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

Fuente: arXiv

Salvato in:

Dettagli Bibliografici
Autori principali:	Yan, Xinchen, Liang, Chen, Yu, Lijun, Yu, Adams Wei, Lu, Yifeng, Le, Quoc V.
Natura:	Preprint
Pubblicazione:	2025
Soggetti:	Computer Vision and Pattern Recognition Machine Learning
Accesso online:	Acceder al recurso
Tags:	Aggiungi Tag Nessun Tag, puoi essere il primo ad aggiungerne!!

Documenti analoghi

PixelWorld: How Far Are We from Perceiving Everything as Pixels?
di: Lyu, Zhiheng, et al.
Pubblicazione: (2025)

PICABench: How Far Are We from Physically Realistic Image Editing?
di: Pu, Yuandong, et al.
Pubblicazione: (2025)

How Far Are We from Optimal Reasoning Efficiency?
di: Gao, Jiaxuan, et al.
Pubblicazione: (2025)

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

How Far Are We From AGI: Are LLMs All We Need?
di: Feng, Tao, et al.
Pubblicazione: (2024)

The AI Hippocampus: How Far are We From Human Memory?
di: Jia, Zixia, et al.
Pubblicazione: (2026)

How Far Are We From True Auto-Research?
di: Zhang, Zhengxin, et al.
Pubblicazione: (2026)

ImageAttributionBench: How Far Are We from Generalizable Attribution?
di: Mou, Tingshu, et al.
Pubblicazione: (2026)

Retrieval-Augmented Test Generation: How Far Are We?
di: Shin, Jiho, et al.
Pubblicazione: (2024)

The Digital Cybersecurity Expert: How Far Have We Come?
di: Wang, Dawei, et al.
Pubblicazione: (2025)

How Far Can We Trust Chaos? Extending the Horizon of Predictability
di: Angelidis, Alexandros K., et al.
Pubblicazione: (2025)

Can AI Agents Generate Microservices? How Far are We?
di: Adnan, Bassam, et al.
Pubblicazione: (2026)

LLM For Loop Invariant Generation and Fixing: How Far Are We?
di: Akhond, Mostafijur Rahman, et al.
Pubblicazione: (2025)

Model Editing for LLMs4Code: How Far are We?
di: Li, Xiaopeng, et al.
Pubblicazione: (2024)

AGI-Elo: How Far Are We From Mastering A Task?
di: Sun, Shuo, et al.
Pubblicazione: (2025)

Unraveling the Potential of Large Language Models in Code Translation: How Far Are We?
di: Tao, Qingxiao, et al.
Pubblicazione: (2024)

PixelDiT: Pixel Diffusion Transformers for Image Generation
di: Yu, Yongsheng, et al.
Pubblicazione: (2025)

A Large-Scale Evaluation for Log Parsing Techniques: How Far Are We?
di: Jiang, Zhihan, et al.
Pubblicazione: (2023)

Vulnerability-Affected Versions Identification: How Far Are We?
di: Chen, Xingchu, et al.
Pubblicazione: (2025)

Autonomous Driving in Unstructured Environments: How Far Have We Come?
di: Min, Chen, et al.
Pubblicazione: (2024)

How Far Are We from True Unlearnability?
di: Ye, Kai, et al.
Pubblicazione: (2025)

LLMs for Relational Reasoning: How Far are We?
di: Li, Zhiming, et al.
Pubblicazione: (2024)

How Far Are We from Generating Missing Modalities with Foundation Models?
di: Ke, Guanzhou, et al.
Pubblicazione: (2025)

Simple synthetic data reduces sycophancy in large language models
di: Wei, Jerry, et al.
Pubblicazione: (2023)

From Scaling to Structured Expressivity: Rethinking Transformers for CTR Prediction
di: Yan, Bencheng, et al.
Pubblicazione: (2025)

Automatically Detecting Checked-In Secrets in Android Apps: How Far Are We?
di: Li, Kevin, et al.
Pubblicazione: (2024)

How Far Have We Gone in Binary Code Understanding Using Large Language Models
di: Shang, Xiuwei, et al.
Pubblicazione: (2024)

How Far Are We? The Triumphs and Trials of Generative AI in Learning Software Engineering
di: Choudhuri, Rudrajit, et al.
Pubblicazione: (2023)

Duplicate Bug Report Detection: How Far Are We?
di: Zhang, Ting, et al.
Pubblicazione: (2022)

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

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

IDEA-Bench: How Far are Generative Models from Professional Designing?
di: Liang, Chen, et al.
Pubblicazione: (2024)

When ChatGPT Meets Smart Contract Vulnerability Detection: How Far Are We?
di: Chen, Chong, et al.
Pubblicazione: (2023)

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

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

Leveraging Language Models for Log Statement Generation in Multilingual Scenarios: How Far Are We?
di: Kusama, Kazuki, et al.
Pubblicazione: (2026)

An Empirical Study on Automatically Detecting AI-Generated Source Code: How Far Are We?
di: Suh, Hyunjae, et al.
Pubblicazione: (2024)

How Far Are We from Genuinely Useful Deep Research Agents?
di: Zhang, Dingling, et al.
Pubblicazione: (2025)

Vulnerability Detection with Code Language Models: How Far Are We?
di: Ding, Yangruibo, et al.
Pubblicazione: (2024)

Representation Learning for Stack Overflow Posts: How Far are We?
di: He, Junda, et al.
Pubblicazione: (2023)