Imagen de Portada

MacTok: Robust Continuous Tokenization for Image Generation

Fuente: arXiv

Guardado en:

Detalles Bibliográficos
Autores principales:	Zeng, Hengyu, Gao, Xin, Li, Guanghao, Yan, Yuxiang, Ruan, Jiaoyang, Ma, Junpeng, Wang, Haoyu Albert, Pu, Jian
Formato:	Preprint
Publicado:	2026
Materias:	Computer Vision and Pattern Recognition Artificial Intelligence
Acceso en línea:	Acceder al recurso
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

Ejemplares similares

Dark-ISP: Enhancing RAW Image Processing for Low-Light Object Detection
por: Guo, Jiasheng, et al.
Publicado: (2025)

GIFT: Global Irreplaceability Frame Targeting for Efficient Video Understanding
por: Ma, Junpeng, et al.
Publicado: (2026)

DINO-VO: Learning Where to Focus for Enhanced State Estimation
por: Chen, Qi, et al.
Publicado: (2026)

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

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

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

InsightTok: Improving Text and Face Fidelity in Discrete Tokenization for Autoregressive Image Generation
por: Yue, Yang, et al.
Publicado: (2026)

ResTok: Learning Hierarchical Residuals in 1D Visual Tokenizers for Autoregressive Image Generation
por: Zhang, Xu, et al.
Publicado: (2026)

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

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

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

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

FlowTok: Flowing Seamlessly Across Text and Image Tokens
por: He, Ju, et al.
Publicado: (2025)

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

Reasoning on the Manifold: Bidirectional Consistency for Self-Verification in Diffusion Language Models
por: Ruan, Jiaoyang, et al.
Publicado: (2026)

CaTok: Taming Mean Flows for One-Dimensional Causal Image Tokenization
por: Chen, Yitong, et al.
Publicado: (2026)

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

CasPoinTr: Point Cloud Completion with Cascaded Networks and Knowledge Distillation
por: Yang, Yifan, et al.
Publicado: (2025)

Importance-Based Token Merging for Efficient Image and Video Generation
por: Wu, Haoyu, et al.
Publicado: (2024)

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

WinTok: A Win-Win Hybrid Tokenizer via Decomposing Visual Understanding and Generation with Transferable Tokens
por: Guo, Yiwei, et al.
Publicado: (2026)

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

FlexTok: Resampling Images into 1D Token Sequences of Flexible Length
por: Bachmann, Roman, et al.
Publicado: (2025)

NextStep-1: Toward Autoregressive Image Generation with Continuous Tokens at Scale
por: NextStep Team, et al.
Publicado: (2025)

VesselTok: Tokenizing Vessel-like 3D Biomedical Graph Representations for Reconstruction and Generation
por: Prabhakar, Chinmay, et al.
Publicado: (2026)

PAPL-SLAM: Principal Axis-Anchored Monocular Point-Line SLAM
por: Li, Guanghao, et al.
Publicado: (2024)

Frequency Autoregressive Image Generation with Continuous Tokens
por: Yu, Hu, et al.
Publicado: (2025)

SweetTok: Semantic-Aware Spatial-Temporal Tokenizer for Compact Video Discretization
por: Tan, Zhentao, et al.
Publicado: (2024)

Vision Foundation Models as Generalist Tokenizers for Image Generation
por: Zheng, Anlin, et al.
Publicado: (2026)

CODA: Repurposing Continuous VAEs for Discrete Tokenization
por: Liu, Zeyu, et al.
Publicado: (2025)

SemHiTok: A Unified Image Tokenizer via Semantic-Guided Hierarchical Codebook for Multimodal Understanding and Generation
por: Chen, Zisheng, et al.
Publicado: (2025)

TokLIP: Marry Visual Tokens to CLIP for Multimodal Comprehension and Generation
por: Lin, Haokun, et al.
Publicado: (2025)

Deep Incomplete Multi-view Learning via Cyclic Permutation of VAEs
por: Gao, Xin, et al.
Publicado: (2025)

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

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

AlignTok: Aligning Visual Foundation Encoders to Tokenizers for Diffusion Models
por: Chen, Bowei, et al.
Publicado: (2025)

AdaTok: Adaptive Token Compression with Object-Aware Representations for Efficient Multimodal LLMs
por: Zhang, Xinliang, et al.
Publicado: (2025)

LINA: Linear Autoregressive Image Generative Models with Continuous Tokens
por: Wang, Jiahao, et al.
Publicado: (2026)

Continual Alignment for SAM: Rethinking Foundation Models for Medical Image Segmentation in Continual Learning
por: Wang, Jiayi, et al.
Publicado: (2025)

Can3Tok: Canonical 3D Tokenization and Latent Modeling of Scene-Level 3D Gaussians
por: Gao, Quankai, et al.
Publicado: (2025)