9 6 131

Attashe

attashe

attashe

AI & ML interests

Neural Network, Object detection, Generative Art

Recent Activity

liked a model 7 days ago

nvidia/C-RADIOv4-H

upvoted a paper 9 days ago

Memory-V2V: Augmenting Video-to-Video Diffusion Models with Memory

reacted to imnotkitty's post with 🔥 9 days ago

📌Same day, Two Releases. Jan 27th just got interesting on Open-source AI modles. ✅Kimi K2.5: How to make models "think" across text and vision natively? https://huggingface.co/moonshotai/Kimi-K2.5 ✅DeepSeek-OCR 2: How to make models "see" more like humans, not scanners? https://huggingface.co/deepseek-ai/DeepSeek-OCR-2 One focuses on depth of reasoning, the other on precision of vision. What's the key differentiator for a multimodal model in your view: raw power or computational elegance?

View all activity

Organizations

liked a model 7 days ago

nvidia/C-RADIOv4-H

Feature Extraction • 0.7B • Updated 8 days ago • 5.87k • 33

upvoted a paper 9 days ago

Memory-V2V: Augmenting Video-to-Video Diffusion Models with Memory

Paper • 2601.16296 • Published 16 days ago • 28

reacted to imnotkitty's post with 🔥 9 days ago

Post

2300

📌Same day, Two Releases.

Jan 27th just got interesting on Open-source AI modles.
✅Kimi K2.5: How to make models "think" across text and vision natively?
moonshotai/Kimi-K2.5
✅DeepSeek-OCR 2: How to make models "see" more like humans, not scanners?
deepseek-ai/DeepSeek-OCR-2

One focuses on depth of reasoning, the other on precision of vision.
What's the key differentiator for a multimodal model in your view: raw power or computational elegance?