📚 AI Paper Notes

Read a top-tier AI paper in 5 minutes — one repo to keep up with the latest AI progress.

• 📖 23,000+ AI · LLM · NLP · CV top-venue paper notes
• 🏛️ Covers ACL · CVPR · ICLR · AAAI · NeurIPS · ICCV · ICML · ECCV and more
• 🔬 Spans LLM Reasoning · VLM · Agent · RLHF · RAG · AIGC · Robotics and 55 research areas
• 🔄 Continuously updated

🌐 Read Online

https://en.papernotes.org/

💡 Tip: If math formulas don't render correctly, refreshing the page usually fixes it.

📊 Conference Coverage

| Conference | Notes | Full Paper List | |------------|------:|:----------------| | ICLR 2026 | 5,327 | ICLR2026-Papers.md → | | CVPR 2026 | 4,066 | CVPR2026-Papers.md → | | NeurIPS 2025 | 2,530 | NeurIPS2025-Papers.md → | | ACL 2025 | 1,853 | ACL2025-Papers.md → | | ICML 2026 | 1,846 | ICML2026-Papers.md → | | CVPR 2025 | 1,819 | CVPR2025-Papers.md → | | ACL 2026 | 1,419 | ACL2026-Papers.md → | | AAAI 2026 | 1,380 | AAAI2026-Papers.md → | | ICCV 2025 | 1,315 | ICCV2025-Papers.md → | | ICML 2025 | 1,060 | ICML2025-Papers.md → | | ECCV 2024 | 869 | ECCV2024-Papers.md → |

🗓️ Roadmap

Notes for the following conferences will be added once their acceptance lists are announced. All dates are estimates, subject to official announcements.

| Conference | Notification | List Released | Conference Dates | |------------|--------------|---------------|------------------| | ECCV 2026 | 2026-06 | 2026-07 | 2026-09 | | NeurIPS 2026 | 2026-09 | 2026-09 | 2026-12 | | EMNLP 2026 | 2026-08 | 2026-10 | 2026-10 | | AAAI 2027 | 2026-11 | 2026-12 | 2027-01 | | ICLR 2027 | 2027-01 | 2027-01 | 2027-04 | | CVPR 2027 | 2027-02 | 2027-03 | 2027-06 |

🔍 Research Areas

| Folder | Area | Notes | |--------|------|------:| | 3d_vision/ | 🧊 3D Vision | 2,003 | | ai_safety/ | 🛡️ AI Safety / Privacy | 637 | | aigc_detection/ | 🔎 AIGC Detection | 97 | | anomaly_detection/ | 🔍 Anomaly Detection | 17 | | audio_speech/ | 🎵 Audio & Speech | 386 | | autonomous_driving/ | 🚗 Autonomous Driving | 562 | | causal_inference/ | 🔗 Causal Inference | 158 | | code_intelligence/ | 💻 Code Intelligence | 199 | | computational_biology/ | 🧬 Computational Biology | 395 | | dialogue/ | 🗣️ Dialogue Systems | 75 | | earth_science/ | 🌍 Earth Science | 21 | | federated_learning/ | 🤝 Federated Learning | 19 | | graph_learning/ | 🕸️ Graph Learning | 343 | | hallucination/ | 👻 Hallucination Detection | 200 | | human_understanding/ | 🧑 Human Understanding | 415 | | image_generation/ | 🎨 Image Generation | 2,026 | | image_restoration/ | 🖼️ Image Restoration | 364 | | information_retrieval/ | 🔍 Information Retrieval / RAG | 336 | | interpretability/ | 🔬 Interpretability | 591 | | knowledge_editing/ | ✏️ Knowledge Editing | 67 | | learning_theory/ | 📐 Learning Theory | 382 | | llm_agent/ | 🦾 LLM Agent | 499 | | llm_alignment/ | ⚖️ Alignment / RLHF | 347 | | llm_efficiency/ | ⚡ LLM Efficiency | 353 | | llm_evaluation/ | 📊 LLM Evaluation | 483 | | llm_nlp/ | 💬 LLM (Other) | 745 | | llm_pretraining/ | 📚 Pretraining | 286 | | llm_reasoning/ | 💡 LLM Reasoning | 620 | | llm_safety/ | 🔒 LLM Safety | 555 | | medical_imaging/ | 🏥 Medical Imaging | 598 | | medical_nlp/ | 🩺 Medical NLP | 136 | | model_compression/ | 📦 Model Compression | 1,021 | | multi_agent/ | 🤝 Multi-Agent | 174 | | multilingual_mt/ | 🌐 Multilingual / Translation | 184 | | multimodal_vlm/ | 🧩 Multimodal VLM | 1,437 | | nlp_generation/ | ✍️ NLP Generation | 65 | | nlp_understanding/ | 📖 NLP Understanding | 75 | | object_detection/ | 🎯 Object Detection | 303 | | optimization/ | 📐 Optimization & Theory | 563 | | others/ | 📂 Others | 940 | | physics/ | ⚛️ Physics & Scientific Computing | 206 | | recommender/ | 🎁 Recommender Systems | 134 | | reinforcement_learning/ | 🎮 Reinforcement Learning | 873 | | remote_sensing/ | 🛰️ Remote Sensing | 131 | | robotics/ | 🤖 Robotics & Embodied AI | 583 | | scientific_computing/ | 🧮 Scientific Computing | 3 | | segmentation/ | ✂️ Segmentation | 485 | | self_supervised/ | 🔄 Self-Supervised Learning | 337 | | signal_comm/ | 📡 Signal & Communications | 38 | | social_computing/ | 👥 Social Computing | 150 | | time_series/ | 📈 Time Series | 306 | | video_generation/ | 🎬 Video Generation | 507 | | video_understanding/ | 📹 Video Understanding | 505 | | vlm_efficiency/ | ⚡ VLM Efficiency | 133 | | vlm_reasoning/ | 🧠 VLM Reasoning | 416 |

📂 Directory Structure

docs/
├── index.md                          # Site index (homepage with full-text search)
├── CVPR2026/
│   ├── index.md                      # Conference index (grouped by area)
│   ├── 3d_vision/
│   │   ├── index.md                  # Area index
│   │   ├── paperslug1.md           # Single paper note
│   │   ├── paperslug2.md
│   │   └── ...
│   ├── llm_reasoning/
│   ├── multimodal_vlm/
│   └── ...
├── ICML2026/
├── ACL2026/
├── ICLR2026/
├── AAAI2026/
├── NeurIPS2025/
├── ICCV2025/
├── ACL2025/
├── CVPR2025/
├── ICML2025/
└── ECCV2024/

📄 License

This project is licensed under CC BY-NC-SA 4.0.

• Attribution — please credit the source
• NonCommercial — not for commercial use
• ShareAlike — derivatives must be shared under the same license