AI/ML Research Papers Collection

A curated, pedagogically-organized collection of essential research papers spanning the landscape of artificial intelligence and machine learning — from the field's origins to the current frontier.

Jump to: The Collection · Pick Your Path · The Areas · Contributing · Resources · License

---

🎯 The Collection

This repository is a reading curriculum: 283 carefully selected research papers and policy documents, each with a short note on why it matters. There are three ways in:

1. 📚 Learn by area - 15 topic areas from the field's historical roots to the current frontier, plus curated tracks by goal
2. 📅 Browse by date - Every paper on one chronological timeline (1936-2026)
3. 📖 Look things up - 161 terms, concepts, and acronyms explained with context

---

🚀 Pick Your Path

• New to AI/ML? Start with the Classics for the story, then Foundations for the fundamentals — keep the Glossary nearby.
• ML practitioner? Follow the Practitioner Track: Language Models → Attention → Reasoning → Interpretability.
• Researcher? Browse the chronological view for the latest work, or deep-dive via the Researcher Track.
• Engineer? The Engineer Track prioritizes efficiency, safety, and hardware.
• Security specialist? Head to Security, Safety & Robustness via the Security Specialist Track.

All tracks, reading-order suggestions, and study tips live in learning-path.md.

---

🗺️ The Areas

<!-- COVERAGE:START (generated by scripts/validate.py --fix; do not hand-edit) -->

Every paper lives in exactly one area page, with a short "why it matters" note. Areas are listed in curriculum order:

| Area | Papers | What's inside | |------|--------|---------------| | 🏺 Classics | 29 | Computation & the First Neurons · Perceptrons & the First Winter · Backprop's Prehistory & Associative Memory · Attractors & Self-Organization · The Connectionist Revival · Limits, Winter, and the Way Out · Guides & Retrospectives | | 🏗️ Foundations | 25 | Deep Learning Basics · Word Embeddings & Representations · Sequence Models · Generative Models · Tokenization & Subword Models | | 🤖 Language Models | 21 | LLM Foundations · Training at Scale · Memory & Efficiency Optimizations | | ⚡ Attention | 11 | Efficient Attention · Long Context & Compression | | 🔍 Retrieval & RAG | 11 | Retrieval-Augmented Generation (RAG) · Federated & Distributed Learning | | 🧠 Reasoning & Agents | 22 | Teaching Models to Reason · Agentic Systems | | 🏛️ Architectures | 18 | Alternative Architectures · Theoretical Foundations | | 🔬 Interpretability | 16 | Understanding Model Behavior · Model Evaluation & Robustness | | 🛡️ Safety & Security | 36 | AI Alignment & Safety Training · Security Threats & Attacks · Safety Evaluation & Red Teaming · Bias, Fairness & Robustness · Harmful Content & Misinformation · Long-term Safety Research | | 🎯 Advanced | 8 | Automated AI Research · Specialized Applications · Consciousness & AGI | | 🎲 Probabilistic | 9 | Probabilistic Programming · Diffusion Models · Generative Models for Vision | | 👁️ Vision & Multimodal | 11 | Vision Transformers · Multimodal & Speech · Vision Interpretability | | ⚙️ Hardware & Systems | 5 | Hardware Considerations | | 🧠 Human-AI Interaction | 11 | Trust, Reliance & Automation Bias · Cognitive Effects of AI · Human-AI Decision-Making | | 📜 Policy & Governance | 53 | Financial Services & Model Risk Management · Data Protection & Privacy Law · AI-Specific Legislation & Executive Action · Risk Management Frameworks & Standards · Sector-Specific AI Guidance · Dual-Use AI & National Security · Responsible AI & Industry Best Practices |

<!-- COVERAGE:END -->

Total: 283 papers across 15 areas (including 53 policy documents & frameworks)

---

🤝 Contributing

We welcome contributions! There are many ways to help:

| Contribution Type | How to Help | |-------------------|-------------| | 📄 Suggest Papers | Open an issue with paper details | | 🔗 Fix Broken Links | Report or submit a PR | | 📖 Improve Glossary | Suggest terms or definitions | | ✏️ Better Annotations | Improve "Why" explanations via PR | | 💬 Discuss Papers | Join Discussions |

📋 Read the full Contributing Guide for detailed instructions, paper selection criteria, and style guidelines

---

📚 Additional Resources

Related Collections

• Papers We Love - Classic CS papers
• Awesome Deep Learning Papers - DL fundamentals
• ML Papers of The Week - Weekly updates

Tools & Platforms

• arXiv - Preprint repository
• Papers With Code - Papers + implementations
• Semantic Scholar - AI-powered paper search
• Connected Papers - Visual paper exploration

Conference Deadlines

• 🎓 AI Deadlines - Track ML/AI conference submissions

---

📄 License

The curation, organization, and annotations in this repository are licensed under the Apache License 2.0.

The linked papers themselves remain under their original licenses and copyrights held by their authors and publishers; this repository only links to them.

---

🙏 Acknowledgments

Papers compiled from:

• Major AI/ML conferences (NeurIPS, ICML, ICLR, CVPR, ACL, etc.)
• Leading research institutions and labs
• arXiv preprint server
• Open access initiatives

Special thanks to the researchers, authors, and institutions making their work freely available.

---

📬 Contact & Feedback

Found this helpful? Have suggestions? Want to discuss a paper?

• Issues: Open an issue for bugs, suggestions, or paper recommendations
• Discussions: Start a discussion for paper analysis or learning questions

---

Happy Reading! 📖🚀

Building knowledge, one paper at a time.