On RL Objectives and Credit Assignment for LLMs less than 1 minute read Published: October 21, 2026Maximum Entropy RL :\[J(\theta) = \sum_t \mathbb{E}_{\tau \sim \pi_\theta(\tau)} \left[ r(s_t, a_t) + \beta H\!\left(\pi_\theta(\cdot \mid s_t)\right) \right]\]Share on Twitter Facebook Previous Next
Flow Matching 16 minute read Published: June 15, 2025Flow matching gives us a way to model complex real world distributions (target) from simpler or known distrubitions (source).
