Signin

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

Umar Jamil • January 23, 2025

Video Thumbnail

You May Also Like

Video Thumbnail

Reinforcement Learning from Human Feedback explained with math derivations and the PyTorch code.

Umar Jamil

Video Thumbnail

DeepSeek R1 Theory Overview | GRPO + RL + SFT

Deep Learning with Yacine

Video Thumbnail

Direct Preference Optimization (DPO) explained: Bradley-Terry model, log probabilities, math

Umar Jamil

Video Thumbnail

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

Joint Mathematics Meetings

Video Thumbnail

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

Yannic Kilcher

Video Thumbnail

Panagiotis Andreou (UNC), Homogeneity Fusion for Grouped Network VAR Models

VTSS

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

Quantum and the unknowable universe | FULL DEBATE | Roger Penrose, Sabine Hossenfelder, Slavoj Žižek

The Institute of Art and Ideas

Video Thumbnail

LoRA: Low-Rank Adaptation of Large Language Models - Explained visually + PyTorch code from scratch

Umar Jamil

Video Thumbnail

What Every Programmer Should Know about How CPUs Work • Matt Godbolt • GOTO 2024

GOTO Conferences

Video Thumbnail

The Biggest Misconception in Physics

Veritasium

Video Thumbnail

Prof. Judy Fan: Cognitive Tools for Making the Invisible Visible

MIT Quest for Intelligence

Video Thumbnail

Titans: Learning to Memorize at Test Time

Umar Jamil

Video Thumbnail

Retrieval Augmented Generation (RAG) Explained: Embedding, Sentence BERT, Vector Database (HNSW)

Umar Jamil

Video Thumbnail

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

Veritasium

Video Thumbnail

Why Can't We Make Simple Software? - Peter van Hardenberg

Handmade Cities

Video Thumbnail

Biggest Puzzle in Computer Science: P vs. NP

Quanta Magazine

Video Thumbnail

Father of AI: AI Needs PHYSICS to EVOLVE | prof. Yann LeCun

This Is World

Video Thumbnail

Transformers (how LLMs work) explained visually | DL5

3Blue1Brown

Umar Jamil

About

No channel description available.

Latest Posts

Video Thumbnail

Attention is all you need (Transformer) - Model explanation (including math), Inference and Training

Umar Jamil

Video Thumbnail

LoRA: Low-Rank Adaptation of Large Language Models - Explained visually + PyTorch code from scratch

Umar Jamil

Video Thumbnail

Distributed Training with PyTorch: complete tutorial with cloud infrastructure and code

Umar Jamil

Video Thumbnail

LLaMA explained: KV-Cache, Rotary Positional Embedding, RMS Norm, Grouped Query Attention, SwiGLU

Umar Jamil