SmolDocling: An Ultra-Compact VLM for Document Understanding

Creating artificial doubt significantly improves AI math accuracy

Step-by-step reasoning can fix madman logic in vision AI

All LLMs use tokenization. Are we doing it totally wrong?

Can image models understand what we’re asking for?

Teaching AI to tell visually consistent stories

Bye tokens, hello patches

SmolDocling: An Ultra-Compact VLM for Document Understanding

Creating artificial doubt significantly improves AI math accuracy

Step-by-step reasoning can fix madman logic in vision AI

All LLMs use tokenization. Are we doing it totally wrong?

Can image models understand what we’re asking for?

Teaching AI to tell visually consistent stories

Bye tokens, hello patches