Technology ❯Artificial Intelligence ❯Model Training

Supervised Learning

Reinforcement Learning Fine-Tuning Techniques Supervised Fine-Tuning

Microsoft Unveils Phi-4 Reasoning Models That Outperform Larger AI Systems

The new Phi-4-reasoning, Phi-4-reasoning-plus, and Phi-4-mini-reasoning models deliver advanced reasoning capabilities with smaller sizes, open weights, and broad deployment options.