenizer for Efficient Transformer-Based 3D Human Pose Estimation
por: Li, Wenhao, et al.
Publicado: (2023)

Token Turing Machines are Efficient Vision Models
por: Jajal, Purvish, et al.
Publicado: (2024)

PaCX-MAE: Physiology-Augmented Chest X-Ray Masked Autoencoder
por: Liu, Yancheng, et al.
Publicado: (2026)