Paper Reviews
Finetuning
- Direct Preference Optimization: Your Language Model is Secretly a Reward Model - 29 May 2023
- QLoRA: Efficient Finetuning of Quantized LLMs - 23 May 2023
- Constitutional AI: Harmlessness from AI Feedback - 15 December 2022
Language Models
- DeepSeek-V3.2: Pushing the Frontier of Open Large Language Models - 02 December 2025
- Kimi K2: Open Agentic Intelligence - 28 July 2025
- Qwen3 Technical Report - 14 May 2025
- DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning - 22 January 2025
- DeepSeek-V3 Technical Report - 27 December 2024
- Tulu 3: Pushing Frontiers in Open Language Model Post-Training - 22 November 2024
- Gemma 2: Improving Open Language Models at a Practical Size - 31 July 2024
- The Llama 3 Herd of Models - 31 July 2024
- DeepSeek-V2: A Strong, Economical, and Efficient Mixture-of-Experts Language Model - 07 May 2024
- DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models - 05 February 2024
- DeepSeek-Coder: When the Large Language Model Meets Programming - The Rise of Code Intelligence - 25 January 2024
- DeepSeekMoE: Towards Ultimate Expert Specialization in Mixture-of-Experts Language Models - 11 January 2024
- Mixtral of Experts - 08 January 2024
- DeepSeek LLM: Scaling Open-Source Language Models with Longtermism - 05 January 2024
- Mistral 7B - 10 October 2023
- Llama 2: Open Foundation and Fine-Tuned Chat Models - 18 July 2023
- LLaMA: Open and Efficient Foundation Language Models - 27 February 2023
Multimodal Learning
- Gemini 2.5: Pushing the Frontier with Advanced Reasoning, Multimodality, Long Context, and Next Generation Agentic Capabilities - 07 July 2025
- Gemma 3 Technical Report - 25 March 2025
- Pixtral 12B - 09 October 2024
- Gemini: A Family of Highly Capable Multimodal Models - 19 December 2023
Retrieval Augmented Generation
- LightRAG: Simple and Fast Retrieval-Augmented Generation - 08 October 2024
- From Local to Global: A Graph RAG Approach to Query-Focused Summarization - 24 April 2024
- RAPTOR: Recursive Abstractive Processing for Tree-Organized Retrieval - 31 January 2024
Agentic Ai
- 프롬프트에서 하네스까지 — AI 에이전틱 패턴 4년의 기록 - 05 April 2026
- From Prompts to Harnesses — Four Years of AI Agentic Patterns - 05 April 2026
- Claude Code Architecture Analysis - 31 March 2026
- Claude Code 내부 아키텍처 분석 - 31 March 2026