Do MLLMs Really See It: Reinforcing Visual Attention in Multimodal LLMs
Paper • 2602.08241 • Published
SAYO is a reasoning model trained with visual attention reward
Paper: https://arxiv.org/abs/2602.08241
Project URL: https://cratileo.github.io/Sayo-Pages/
- Downloads last month
- 7
Inference Providers NEW
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support