Copertina

Multi-criteria Token Fusion with One-step-ahead Attention for Efficient Vision Transformers

Fuente: arXiv

Salvato in:

Dettagli Bibliografici
Autori principali:	Lee, Sanghyeok, Choi, Joonmyung, Kim, Hyunwoo J.
Natura:	Preprint
Pubblicazione:	2024
Soggetti:	Computer Vision and Pattern Recognition
Accesso online:	Acceder al recurso
Tags:	Aggiungi Tag Nessun Tag, puoi essere il primo ad aggiungerne!!

Documenti analoghi

EfficientViM: Efficient Vision Mamba with Hidden State Mixer based State Space Duality
di: Lee, Sanghyeok, et al.
Pubblicazione: (2024)

vid-TLDR: Training Free Token merging for Light-weight Video Transformer
di: Choi, Joonmyung, et al.
Pubblicazione: (2024)

Representation Shift: Unifying Token Compression with FlashAttention
di: Choi, Joonmyung, et al.
Pubblicazione: (2025)

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

TabFlash: Efficient Table Understanding with Progressive Question Conditioning and Token Focusing
di: Kim, Jongha, et al.
Pubblicazione: (2025)

Transferable Model-agnostic Vision-Language Model Adaptation for Efficient Weak-to-Strong Generalization
di: Park, Jihwan, et al.
Pubblicazione: (2025)

MoE-GRPO: Optimizing Mixture-of-Experts via Reinforcement Learning in Vision-Language Models
di: Ko, Dohwan, et al.
Pubblicazione: (2026)

ToSA: Token Selective Attention for Efficient Vision Transformers
di: Singh, Manish Kumar, et al.
Pubblicazione: (2024)

Frequency-Aware Token Reduction for Efficient Vision Transformer
di: Lee, Dong-Jae, et al.
Pubblicazione: (2025)

Robust Multimodal 3D Object Detection via Modality-Agnostic Decoding and Proximity-based Modality Ensemble
di: Cha, Juhan, et al.
Pubblicazione: (2024)

Efficient multi-view training for 3D Gaussian Splatting
di: Choi, Minhyuk, et al.
Pubblicazione: (2025)

Lossless Token Merging Even Without Fine-Tuning in Vision Transformers
di: Lee, Jaeyeon, et al.
Pubblicazione: (2025)

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

Sprint: Sparse-Dense Residual Fusion for Efficient Diffusion Transformers
di: Park, Dogyun, et al.
Pubblicazione: (2025)

Probabilistic Vision-Language Representation for Weakly Supervised Temporal Action Localization
di: Lim, Geuntaek, et al.
Pubblicazione: (2024)

MVFormer: Diversifying Feature Normalization and Token Mixing for Efficient Vision Transformers
di: Bae, Jongseong, et al.
Pubblicazione: (2024)

HEART-VIT: Hessian-Guided Efficient Dynamic Attention and Token Pruning in Vision Transformer
di: Uddin, Mohammad Helal, et al.
Pubblicazione: (2025)

TCSAFormer: Efficient Vision Transformer with Token Compression and Sparse Attention for Medical Image Segmentation
di: Xia, Zunhui, et al.
Pubblicazione: (2025)

Retinal Layer Segmentation in OCT Images With 2.5D Cross-slice Feature Fusion Module for Glaucoma Assessment
di: Kim, Hyunwoo, et al.
Pubblicazione: (2026)

ReCo: Reminder Composition Mitigates Hallucinations in Vision-Language Models
di: Chytas, Sotirios Panagiotis, et al.
Pubblicazione: (2025)

BinaryAttention: One-Bit QK-Attention for Vision and Diffusion Transformers
di: Xiao, Chaodong, et al.
Pubblicazione: (2026)

Speed-up of Vision Transformer Models by Attention-aware Token Filtering
di: Naruko, Takahiro, et al.
Pubblicazione: (2025)

PPT: Token Pruning and Pooling for Efficient Vision Transformers
di: Wu, Xinjian, et al.
Pubblicazione: (2023)

Multi-manifold Attention for Vision Transformers
di: Konstantinidis, Dimitrios, et al.
Pubblicazione: (2022)

Bidirectional Likelihood Estimation with Multi-Modal Large Language Models for Text-Video Retrieval
di: Ko, Dohwan, et al.
Pubblicazione: (2025)

Cross-aware Early Fusion with Stage-divided Vision and Language Transformer Encoders for Referring Image Segmentation
di: Cho, Yubin, et al.
Pubblicazione: (2024)

Self-Supervised Multi-Scale Transformer with Attention-Guided Fusion for Efficient Crack Detection
di: Kyem, Blessing Agyei, et al.
Pubblicazione: (2025)

GeminiFusion: Efficient Pixel-wise Multimodal Fusion for Vision Transformer
di: Jia, Ding, et al.
Pubblicazione: (2024)

Groupwise Query Specialization and Quality-Aware Multi-Assignment for Transformer-based Visual Relationship Detection
di: Kim, Jongha, et al.
Pubblicazione: (2024)

Learning to Merge Tokens via Decoupled Embedding for Efficient Vision Transformers
di: Lee, Dong Hoon, et al.
Pubblicazione: (2024)

Token-Space Mask Prediction for Efficient Vision Transformer Segmentation
di: Galagain, Calvin, et al.
Pubblicazione: (2026)

MSVIT: Improving Spiking Vision Transformer Using Multi-scale Attention Fusion
di: Hua, Wei, et al.
Pubblicazione: (2025)

Blockwise Flow Matching: Improving Flow Matching Models For Efficient High-Quality Generation
di: Park, Dogyun, et al.
Pubblicazione: (2025)

HiPrune: Hierarchical Attention for Efficient Token Pruning in Vision-Language Models
di: Liu, Jizhihui, et al.
Pubblicazione: (2025)

Efficient One-Step Diffusion Restoration Model with Compact Token Compression and Linear Attention
di: Qiao, Bingtian, et al.
Pubblicazione: (2026)

UniForm: A Reuse Attention Mechanism Optimized for Efficient Vision Transformers on Edge Devices
di: Yeom, Seul-Ki, et al.
Pubblicazione: (2024)

Spectral Vision Transformer for Efficient Tokenization with Limited Data
di: Roberts, Alexandra G., et al.
Pubblicazione: (2026)

Vote&Mix: Plug-and-Play Token Reduction for Efficient Vision Transformer
di: Peng, Shuai, et al.
Pubblicazione: (2024)

Block-based Symmetric Pruning and Fusion for Efficient Vision Transformers
di: Hsieh, Yi-Kuan, et al.
Pubblicazione: (2025)

ExFusion: Efficient Transformer Training via Multi-Experts Fusion
di: Ruan, Jiacheng, et al.
Pubblicazione: (2026)