Signin

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

Yannic Kilcher • February 2, 2025

Video Thumbnail

You May Also Like

Video Thumbnail

On the Biology of a Large Language Model (Part 1)

Yannic Kilcher

Video Thumbnail

DeepSeek R1 Theory Overview | GRPO + RL + SFT

Deep Learning with Yacine

Video Thumbnail

The Man Who Almost Broke Math (And Himself...)

Veritasium

Video Thumbnail

Were RNNs All We Needed? (Paper Explained)

Yannic Kilcher

Video Thumbnail

How DeepSeek Rewrote the Transformer [MLA]

Welch Labs

Video Thumbnail

Veritasium: What Everyone Gets Wrong About AI and Learning – Derek Muller Explains

Perimeter Institute for Theoretical Physics

Video Thumbnail

How I use LLMs

Andrej Karpathy

Video Thumbnail

Why Does Diffusion Work Better than Auto-Regression?

Algorithmic Simplicity

Video Thumbnail

DeepSeek R1 Explained to your grandma

AI with Alex

Video Thumbnail

DeepSeek's GRPO (Group Relative Policy Optimization) | Reinforcement Learning for LLMs

Julia Turc

Video Thumbnail

Mixtral of Experts (Paper Explained)

Yannic Kilcher

Video Thumbnail

How DeepSeek learns: GRPO explained with Triangle Creatures

Dr Mihai Nica

Video Thumbnail

Why Trump's Tariffs Are Doomed To Fail

Adam Something

Video Thumbnail

The Biggest Misconception in Physics

Veritasium

Video Thumbnail

Scaling LLM Test-Time Compute Optimally can be More Effective than Scaling Model Parameters (Paper)

Yannic Kilcher

Video Thumbnail

Building a fully local "deep researcher" with DeepSeek-R1

LangChain

Video Thumbnail

The Most Important Algorithm in Machine Learning

Artem Kirsanov

Video Thumbnail

Paper: DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning

Umar Jamil

Video Thumbnail

Yann LeCun "Mathematical Obstacles on the Way to Human-Level AI"

Joint Mathematics Meetings

Video Thumbnail

NVIDIA CEO Jensen Huang's Vision for the Future

Cleo Abram

Yannic Kilcher

About

No channel description available.

Latest Posts

Video Thumbnail

All about AI Accelerators: GPU, TPU, Dataflow, Near-Memory, Optical, Neuromorphic & more (w/ Author)

Yannic Kilcher

Video Thumbnail

xLSTM: Extended Long Short-Term Memory

Yannic Kilcher

Video Thumbnail

Leave No Context Behind: Efficient Infinite Context Transformers with Infini-attention

Yannic Kilcher

Video Thumbnail

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

Yannic Kilcher