Richards Brent

rch-rico07

1 5

·

AI & ML interests

OCR Gen + LL T

Recent Activity

liked a Space 9 days ago

cinderholm/wan2-2-i2v-v3

liked a Space 13 days ago

davanstrien/ocr-time-capsule

liked a Space 13 days ago

google/gemma4_vision_token_budget

View all activity

Organizations

None yet

liked a Space 9 days ago

Wan2.2 14B Fast Preview [NEW]

Generate animated video from a single image with custom prompts

liked 2 Spaces 13 days ago

OCR Time Capsule

Compare original and improved OCR text from historical documents

Gemma 4 - Vision Token Budget

Resize images for visual token budgets while keeping aspect ratio

liked 2 models 13 days ago

moonshotai/Kimi-K3

Image-Text-to-Text • 2.8T • Updated 13 days ago • 1.46M • • 10.4k

baidu/Unlimited-OCR

Image-Text-to-Text • 3B • Updated 12 days ago • 2.89M • 3.99k

upvoted a paper 13 days ago

Aesthetics is Cheap, Show me the Text: An Empirical Evaluation of State-of-the-Art Generative Models for OCR

Paper • 2507.15085 • Published Jul 20, 2025 • 8