Deepseek R1 Articles

Page 1 of 1 (3 articles)

7/18/2026 • EN

Controlling Reasoning Effort in LLMs

Explains how LLMs learn low, medium, and high-effort reasoning modes, covering training techniques and effort settings.

Deepseek R1 Gpt 56 llm Reasoning Models Reinforcement Learning

Sebastian Raschka

12/19/2025 • EN

2025 LLM Year in Review

A review of key paradigm shifts in Large Language Models (LLMs) in 2025, focusing on RLVR training and new conceptual models of AI intelligence.

AI Research Deepseek R1 LLM Training Reinforcement Learning Rlvr

Andrej Karpathy

1/30/2025 • EN

Mini-R1: Reproduce Deepseek R1 „aha moment“ a RL tutorial

A tutorial on reproducing DeepSeek R1's RL 'aha moment' using Group Relative Policy Optimization (GRPO) to train a model on the Countdown numbers game.

Deepseek R1 Group Relative Policy Optimization Grpo Reasoning Reinforcement Learning

Philipp Schmid

Deepseek R1 Articles

Controlling Reasoning Effort in LLMs

2025 LLM Year in Review

Mini-R1: Reproduce Deepseek R1 „aha moment“ a RL tutorial

Select Language

We use cookies