Writings and projects

Pasquale Casciano

HOME
CATEGORIES
TAGS
ARCHIVES
ABOUT

Home Tags KL Divergence

Tag

KL Divergence 1

Post-training degli LLM: PPO e GRPO Oct 10, 2026

Recently Updated

Post-training degli LLM: dati e token
Post-training degli LLM: PPO e GRPO
Post-training degli LLM: reward, reward model e RLHF
Post-training degli LLM: fine-tuning e reinforcement learning
Post-training in pratica: reasoning, Constitutional AI e pipeline reali

Trending Tags

Post-Training Machine Learning Agentic Memory AI AWS Embedding LangChain Memory Manager pgvector PostgreSQL

© 2026 Pasquale Casciano. Some rights reserved.

Using the Chirpy theme for Jekyll.

Trending Tags

Post-Training Machine Learning Agentic Memory AI AWS Embedding LangChain Memory Manager pgvector PostgreSQL

New content available