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

Обзор теории DeepSeek R1 | GRPO + RL + SFT

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

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

Yann LeCun | Self-Supervised Learning, JEPA, World Models, and the future of AI

Понимание рассуждений LLM (o1/o3, DeepSeek-R1, Gemini Thinking, Grok 3, Claude 3.7)

Внимание — это всё, что вам нужно (Transformer) — объяснение модели (включая математику), вывод и...

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

[Full Workshop] Reinforcement Learning, Kernels, Reasoning, Quantization & Agents — Daniel Han

The ONLY DeepSeek GRPO/PPO video you'll EVER need (with examples and exercises) | RL Foundations

How DeepSeek Rewrote the Transformer [MLA]

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

How Did They Do It? DeepSeek V3 and R1 Explained

LLM и GPT - как работают большие языковые модели? Визуальное введение в трансформеры

How I finetuned a Small LM to THINK and solve puzzles on its own (GRPO & RL!)

Теренс Тао о том, как Григорий Перельман решил гипотезу Пуанкаре | Лекс Фридман

The Key Equation Behind Probability

Train Your Own Reasoning Model (DeepSeek Clone) Fast & With Only 7Gb Of VRAM

Direct Preference Optimization (DPO) - How to fine-tune LLMs directly without reinforcement learning

DeepSeek R1: объяснение твоей бабушке

GRPO - Group Relative Policy Optimization - How DeepSeek trains reasoning models