Imagen de Portada

Scalable Pre-training of Large Autoregressive Image Models

Fuente: arXiv

Guardado en:

Detalles Bibliográficos
Autores principales:	El-Nouby, Alaaeldin, Klein, Michal, Zhai, Shuangfei, Bautista, Miguel Angel, Toshev, Alexander, Shankar, Vaishaal, Susskind, Joshua M, Joulin, Armand
Formato:	Preprint
Publicado:	2024
Materias:	Computer Vision and Pattern Recognition
Acceso en línea:	Acceder al recurso
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

Ejemplares similares

Multimodal Autoregressive Pre-training of Large Vision Encoders
por: Fini, Enrico, et al.
Publicado: (2024)

World-consistent Video Diffusion with Explicit 3D Modeling
por: Zhang, Qihang, et al.
Publicado: (2024)

Pre-trained Language Models Do Not Help Auto-regressive Text-to-Image Generation
por: Zhang, Yuhui, et al.
Publicado: (2023)

DART: Denoising Autoregressive Transformer for Scalable Text-to-Image Generation
por: Gu, Jiatao, et al.
Publicado: (2024)

Scaling Laws for Native Multimodal Models
por: Shukor, Mustafa, et al.
Publicado: (2025)

Kaleido Diffusion: Improving Conditional Diffusion Models with Autoregressive Latent Modeling
por: Gu, Jiatao, et al.
Publicado: (2024)

Many-to-many Image Generation with Auto-regressive Diffusion Models
por: Shen, Ying, et al.
Publicado: (2024)

Normalizing Flows with Iterative Denoising
por: Chen, Tianrong, et al.
Publicado: (2026)

STARFlow2: Bridging Language Models and Normalizing Flows for Unified Multimodal Generation
por: Shen, Ying, et al.
Publicado: (2026)

STARFlow: Scaling Latent Normalizing Flows for High-resolution Image Synthesis
por: Gu, Jiatao, et al.
Publicado: (2025)

MobileCLIP2: Improving Multi-Modal Reinforced Training
por: Faghri, Fartash, et al.
Publicado: (2025)

STARFlow-V: End-to-End Video Generative Modeling with Normalizing Flows
por: Gu, Jiatao, et al.
Publicado: (2025)

Matryoshka Diffusion Models
por: Gu, Jiatao, et al.
Publicado: (2023)

The Coupling Within: Flow Matching via Distilled Normalizing Flows
por: Berthelot, David, et al.
Publicado: (2026)

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

Flexible Language Modeling in Continuous Space with Transformer-based Autoregressive Flows
por: Zhang, Ruixiang, et al.
Publicado: (2025)

Improving GFlowNets for Text-to-Image Diffusion Alignment
por: Zhang, Dinghuai, et al.
Publicado: (2024)

Normalizing Flows are Capable Generative Models
por: Zhai, Shuangfei, et al.
Publicado: (2024)

TypeScore: A Text Fidelity Metric for Text-to-Image Generative Models
por: Sampaio, Georgia Gabriela, et al.
Publicado: (2024)

Normalizing Trajectory Models
por: Gu, Jiatao, et al.
Publicado: (2026)

Pseudo-Generalized Dynamic View Synthesis from a Video
por: Zhao, Xiaoming, et al.
Publicado: (2023)

Interpreting CLIP: Insights on the Robustness to ImageNet Distribution Shifts
por: Crabbé, Jonathan, et al.
Publicado: (2023)

CTRLorALTer: Conditional LoRAdapter for Efficient 0-Shot Control & Altering of T2I Models
por: Stracke, Nick, et al.
Publicado: (2024)

How Far Are We from Intelligent Visual Deductive Reasoning?
por: Zhang, Yizhe, et al.
Publicado: (2024)

Datasets, Documents, and Repetitions: The Practicalities of Unequal Data Quality
por: Fang, Alex, et al.
Publicado: (2025)

Generative Pre-trained Autoregressive Diffusion Transformer
por: Zhang, Yuan, et al.
Publicado: (2025)

Towards Scalable Language-Image Pre-training for 3D Medical Imaging
por: Zhao, Chenhui, et al.
Publicado: (2025)

An Empirical Study of Autoregressive Pre-training from Videos
por: Rajasegaran, Jathushan, et al.
Publicado: (2025)

Scalable Autoregressive Image Generation with Mamba
por: Li, Haopeng, et al.
Publicado: (2024)

Swallowing the Bitter Pill: Simplified Scalable Conformer Generation
por: Wang, Yuyang, et al.
Publicado: (2023)

Dynamic Pre-training: Towards Efficient and Scalable All-in-One Image Restoration
por: Dudhane, Akshay, et al.
Publicado: (2024)

Learning Long-term Motion Embeddings for Efficient Kinematics Generation
por: Stracke, Nick, et al.
Publicado: (2026)

From Visuals to Vocabulary: Establishing Equivalence Between Image and Text Token Through Autoregressive Pre-training in MLLMs
por: Li, Mingxiao, et al.
Publicado: (2025)

Towards Scalable Pre-training of Visual Tokenizers for Generation
por: Yao, Jingfeng, et al.
Publicado: (2025)

Adapting Self-Supervised Representations as a Latent Space for Efficient Generation
por: Gui, Ming, et al.
Publicado: (2025)

Self-supervised Pre-training of Text Recognizers
por: Kišš, Martin, et al.
Publicado: (2024)

DINOv2: Learning Robust Visual Features without Supervision
por: Oquab, Maxime, et al.
Publicado: (2023)

Self-Supervised Learning for Pre-training Capsule Networks: Overcoming Medical Imaging Dataset Challenges
por: El-Shimy, Heba, et al.
Publicado: (2025)

Autoregressive Model Beats Diffusion: Llama for Scalable Image Generation
por: Sun, Peize, et al.
Publicado: (2024)

Generative Modeling with Phase Stochastic Bridges
por: Chen, Tianrong, et al.
Publicado: (2023)