Skip to content
AI.info
News
Tools
Research
Learn
AI.info
Sadegh Mahdavi
Explore Sadegh Mahdavi on AI.info.
An Open Recipe for IMO Gold: Training Nemotron for Olympiad Mathematics
NVIDIA Nemotron 3: Efficient and Open Intelligence
Advantage Shaping as Surrogate Reward Maximization: Unifying Pass@K Policy Gradients
Page 1