Image de couverture de livre

MergeTok: Unified Continuous and Discrete Visual Tokenization via Token Merging

Fuente: arXiv

Enregistré dans:

Détails bibliographiques
Auteurs principaux:	Zhang, Luyuan, Li, Siyuan, Wang, Zedong, Xie, Qingsong, Tan, Cheng, Wang, Anna, Zhang, Yanhao, Chen, Chen, Lu, Haonan, Wang, Haoqian
Format:	Preprint
Publié:	2026
Sujets:	Computer Vision and Pattern Recognition
Accès en ligne:	Acceder al recurso
Tags:	Ajouter un tag Pas de tags, Soyez le premier à ajouter un tag!

Documents similaires

MergeVQ: A Unified Framework for Visual Generation and Representation with Disentangled Token Merging and Quantization
par: Li, Siyuan, et autres
Publié: (2025)

Layton: Latent Consistency Tokenizer for 1024-pixel Image Reconstruction and Generation by 256 Tokens
par: Xie, Qingsong, et autres
Publié: (2025)

Efficient Visual Transformer by Learnable Token Merging
par: Wang, Yancheng, et autres
Publié: (2024)

WeTok: Powerful Discrete Tokenization for High-Fidelity Visual Reconstruction
par: Zhuang, Shaobin, et autres
Publié: (2025)

PainterNet: Adaptive Image Inpainting with Actual-Token Attention and Diverse Mask Control
par: Wang, Ruichen, et autres
Publié: (2024)

Wave-Particle (Continuous-Discrete) Dualistic Visual Tokenization for Unified Understanding and Generation
par: Chen, Yizhu, et autres
Publié: (2025)

Token Merging via Spatiotemporal Information Mining for Surgical Video Understanding
par: Jiang, Xixi, et autres
Publié: (2025)

ToSA: Token Merging with Spatial Awareness
par: Huang, Hsiang-Wei, et autres
Publié: (2025)

Sequential Token Merging: Revisiting Hidden States
par: Wen, Yan, et autres
Publié: (2025)

Video Token Merging for Long-form Video Understanding
par: Lee, Seon-Ho, et autres
Publié: (2024)

RankE: End-to-End Post-Training for Discrete Text-to-Image Generation with Decoder Co-Evolution
par: Jian, Siyong, et autres
Publié: (2026)

TMCIR: Token Merge Benefits Composed Image Retrieval
par: Wang, Chaoyang, et autres
Publié: (2025)

MergeDNA: Context-aware Genome Modeling with Dynamic Tokenization through Token Merging
par: Li, Siyuan, et autres
Publié: (2025)

AlignTok: Aligning Visual Foundation Encoders to Tokenizers for Diffusion Models
par: Chen, Bowei, et autres
Publié: (2025)

DINO-Tok: Adapting DINO for Visual Tokenizers
par: Jia, Mingkai, et autres
Publié: (2025)

Co-Me: Confidence-Guided Token Merging for Visual Geometric Transformers
par: Chen, Yutian, et autres
Publié: (2025)

EvoTok: A Unified Image Tokenizer via Residual Latent Evolution for Visual Understanding and Generation
par: Li, Yan, et autres
Publié: (2026)

PixelPrune: Pixel-Level Adaptive Visual Token Reduction via Predictive Coding
par: Wang, Nan, et autres
Publié: (2026)

WinTok: A Win-Win Hybrid Tokenizer via Decomposing Visual Understanding and Generation with Transferable Tokens
par: Guo, Yiwei, et autres
Publié: (2026)

TokBench: Evaluating Your Visual Tokenizer before Visual Generation
par: Wu, Junfeng, et autres
Publié: (2025)

SweetTok: Semantic-Aware Spatial-Temporal Tokenizer for Compact Video Discretization
par: Tan, Zhentao, et autres
Publié: (2024)

MergeMix: A Unified Augmentation Paradigm for Visual and Multi-Modal Understanding
par: Jin, Xin, et autres
Publié: (2025)

CubistMerge: Spatial-Preserving Token Merging For Diverse ViT Backbones
par: Gong, Wenyi, et autres
Publié: (2025)

TinyChart: Efficient Chart Understanding with Visual Token Merging and Program-of-Thoughts Learning
par: Zhang, Liang, et autres
Publié: (2024)

DynTok: Dynamic Compression of Visual Tokens for Efficient and Effective Video Understanding
par: Zhang, Hongzhi, et autres
Publié: (2025)

Token Merging for Training-Free Semantic Binding in Text-to-Image Synthesis
par: Hu, Taihang, et autres
Publié: (2024)

Unified Language-Vision Pretraining in LLM with Dynamic Discrete Visual Tokenization
par: Jin, Yang, et autres
Publié: (2023)

UniTok: A Unified Tokenizer for Visual Generation and Understanding
par: Ma, Chuofan, et autres
Publié: (2025)

HTTM: Head-wise Temporal Token Merging for Faster VGGT
par: Wang, Weitian, et autres
Publié: (2025)

InfoTok: Adaptive Discrete Video Tokenizer via Information-Theoretic Compression
par: Ye, Haotian, et autres
Publié: (2025)

Beyond Training: Dynamic Token Merging for Zero-Shot Video Understanding
par: Zhang, Yiming, et autres
Publié: (2024)

Video, How Do Your Tokens Merge?
par: Pollard, Sam, et autres
Publié: (2025)

AIM: Adaptive Inference of Multi-Modal LLMs via Token Merging and Pruning
par: Zhong, Yiwu, et autres
Publié: (2024)

LiteVGGT: Boosting Vanilla VGGT via Geometry-aware Cached Token Merging
par: Shu, Zhijian, et autres
Publié: (2025)

Bridging Continuous and Discrete Tokens for Autoregressive Visual Generation
par: Wang, Yuqing, et autres
Publié: (2025)

DORA: Dynamic Online Reinforcement Agent for Token Merging in Vision Transformers
par: He, Kaixuan, et autres
Publié: (2026)

TokLIP: Marry Visual Tokens to CLIP for Multimodal Comprehension and Generation
par: Lin, Haokun, et autres
Publié: (2025)

Unified Autoregressive Visual Generation and Understanding with Continuous Tokens
par: Fan, Lijie, et autres
Publié: (2025)

MacTok: Robust Continuous Tokenization for Image Generation
par: Zeng, Hengyu, et autres
Publié: (2026)

Improved Visual-Spatial Reasoning via R1-Zero-Like Training
par: Liao, Zhenyi, et autres
Publié: (2025)