Recent studies have shown that while Zero-style GRPO effectively enhances the math reasoning capabilities of base LLMs, it simultaneously degrades factuality: models begin producing repeated incorrect ...

This project introduces the fundamental mathematical principles that form the foundation of Machine Learning (ML). The notebook titled "Math_for_ML_Basics.ipynb" demonstrates essential concepts such ...

In a recent submission to the arXiv* server, researchers presented a method for fine-tuning open-source language models, enabling them to employ code for modeling and deriving mathematical equations, ...