AI Research Papers
Plain-language TL;DR summaries of the most influential AI research papers. Each entry covers what the paper does, why it matters, and links to the full text.
- Gemini 3 and Gemini 2.5 - Google DeepMind (2025-2026)Read summary
- GPT-5 System Card - OpenAI (August 2025)Read summary
- Claude 4 System Card - Anthropic (May 2025)Read summary
- DeepSeek-R1: Incentivizing Reasoning via Reinforcement Learning (January 2025)Read summary
- LLaMA 4: Natively Multimodal Open-Source AI - Meta (April 2025)Read summary
- Circuit Tracing: Mechanistic Interpretability Breakthrough - Anthropic (2025)Read summary
- Meta Chain-of-Thought: System 2 Reasoning in LLMs (January 2025)Read summary
- Alignment Faking in Large Language Models - Anthropic (December 2024)Read summary
- From LLM Reasoning to Autonomous AI Agents: A Comprehensive Review (2025)Read summary
- AlphaGenome and AI for Science - Google DeepMind (2025-2026)Read summary
- Gemini: A Family of Highly Capable Multimodal Models (2023)Read summary
- The Claude 3 Model Family (2024)Read summary
- Direct Preference Optimization: Your Language Model Is Secretly a Reward Model (2023)Read summary
- Tree of Thoughts: Deliberate Problem Solving with Large Language Models (2023)Read summary
- Switch Transformers: Scaling to Trillion Parameter Models (2022)Read summary
- Mistral 7B (2023)Read summary
- LoRA: Low-Rank Adaptation of Large Language Models (2021)Read summary
- High-Resolution Image Synthesis with Latent Diffusion Models (2022)Read summary
- Denoising Diffusion Probabilistic Models (2020)Read summary
- DALL-E: Zero-Shot Text-to-Image Generation (2021)Read summary
- Scaling Laws for Neural Language Models (2020)Read summary
- Chain-of-Thought Prompting Elicits Reasoning in Large Language Models (2022)Read summary
- Retrieval-Augmented Generation for Knowledge-Intensive NLP Tasks (2020)Read summary
- GPT-4 Technical Report (2023)Read summary
- LLaMA: Open and Efficient Foundation Language Models (2023)Read summary
- Constitutional AI: Harmlessness from AI Feedback (2022)Read summary
- Training Language Models to Follow Instructions with Human Feedback (2022)Read summary
- Language Models Are Few-Shot Learners - GPT-3 (2020)Read summary
- BERT: Pre-training of Deep Bidirectional Transformers (2018)Read summary
- Attention Is All You Need (2017)Read summary