GRPO's new variants and implementation secrets

GRPO's new variants and implementation secrets
Share:

Download MP3


Similar Tracks

Experimenting with Reinforcement Learning with Verifiable Rewards (RLVR) Nathan Lambert
How to approach post-training for AI applications Nathan Lambert
DPO Debate: Is RL needed for RLHF? Nathan Lambert
How DeepSeek learns: GRPO explained with Triangle Creatures Dr Mihai Nica
MINIMUM TIME TO REACH LAST ROOM II | LeetCode 3342 | Dijkstra's Algorithm R Sai Siddhu
What Textbooks Don't Tell You About Curve Fitting Artem Kirsanov
Lofi hip hop mix - Beats to Relax/Study to [2018] Lofi Girl
An update on DPO vs PPO for LLM alignment Nathan Lambert
[Talk] Dissertation Talk: Synergy of Prediction and Control in Model-based Reinforcement Learning Nathan Lambert
The Magic of LLM Distillation — Rishabh Agarwal, Google DeepMind Latent Space
Model Context Protocol (MCP), clearly explained (why it matters) Greg Isenberg
[GRPO Explained] DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models Yannic Kilcher
Everything You Wanted to Know About LLM Post-Training, with Nathan Lambert of Allen Institute for AI Cognitive Revolution \
How does GRPO work? Trelis Research
Early stages of the reinforcement learning era of language models Nathan Lambert
DeepSeek R1 Theory Overview | GRPO + RL + SFT Deep Learning with Yacine
Transformers (how LLMs work) explained visually | DL5 3Blue1Brown