[SUBS]RANK
VIDEOS / YANNIC KILCHER / BAWV_YRQX4W

[GRPO Explained] DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models

Yannic Kilcher YANNIC KILCHER · SEP 10, 2025

This YouTube video has 174 000 views and was published Sep 10, 2025 on Yannic Kilcher. That is 3.3x the channel's average views.

[GRPO Explained] DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models ▸ WATCH ON YOUTUBE
Views
174 000
Likes
—
Comments
—
Like rate
—
▸ Vs channel average
+229%
This video is at 3.3x the channel's average views.
LAST 13 UPLOADS · ■ THIS VIDEO
Yannic Kilcher
Yannic Kilcher
@YannicKilcher · 331K SUBS · 90 VIDEOS
AUDIT →
More from this channel
I BUILT A FULLY AUTOMATIC MANSPLAINER I BUILT A FULLY AUTOMATIC MANSPLAINER 11 000 VIEWS · 7MO AGO Titans: Learning to Memorize at Test Time (Paper Analysis) Titans: Learning to Memorize at Test Time (Paper Analysis) 24 000 VIEWS · 9MO AGO TiDAR: Think in Diffusion, Talk in Autoregression (Paper Analysis) TiDAR: Think in Diffusion, Talk in Autoregression (Paper Analysis) 23 000 VIEWS · 9MO AGO [Paper Analysis] On the Theoretical Limitations of Embedding-Based Retrieval (Warning: Rant) [Paper Analysis] On the Theoretical Limitations of Embedding-Based Retrieval (Warning: Rant) 36 000 VIEWS · 11MO AGO