Unifying LLM Post-Training: From SFT and RL to Hybrid Approaches

Unifying LLM Post-Training: From SFT and RL to Hybrid Approaches

This episode of The ML Digest covers the paper “Towards a Unified View of Large Language Model Post-Training” from researchers at Tsinghua University, Shanghai AI Lab, and WeChat AI. The authors argue that seemingly distinct approaches—Supervised Fine-Tuning (SFT) with offline demonstrations and Reinforcement Learning (RL) with online rollouts—are in fact instances of a single optimization process. Link to original paper: https://arxiv.org/pdf/2509.04419

Are Small Language Models the Future of Agentic AI?

In this episode we go over the recent NVIDIA paper titled "Small Language Models are the Future of Agentic AI." Link to the original paper: https://arxiv.org/pdf/2506.02153