Cover Image

WinTok: A Win-Win Hybrid Tokenizer via Decomposing Visual Understanding and Generation with Transferable Tokens

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Guo, Yiwei, Zhuang, Shaobin, Huang, Zhipeng, Fu, Canmiao, Li, Chen, Lyu, Jing, Wang, Yali
Format:	Preprint
Published:	2026
Subjects:	Computer Vision and Pattern Recognition
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

WeTok: Powerful Discrete Tokenization for High-Fidelity Visual Reconstruction
by: Zhuang, Shaobin, et al.
Published: (2025)

Random Wins All: Rethinking Grouping Strategies for Vision Tokens
by: Fan, Qihang, et al.
Published: (2026)

WinT3R: Window-Based Streaming Reconstruction with Camera Token Pool
by: Li, Zizun, et al.
Published: (2025)

Win-Win: Training High-Resolution Vision Transformers from Two Windows
by: Leroy, Vincent, et al.
Published: (2023)

UniFlow: A Unified Pixel Flow Tokenizer for Visual Understanding and Generation
by: Yue, Zhengrong, et al.
Published: (2025)

TransAgent: Transfer Vision-Language Foundation Models with Heterogeneous Agent Collaboration
by: Guo, Yiwei, et al.
Published: (2024)

Revealing the Two Sides of Data Augmentation: An Asymmetric Distillation-based Win-Win Solution for Open-Set Recognition
by: Jia, Yunbing, et al.
Published: (2024)

Video-GPT via Next Clip Diffusion
by: Zhuang, Shaobin, et al.
Published: (2025)

WeGen: A Unified Model for Interactive Multimodal Generation as We Chat
by: Huang, Zhipeng, et al.
Published: (2025)

UniTok: A Unified Tokenizer for Visual Generation and Understanding
by: Ma, Chuofan, et al.
Published: (2025)

NativeTok: Native Visual Tokenization for Improved Image Generation
by: Wu, Bin, et al.
Published: (2026)

DINO-Tok: Adapting DINO for Visual Tokenizers
by: Jia, Mingkai, et al.
Published: (2025)

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

Get In Video: Add Anything You Want to the Video
by: Zhuang, Shaobin, et al.
Published: (2025)

Evaluation of Winning Solutions of 2025 Low Power Computer Vision Challenge
by: Ye, Zihao, et al.
Published: (2026)

The Championship-Winning Solution for the 5th CLVISION Challenge 2024
by: Pan, Sishun, et al.
Published: (2024)

EvoTok: A Unified Image Tokenizer via Residual Latent Evolution for Visual Understanding and Generation
by: Li, Yan, et al.
Published: (2026)

Text-guided Visual Prompt DINO for Generic Segmentation
by: Guan, Yuchen, et al.
Published: (2025)

Layer Pruning with Consensus: A Triple-Win Solution
by: Mugnaini, Leandro Giusti, et al.
Published: (2024)

Predicting Winning Captions for Weekly New Yorker Comics
by: Cao, Stanley, et al.
Published: (2024)

WinSyn: A High Resolution Testbed for Synthetic Data
by: Kelly, Tom, et al.
Published: (2023)

CAIT: Triple-Win Compression towards High Accuracy, Fast Inference, and Favorable Transferability For ViTs
by: Wang, Ao, et al.
Published: (2023)

PhaseWin Search Framework Enable Efficient Object-Level Interpretation
by: Gu, Zihan, et al.
Published: (2025)

TokBench: Evaluating Your Visual Tokenizer before Visual Generation
by: Wu, Junfeng, et al.
Published: (2025)

SliceFine: The Universal Winning-Slice Hypothesis for Pretrained Networks
by: Kowsher, Md, et al.
Published: (2025)

GloTok: Global Perspective Tokenizer for Image Reconstruction and Generation
by: Zhao, Xuan, et al.
Published: (2025)

GigaTok: Scaling Visual Tokenizers to 3 Billion Parameters for Autoregressive Image Generation
by: Xiong, Tianwei, et al.
Published: (2025)

BitDance: Scaling Autoregressive Generative Models with Binary Tokens
by: Ai, Yuang, et al.
Published: (2026)

TrajTok: Learning Trajectory Tokens enables better Video Understanding
by: Zheng, Chenhao, et al.
Published: (2026)

MVP: Winning Solution to SMP Challenge 2025 Video Track
by: Ye, Liliang, et al.
Published: (2025)

UniCompress: Token Compression for Unified Vision-Language Understanding and Generation
by: Wang, Ziyao, et al.
Published: (2026)

UniWeTok: An Unified Binary Tokenizer with Codebook Size $\mathit{2^{128}}$ for Unified Multimodal Large Language Model
by: Zhuang, Shaobin, et al.
Published: (2026)

DaWin: Training-free Dynamic Weight Interpolation for Robust Adaptation
by: Oh, Changdae, et al.
Published: (2024)

DynTok: Dynamic Compression of Visual Tokens for Efficient and Effective Video Understanding
by: Zhang, Hongzhi, et al.
Published: (2025)

pMoE: Prompting Diverse Experts Together Wins More in Visual Adaptation
by: Mo, Shentong, et al.
Published: (2026)

Structured Semantic 3D Reconstruction (S23DR) Challenge 2025 -- Winning solution
by: Skvrna, Jan, et al.
Published: (2025)

PyraTok: Language-Aligned Pyramidal Tokenizer for Video Understanding and Generation
by: Susladkar, Onkar, et al.
Published: (2026)

Continual Learning: Forget-free Winning Subnetworks for Video Representations
by: Kang, Haeyong, et al.
Published: (2023)

HieraTok: Multi-Scale Visual Tokenizer Improves Image Reconstruction and Generation
by: Chen, Cong, et al.
Published: (2025)

RefTok: Reference-Based Tokenization for Video Generation
by: Fan, Xiang, et al.
Published: (2025)