Cover Image

EVATok: Adaptive Length Video Tokenization for Efficient Visual Autoregressive Generation

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Xiong, Tianwei, Liew, Jun Hao, Huang, Zilong, Lin, Zhijie, Feng, Jiashi, Liu, Xihui
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

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

Bridging Continuous and Discrete Tokens for Autoregressive Visual Generation
by: Wang, Yuqing, et al.
Published: (2025)

Loong: Generating Minute-level Long Videos with Autoregressive Language Models
by: Wang, Yuqing, et al.
Published: (2024)

Parallelized Autoregressive Visual Generation
by: Wang, Yuqing, et al.
Published: (2024)

LVD-2M: A Long-take Video Dataset with Temporally Dense Captions
by: Xiong, Tianwei, et al.
Published: (2024)

Cubic Discrete Diffusion: Discrete Visual Generation on High-Dimensional Representation Tokens
by: Wang, Yuqing, et al.
Published: (2026)

ALTo: Adaptive-Length Tokenizer for Autoregressive Mask Generation
by: Wang, Lingfeng, et al.
Published: (2025)

DiG: Scalable and Efficient Diffusion Models with Gated Linear Attention
by: Zhu, Lianghui, et al.
Published: (2024)

The Scalability of Simplicity: Empirical Analysis of Vision-Language Learning with a Single Transformer
by: Lei, Weixian, et al.
Published: (2025)

Adaptive Begin-of-Video Tokens for Autoregressive Video Diffusion Models
by: Cheng, Tianle, et al.
Published: (2025)

MagicVideo-V2: Multi-Stage High-Aesthetic Video Generation
by: Wang, Weimin, et al.
Published: (2024)

Empowering Visual Creativity: A Vision-Language Assistant to Image Editing Recommendations
by: Shen, Tiancheng, et al.
Published: (2024)

LightningDrag: Lightning Fast and Accurate Drag-based Image Editing Emerging from Videos
by: Shi, Yujun, et al.
Published: (2024)

Efficient Autoregressive Shape Generation via Octree-Based Adaptive Tokenization
by: Deng, Kangle, et al.
Published: (2025)

PLLaVA : Parameter-free LLaVA Extension from Images to Videos for Video Dense Captioning
by: Xu, Lin, et al.
Published: (2024)

ActVAR: Activating Mixtures of Weights and Tokens for Efficient Visual Autoregressive Generation
by: Zhang, Kaixin, et al.
Published: (2025)

SuperCLIP: CLIP with Simple Classification Supervision
by: Zhao, Weiheng, et al.
Published: (2025)

Vista-LLaMA: Reducing Hallucination in Video Language Models via Equal Distance to Visual Tokens
by: Ma, Fan, et al.
Published: (2023)

Principles of Visual Tokens for Efficient Video Understanding
by: Hao, Xinyue, et al.
Published: (2024)

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

PruneVid: Visual Token Pruning for Efficient Video Large Language Models
by: Huang, Xiaohu, et al.
Published: (2024)

How Far is Video Generation from World Model: A Physical Law Perspective
by: Kang, Bingyi, et al.
Published: (2024)

Efficient Conditional Generation on Scale-based Visual Autoregressive Models
by: Liu, Jiaqi, et al.
Published: (2025)

LARP: Tokenizing Videos with a Learned Autoregressive Generative Prior
by: Wang, Hanyu, et al.
Published: (2024)

Depth Adaptive Efficient Visual Autoregressive Modeling
by: Li, Chunliang, et al.
Published: (2026)

Adaptive 1D Video Diffusion Autoencoder
by: Teng, Yao, et al.
Published: (2026)

Classification Done Right for Vision-Language Pre-Training
by: Huang, Zilong, et al.
Published: (2024)

Video Depth Anything: Consistent Depth Estimation for Super-Long Videos
by: Chen, Sili, et al.
Published: (2025)

ImageFolder: Autoregressive Image Generation with Folded Tokens
by: Li, Xiang, et al.
Published: (2024)

Image Understanding Makes for A Good Tokenizer for Image Generation
by: Wang, Luting, et al.
Published: (2024)

Depth Anything 3: Recovering the Visual Space from Any Views
by: Lin, Haotong, et al.
Published: (2025)

FastSTAR: Spatiotemporal Token Pruning for Efficient Autoregressive Video Synthesis
by: Yune, Sungwoong, et al.
Published: (2026)

TrimTokenator-LC: Towards Adaptive Visual Token Pruning for Large Multimodal Models with Long Contexts
by: Zhang, Hao, et al.
Published: (2025)

Improving Autoregressive Visual Generation with Cluster-Oriented Token Prediction
by: Hu, Teng, et al.
Published: (2025)

GenMAC: Compositional Text-to-Video Generation with Multi-Agent Collaboration
by: Huang, Kaiyi, et al.
Published: (2024)

VTBench: Evaluating Visual Tokenizers for Autoregressive Image Generation
by: Lin, Huawei, et al.
Published: (2025)

VideoMAR: Autoregressive Video Generatio with Continuous Tokens
by: Yu, Hu, et al.
Published: (2025)

TrimTokenator: Towards Adaptive Visual Token Pruning for Large Multimodal Models
by: Zhang, Hao, et al.
Published: (2025)

LottieGPT: Tokenizing Vector Animation for Autoregressive Generation
by: Chen, Junhao, et al.
Published: (2026)

From Slow Bidirectional to Fast Autoregressive Video Diffusion Models
by: Yin, Tianwei, et al.
Published: (2024)