Haoran Wei

HaoranWei's activity

• All
• Models
• Datasets
• Spaces
• Papers
• Collections
• Community
• Posts
• Upvotes
• Likes

upvoted a collection 29 days ago

Document AI

Collection

All the papers that can fundementally help in creating a true open-source processing pipeline. • 1 item • Updated Nov 11 • 1

upvoted a paper 29 days ago

Focus Anywhere for Fine-grained Multi-page Document Understanding

Paper • 2405.14295 • Published May 23 • 1

upvoted a collection 29 days ago

PixMo

Collection

A set of vision-language datasets built by Ai2 and used to train the Molmo family of models. Read more at https://molmo.allenai.org/blog • 9 items • Updated 30 days ago • 51

upvoted a paper 4 months ago

General OCR Theory: Towards OCR-2.0 via a Unified End-to-end Model

Paper • 2409.01704 • Published Sep 3 • 83

upvoted a paper 6 months ago

DreamBench++: A Human-Aligned Benchmark for Personalized Image Generation

Paper • 2406.16855 • Published Jun 24 • 54

upvoted a paper 8 months ago

OneChart: Purify the Chart Structural Extraction via One Auxiliary Token

Paper • 2404.09987 • Published Apr 15 • 2

upvoted a paper 11 months ago

Small Language Model Meets with Reinforced Vision Vocabulary

Paper • 2401.12503 • Published Jan 23 • 32

upvoted 2 papers about 1 year ago

Vary: Scaling up the Vision Vocabulary for Large Vision-Language Models

Paper • 2312.06109 • Published Dec 11, 2023 • 20

Merlin:Empowering Multimodal LLMs with Foresight Minds

Paper • 2312.00589 • Published Nov 30, 2023 • 24