Image de couverture de livre

Scaling Laws in Patchification: An Image Is Worth 50,176 Tokens And More

Fuente: arXiv

Enregistré dans:

Détails bibliographiques
Auteurs principaux:	Wang, Feng, Yu, Yaodong, Wei, Guoyizhe, Shao, Wei, Zhou, Yuyin, Yuille, Alan, Xie, Cihang
Format:	Preprint
Publié:	2025
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

Adventurer: Optimizing Vision Mamba Architecture Designs for Efficiency
par: Wang, Feng, et autres
Publié: (2024)

Mamba-R: Vision Mamba ALSO Needs Registers
par: Wang, Feng, et autres
Publié: (2024)

M-VAR: Decoupled Scale-wise Autoregressive Modeling for High-Quality Image Generation
par: Ren, Sucheng, et autres
Publié: (2024)

RNN as Linear Transformer: A Closer Investigation into Representational Potentials of Visual Mamba Models
par: Yang, Timing, et autres
Publié: (2025)

A Semantic Space is Worth 256 Language Descriptions: Make Stronger Segmentation Models with Descriptive Properties
par: Xiao, Junfei, et autres
Publié: (2023)

Scaling White-Box Transformers for Vision
par: Yang, Jinrui, et autres
Publié: (2024)

From Pixels to Objects: A Hierarchical Approach for Part and Object Segmentation Using Local and Global Aggregation
par: Xie, Yunfei, et autres
Publié: (2024)

Sculpting Holistic 3D Representation in Contrastive Language-Image-3D Pre-training
par: Gao, Yipeng, et autres
Publié: (2023)

SPFormer: Enhancing Vision Transformer with Superpixel Representation
par: Mei, Jieru, et autres
Publié: (2024)

ARVideo: Autoregressive Pretraining for Self-Supervised Video Representation Learning
par: Ren, Sucheng, et autres
Publié: (2024)

GPT-IMAGE-EDIT-1.5M: A Million-Scale, GPT-Generated Image Dataset
par: Wang, Yuhan, et autres
Publié: (2025)

Localization vs. Semantics: Visual Representations in Unimodal and Multimodal Models
par: Li, Zhuowan, et autres
Publié: (2022)

ViT-Linearizer: Distilling Quadratic Knowledge into Linear-Time Vision Models
par: Wei, Guoyizhe, et autres
Publié: (2025)

Pyramidal Patchification Flow for Visual Generation
par: Li, Hui, et autres
Publié: (2025)

ViT-5: Vision Transformers for The Mid-2020s
par: Wang, Feng, et autres
Publié: (2026)

An Image is Worth 32 Tokens for Reconstruction and Generation
par: Yu, Qihang, et autres
Publié: (2024)

Rejuvenating image-GPT as Strong Visual Representation Learners
par: Ren, Sucheng, et autres
Publié: (2023)

$\texttt{Complex-Edit}$: CoT-Like Instruction Generation for Complexity-Controllable Image Editing Benchmark
par: Yang, Siwei, et autres
Publié: (2025)

iLLaVA: An Image is Worth Fewer Than 1/3 Input Tokens in Large Multimodal Models
par: Hu, Lianyu, et autres
Publié: (2024)

Medical Vision Generalist: Unifying Medical Imaging Tasks in Context
par: Ren, Sucheng, et autres
Publié: (2024)

DPAR: Dynamic Patchification for Efficient Autoregressive Visual Generation
par: Srivastava, Divyansh, et autres
Publié: (2025)

Spiral RoPE: Rotate Your Rotary Positional Embeddings in the 2D Plane
par: Liu, Haoyu, et autres
Publié: (2026)

A Unified and Controllable Framework for Layered Image Generation with Visual Effects
par: Yang, Jinrui, et autres
Publié: (2026)

A Creative Agent is Worth a 64-Token Template
par: Shi, Ruixiao, et autres
Publié: (2026)

Beyond Masks: The Case for Medical Image Parsing
par: Gupta, Siddharth, et autres
Publié: (2026)

L2B: Learning to Bootstrap Robust Models for Combating Label Noise
par: Zhou, Yuyin, et autres
Publié: (2022)

Captain Safari: A World Engine with Pose-Aligned 3D Memory
par: Chou, Yu-Cheng, et autres
Publié: (2025)

OpenVision 2: A Family of Generative Pretrained Visual Encoders for Multimodal Learning
par: Liu, Yanqing, et autres
Publié: (2025)

HQ-Edit: A High-Quality Dataset for Instruction-based Image Editing
par: Hui, Mude, et autres
Publié: (2024)

ARFlow: Autoregressive Flow with Hybrid Linear Attention
par: Hui, Mude, et autres
Publié: (2025)

FlowAR: Scale-wise Autoregressive Image Generation Meets Flow Matching
par: Ren, Sucheng, et autres
Publié: (2024)

3D-TransUNet for Brain Metastases Segmentation in the BraTS2023 Challenge
par: Yang, Siwei, et autres
Publié: (2024)

Generative Image Layer Decomposition with Visual Effects
par: Yang, Jinrui, et autres
Publié: (2024)

SCLIP: Rethinking Self-Attention for Dense Vision-Language Inference
par: Wang, Feng, et autres
Publié: (2023)

An Image Is Worth Ten Thousand Words: Verbose-Text Induction Attacks on VLMs
par: Luo, Zhi, et autres
Publié: (2025)

A Picture is Worth More Than 77 Text Tokens: Evaluating CLIP-Style Models on Dense Captions
par: Urbanek, Jack, et autres
Publié: (2023)

Revisiting Adversarial Training at Scale
par: Wang, Zeyu, et autres
Publié: (2024)

VTok: A Unified Video Tokenizer with Decoupled Spatial-Temporal Latents
par: Wang, Feng, et autres
Publié: (2026)

Beyond Next-Token: Next-X Prediction for Autoregressive Visual Generation
par: Ren, Sucheng, et autres
Publié: (2025)

How Well Do Supervised 3D Models Transfer to Medical Imaging Tasks?
par: Li, Wenxuan, et autres
Publié: (2025)