Signin

DeepSeek R1 Theory Overview | GRPO + RL + SFT

Deep Learning with Yacine • February 23, 2025

Video Thumbnail

You May Also Like

Video Thumbnail

Segment Anything Model (SAM) - Foundational Model Deep Dive

Deep Learning with Yacine

Video Thumbnail

Group Relative Policy Optimization (GRPO) - Formula and Code

Deep Learning with Yacine

Video Thumbnail

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

Yannic Kilcher

Video Thumbnail

The moment we stopped understanding AI [AlexNet]

Welch Labs

Video Thumbnail

How to Train LLMs to "Think" (o1 & DeepSeek-R1)

Shaw Talebi

Video Thumbnail

How might LLMs store facts | DL7

3Blue1Brown

Video Thumbnail

How DeepSeek Rewrote the Transformer [MLA]

Welch Labs

Video Thumbnail

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

Umar Jamil

Video Thumbnail

DeepSeek is a Game Changer for AI - Computerphile

Computerphile

Video Thumbnail

The FASTEST introduction to Reinforcement Learning on the internet

Gonkee

Video Thumbnail

Visualizing transformers and attention | Talk for TNG Big Tech Day '24

Grant Sanderson

Video Thumbnail

Fine Tune DeepSeek R1 | Build a Medical Chatbot

DataCamp

Video Thumbnail

The Most Important Algorithm in Machine Learning

Artem Kirsanov

Video Thumbnail

Transformers (how LLMs work) explained visually | DL5

3Blue1Brown

Video Thumbnail

The Engineering Unlocks Behind DeepSeek | YC Decoded

Y Combinator

Video Thumbnail

DeepSeek-V3

Gabriel Mongaras

Video Thumbnail

How DeepSeek learns: GRPO explained with Triangle Creatures

Dr Mihai Nica

Video Thumbnail

Why Does Diffusion Work Better than Auto-Regression?

Algorithmic Simplicity

Video Thumbnail

DeepSeek R1 Theory Tutorial – Architecture, GRPO, KL Divergence

freeCodeCamp.org

Video Thumbnail

Stanford CS229 I Machine Learning I Building Large Language Models (LLMs)

Stanford Online

Deep Learning with Yacine

About

No channel description available.

Latest Posts

Video Thumbnail

DeepSeek R1 Theory Overview | GRPO + RL + SFT

Deep Learning with Yacine

Video Thumbnail

Group Relative Policy Optimization (GRPO) - Formula and Code

Deep Learning with Yacine

Video Thumbnail

Segment Anything Model (SAM) - Foundational Model Deep Dive

Deep Learning with Yacine

Video Thumbnail

ResNet Deep Neural Network Architecture Explained

Machine Learning Explained