Przejdź do treści
Global sound
KnowledgeDB.ai

KnowledgeDB.ai

LLM Post-Training: Reinforcement Learning, Scaling, and Fine-Tuning

· 53 min

Notatki do odcinka

Ref: https://arxiv.org/abs/2502.21321

This document provides a comprehensive survey of post-training methodologies for Large Language Models (LLMs), focusing on refining reasoning capabilities and aligning models with user preferences and ethical standards.
It categorizes these methodologies into fine-tuning, reinforcement learning (RL), and test-time scaling, while exploring the challenges and advancements in each area. The study highlights various techniques such as Proximal Policy Optimization (PPO), Direct Preference Optimization (DPO), and Group Relative Policy Optimization (GRPO), and…

Strona: podcasters.spotify.com

Na żywo, ostatnia godzina: 11 803 utworów na 6 226 stacjach w 147 krajach

Odkrywaj świat przez radio

Więcej sposobów na odkrywanie (9)

Usłyszałeś coś fajnego? Zapisz to albo otwórz od razu w Spotify.

★ Artist of the week The fastest riser on the radio this week
Your song here? From € 9 per week →
Radio Voz de ArariSłuchaj dalej