Haoran Wei

HaoranWei's activity

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

commented a paper 1 day ago

Unlimited OCR Works

Paper • 2606.23050 • Published 5 days ago • 37 •

4

liked a Space 3 days ago

Running on Zero

Agents

53

Unlimited OCR

🏆

53

Extract text from images and PDFs with streaming OCR

upvoted a paper 4 days ago

Unlimited OCR Works

Paper • 2606.23050 • Published 5 days ago • 37

liked a model 5 days ago

baidu/Unlimited-OCR

Image-Text-to-Text • 3B • Updated 3 days ago • 213k • 1.09k

liked 2 models 2 months ago

deepseek-ai/DeepSeek-V4-Flash

Text Generation • 158B • Updated 5 days ago • 2.03M • • 1.61k

deepseek-ai/DeepSeek-V4-Pro

Text Generation • 862B • Updated 5 days ago • 1.17M • • 5.08k

upvoted 4 papers 5 months ago

MemOCR: Layout-Aware Visual Memory for Efficient Long-Horizon Reasoning

Paper • 2601.21468 • Published Jan 29 • 25

CodeOCR: On the Effectiveness of Vision Language Models in Code Understanding

Paper • 2602.01785 • Published Feb 2 • 97

Length-Unbiased Sequence Policy Optimization: Revealing and Controlling Response Length Variation in RLVR

Paper • 2602.05261 • Published Feb 5 • 54

ReGuLaR: Variational Latent Reasoning Guided by Rendered Chain-of-Thought

Paper • 2601.23184 • Published Jan 30 • 36

updated a model 5 months ago

deepseek-ai/DeepSeek-OCR-2

Image-Text-to-Text • 3B • Updated Feb 3 • 3.09M • 1.01k

upvoted a collection 5 months ago

DeepSeek-OCR

Collection

2 items • Updated Feb 2 • 33

upvoted a paper 5 months ago

DeepSeek-OCR 2: Visual Causal Flow

Paper • 2601.20552 • Published Jan 28 • 71

liked a model 5 months ago

deepseek-ai/DeepSeek-OCR-2

Image-Text-to-Text • 3B • Updated Feb 3 • 3.09M • 1.01k

published a model 5 months ago

deepseek-ai/DeepSeek-OCR-2

Image-Text-to-Text • 3B • Updated Feb 3 • 3.09M • 1.01k

liked a Space 5 months ago

Running

Agents

25

Step3 VL 10B

💬

25

Chat with a multimodal AI using text and images

upvoted a paper 5 months ago

STEP3-VL-10B Technical Report

Paper • 2601.09668 • Published Jan 14 • 196

liked a model 5 months ago

stepfun-ai/Step3-VL-10B

Image-Text-to-Text • 10B • Updated Feb 4 • 455k • 410

upvoted 2 papers 6 months ago

BabyVision: Visual Reasoning Beyond Language

Paper • 2601.06521 • Published Jan 10 • 201

AgentOCR: Reimagining Agent History via Optical Self-Compression

Paper • 2601.04786 • Published Jan 8 • 31