EPISODE · Sep 19, 2025 · 11 MIN
DeepSeek-R1: Redefining AI Reasoning with Pure Reinforcement Learning
from The Deep Dive Lab: Unraveling Materials Science · host Son Hoang
Explore how DeepSeek-R1, a groundbreaking Chinese LLM, leverages the Group Relative Policy Optimization (GRPO) framework to master advanced reasoning in math and coding. With low training costs and open weights, this Nature-published model is reshaping global AI research.
What this episode covers
Explore how DeepSeek-R1, a groundbreaking Chinese LLM, leverages the Group Relative Policy Optimization (GRPO) framework to master advanced reasoning in math and coding. With low training costs and open weights, this Nature-published model is reshaping global AI research.
NOW PLAYING
DeepSeek-R1: Redefining AI Reasoning with Pure Reinforcement Learning
No transcript for this episode yet
Similar Episodes
No similar episodes found.
Similar Podcasts
No similar podcasts found.