Image de couverture de livre

Rethinking Generative Image Pretraining: How Far Are We From Scaling Up Next-Pixel Prediction?

Fuente: arXiv

Enregistré dans:

Détails bibliographiques
Auteurs principaux:	Yan, Xinchen, Liang, Chen, Yu, Lijun, Yu, Adams Wei, Lu, Yifeng, Le, Quoc V.
Format:	Preprint
Publié:	2025
Sujets:	Computer Vision and Pattern Recognition Machine Learning
Accès en ligne:	Acceder al recurso
Tags:	Ajouter un tag Pas de tags, Soyez le premier à ajouter un tag!

Documents similaires

PixelWorld: How Far Are We from Perceiving Everything as Pixels?
par: Lyu, Zhiheng, et autres
Publié: (2025)

PICABench: How Far Are We from Physically Realistic Image Editing?
par: Pu, Yuandong, et autres
Publié: (2025)

How Far Are We from Optimal Reasoning Efficiency?
par: Gao, Jiaxuan, et autres
Publié: (2025)

Automatic Data Labeling for Software Vulnerability Prediction Models: How Far Are We?
par: Le, Triet H. M., et autres
Publié: (2024)

How Far Are We From AGI: Are LLMs All We Need?
par: Feng, Tao, et autres
Publié: (2024)

The AI Hippocampus: How Far are We From Human Memory?
par: Jia, Zixia, et autres
Publié: (2026)

How Far Are We From True Auto-Research?
par: Zhang, Zhengxin, et autres
Publié: (2026)

ImageAttributionBench: How Far Are We from Generalizable Attribution?
par: Mou, Tingshu, et autres
Publié: (2026)

Retrieval-Augmented Test Generation: How Far Are We?
par: Shin, Jiho, et autres
Publié: (2024)

The Digital Cybersecurity Expert: How Far Have We Come?
par: Wang, Dawei, et autres
Publié: (2025)

How Far Can We Trust Chaos? Extending the Horizon of Predictability
par: Angelidis, Alexandros K., et autres
Publié: (2025)

Can AI Agents Generate Microservices? How Far are We?
par: Adnan, Bassam, et autres
Publié: (2026)

LLM For Loop Invariant Generation and Fixing: How Far Are We?
par: Akhond, Mostafijur Rahman, et autres
Publié: (2025)

Model Editing for LLMs4Code: How Far are We?
par: Li, Xiaopeng, et autres
Publié: (2024)

AGI-Elo: How Far Are We From Mastering A Task?
par: Sun, Shuo, et autres
Publié: (2025)

Unraveling the Potential of Large Language Models in Code Translation: How Far Are We?
par: Tao, Qingxiao, et autres
Publié: (2024)

PixelDiT: Pixel Diffusion Transformers for Image Generation
par: Yu, Yongsheng, et autres
Publié: (2025)

A Large-Scale Evaluation for Log Parsing Techniques: How Far Are We?
par: Jiang, Zhihan, et autres
Publié: (2023)

Vulnerability-Affected Versions Identification: How Far Are We?
par: Chen, Xingchu, et autres
Publié: (2025)

Autonomous Driving in Unstructured Environments: How Far Have We Come?
par: Min, Chen, et autres
Publié: (2024)

How Far Are We from True Unlearnability?
par: Ye, Kai, et autres
Publié: (2025)

LLMs for Relational Reasoning: How Far are We?
par: Li, Zhiming, et autres
Publié: (2024)

How Far Are We from Generating Missing Modalities with Foundation Models?
par: Ke, Guanzhou, et autres
Publié: (2025)

Simple synthetic data reduces sycophancy in large language models
par: Wei, Jerry, et autres
Publié: (2023)

From Scaling to Structured Expressivity: Rethinking Transformers for CTR Prediction
par: Yan, Bencheng, et autres
Publié: (2025)

Automatically Detecting Checked-In Secrets in Android Apps: How Far Are We?
par: Li, Kevin, et autres
Publié: (2024)

How Far Have We Gone in Binary Code Understanding Using Large Language Models
par: Shang, Xiuwei, et autres
Publié: (2024)

How Far Are We? The Triumphs and Trials of Generative AI in Learning Software Engineering
par: Choudhuri, Rudrajit, et autres
Publié: (2023)

Duplicate Bug Report Detection: How Far Are We?
par: Zhang, Ting, et autres
Publié: (2022)

Portfolio Assessment: How Far Have We Come?
par: Brown, Carol A.
Publié: (2002)

How Far Can We Go with Pixels Alone? A Pilot Study on Screen-Only Navigation in Commercial 3D ARPGs
par: Xu, Kaijie, et autres
Publié: (2026)

IDEA-Bench: How Far are Generative Models from Professional Designing?
par: Liang, Chen, et autres
Publié: (2024)

When ChatGPT Meets Smart Contract Vulnerability Detection: How Far Are We?
par: Chen, Chong, et autres
Publié: (2023)

D-Judge: How Far Are We? Assessing the Discrepancies Between AI-synthesized and Natural Images through Multimodal Guidance
par: Liu, Renyang, et autres
Publié: (2024)

How Far Are We to GPT-4V? Closing the Gap to Commercial Multimodal Models with Open-Source Suites
par: Chen, Zhe, et autres
Publié: (2024)

Leveraging Language Models for Log Statement Generation in Multilingual Scenarios: How Far Are We?
par: Kusama, Kazuki, et autres
Publié: (2026)

An Empirical Study on Automatically Detecting AI-Generated Source Code: How Far Are We?
par: Suh, Hyunjae, et autres
Publié: (2024)

How Far Are We from Genuinely Useful Deep Research Agents?
par: Zhang, Dingling, et autres
Publié: (2025)

Vulnerability Detection with Code Language Models: How Far Are We?
par: Ding, Yangruibo, et autres
Publié: (2024)

Representation Learning for Stack Overflow Posts: How Far are We?
par: He, Junda, et autres
Publié: (2023)