📚 AI Conference Paper Notes

AI / LLM / NLP / CV top-venue paper notes — 5-minute reads of core ideas.
Covers ACL · CVPR · ICLR · AAAI · NeurIPS · ICCV · ICML · ECCV
Continuously updated

25457Notes

12Conferences

56Areas

---

NEW

🎞️ ECCV2026

1970 notes · 48 areas

LLM

LLM Reasoning 1 LLM Agent 30 Multi-Agent 5 Alignment & RLHF 3 LLM Safety 13 Hallucination Detection 11 LLM Evaluation 2 Pretraining 4 Knowledge Editing 1 LLM (Other) 3

LLM Applications

Information Retrieval & RAG 7 Code Intelligence 1

Generation & Multimodal

Image Generation 226 Video Generation 143 Multimodal VLM 164 VLM Reasoning 118 VLM Efficiency 44 Audio & Speech 15 AIGC Detection 8

Visual Perception

3D Vision 326 Object Detection 54 Segmentation 61 Image Restoration 53 Remote Sensing 26 Anomaly Detection 8 Human Understanding 83 Video Understanding 80

Decision & Embodied

Autonomous Driving 109 Robotics & Embodied AI 106 Reinforcement Learning 6

Foundations & Theory

Self-Supervised Learning 16 Optimization & Theory 10 Learning Theory 1 Causal Inference 3 Interpretability 17 Model Compression 69 Graph Learning 1 Federated Learning 2 Time Series 3

Science & Cross-Disciplinary

Medical Imaging 63 Computational Biology 2 Physics & Scientific Computing 4 Earth Science 4 Signal & Communications 6 Social Computing 2 AI Safety 23

Others

Others 32 transfer_learning 1

📷 CVPR2026

4067 notes · 46 areas

LLM

LLM Reasoning 16 LLM Agent 42 Multi-Agent 2 Alignment & RLHF 12 LLM Safety 12 Hallucination Detection 33 LLM Efficiency 8 Pretraining 5 Knowledge Editing 2 LLM (Other) 3

Generation & Multimodal

Image Generation 492 Video Generation 182 Multimodal VLM 419 VLM Reasoning 150 VLM Efficiency 63 Audio & Speech 22 AIGC Detection 10

Visual Perception

3D Vision 751 Object Detection 99 Segmentation 122 Image Restoration 135 Remote Sensing 63 Anomaly Detection 7 Human Understanding 151 Video Understanding 187

Decision & Embodied

Autonomous Driving 157 Robotics & Embodied AI 146 Reinforcement Learning 25

Foundations & Theory

Self-Supervised Learning 92 Optimization & Theory 22 Causal Inference 4 Interpretability 34 Model Compression 108 Graph Learning 8 Federated Learning 19 Time Series 7

Science & Cross-Disciplinary

Medical Imaging 173 Medical LLM 1 Computational Biology 21 Physics & Scientific Computing 2 Scientific Computing 3 Earth Science 2 Signal & Communications 2 Social Computing 3 AI Safety 145

Others

Others 105

🔬 ICLR2026

5331 notes · 53 areas

LLM

LLM Reasoning 241 LLM Agent 162 Multi-Agent 47 Alignment & RLHF 102 LLM Safety 185 Hallucination Detection 40 LLM Evaluation 131 LLM Efficiency 171 Pretraining 79 Knowledge Editing 15 LLM (Other) 56

LLM Applications

NLP Understanding 2 Text Generation 12 Dialogue Systems 10 Multilingual & Translation 8 Information Retrieval & RAG 81 Code Intelligence 59

Generation & Multimodal

Image Generation 353 Video Generation 98 Multimodal VLM 211 VLM Reasoning 112 VLM Efficiency 18 Audio & Speech 80 AIGC Detection 30

Visual Perception

3D Vision 197 Object Detection 31 Segmentation 32 Image Restoration 61 Remote Sensing 11 Anomaly Detection 10 Human Understanding 45 Video Understanding 48

Decision & Embodied

Autonomous Driving 50 Robotics & Embodied AI 162 Reinforcement Learning 400 Recommender Systems 24

Foundations & Theory

Self-Supervised Learning 81 Optimization & Theory 222 Learning Theory 293 Causal Inference 64 Interpretability 196 Model Compression 240 Graph Learning 118 Time Series 121

Science & Cross-Disciplinary

Medical Imaging 88 Medical LLM 20 Computational Biology 156 Physics & Scientific Computing 69 Earth Science 7 Signal & Communications 8 Social Computing 17 AI Safety 141

Others

Others 116

💬 ACL2026

1416 notes · 38 areas

LLM

LLM Reasoning 82 LLM Agent 82 Multi-Agent 40 Alignment & RLHF 38 LLM Safety 115 Hallucination Detection 28 LLM Evaluation 97 LLM Efficiency 23 Pretraining 12 Knowledge Editing 10 LLM (Other) 62

LLM Applications

NLP Understanding 34 Text Generation 17 Dialogue Systems 26 Multilingual & Translation 64 Information Retrieval & RAG 73 Code Intelligence 49

Generation & Multimodal

Image Generation 5 Video Generation 4 Multimodal VLM 82 VLM Reasoning 32 VLM Efficiency 6 Audio & Speech 71 AIGC Detection 17

Decision & Embodied

Robotics & Embodied AI 11 Reinforcement Learning 46 Recommender Systems 22

Foundations & Theory

Self-Supervised Learning 1 Causal Inference 7 Interpretability 63 Model Compression 59 Graph Learning 24 Time Series 8

Science & Cross-Disciplinary

Medical LLM 47 Computational Biology 5 Social Computing 45 AI Safety 5

Others

Others 4

🧪 ICML2026

1846 notes · 51 areas

LLM

LLM Reasoning 78 LLM Agent 59 Multi-Agent 24 Alignment & RLHF 37 Hallucination Detection 21 LLM Evaluation 40 LLM Efficiency 48 Pretraining 27 Knowledge Editing 8 LLM (Other) 39

LLM Applications

NLP Understanding 2 Text Generation 2 Dialogue Systems 5 Multilingual & Translation 3 Information Retrieval & RAG 26 Code Intelligence 22

Generation & Multimodal

Image Generation 141 Video Generation 32 Multimodal VLM 89 VLM Reasoning 31 VLM Efficiency 4 Audio & Speech 36 AIGC Detection 11

Visual Perception

3D Vision 30 Object Detection 7 Segmentation 14 Image Restoration 21 Remote Sensing 3 Human Understanding 5 Video Understanding 17

Decision & Embodied

Autonomous Driving 8 Robotics & Embodied AI 53 Reinforcement Learning 110 Recommender Systems 11

Foundations & Theory

Self-Supervised Learning 28 Optimization & Theory 88 Learning Theory 45 Causal Inference 19 Interpretability 91 Model Compression 117 Graph Learning 35 Time Series 45

Science & Cross-Disciplinary

Medical Imaging 28 Medical LLM 4 Computational Biology 52 Physics & Scientific Computing 33 Earth Science 2 Signal & Communications 2 Social Computing 9 AI Safety 114

Others

Others 70

🤖 AAAI2026

1381 notes · 52 areas

LLM

LLM Reasoning 37 LLM Agent 33 Multi-Agent 26 Alignment & RLHF 17 LLM Safety 41 Hallucination Detection 15 LLM Evaluation 16 LLM Efficiency 9 Pretraining 9 Knowledge Editing 4 LLM (Other) 29

LLM Applications

NLP Understanding 1 Text Generation 3 Dialogue Systems 5 Multilingual & Translation 9 Information Retrieval & RAG 21 Code Intelligence 10

Generation & Multimodal

Image Generation 79 Video Generation 11 Multimodal VLM 75 VLM Reasoning 10 VLM Efficiency 5 Audio & Speech 30 AIGC Detection 2

Visual Perception

3D Vision 79 Object Detection 29 Segmentation 29 Image Restoration 10 Remote Sensing 7 Human Understanding 20 Video Understanding 27

Decision & Embodied

Autonomous Driving 56 Robotics & Embodied AI 30 Reinforcement Learning 58 Recommender Systems 27

Foundations & Theory

Self-Supervised Learning 16 Optimization & Theory 21 Learning Theory 3 Causal Inference 7 Interpretability 37 Model Compression 60 Graph Learning 37 Time Series 31

Science & Cross-Disciplinary

Medical Imaging 76 Medical LLM 12 Computational Biology 20 Physics & Scientific Computing 15 Earth Science 2 Signal & Communications 3 Social Computing 10 AI Safety 45

Others

Others 117

🧠 NeurIPS2025

2530 notes · 51 areas

LLM

LLM Reasoning 82 LLM Agent 39 Multi-Agent 17 Alignment & RLHF 36 LLM Safety 81 Hallucination Detection 17 LLM Evaluation 38 LLM Efficiency 34 Pretraining 51 Knowledge Editing 6 LLM (Other) 54

LLM Applications

NLP Understanding 3 Dialogue Systems 8 Multilingual & Translation 11 Information Retrieval & RAG 25 Code Intelligence 19

Generation & Multimodal

Image Generation 221 Video Generation 23 Multimodal VLM 107 VLM Reasoning 30 VLM Efficiency 8 Audio & Speech 47 AIGC Detection 9

Visual Perception

3D Vision 116 Object Detection 27 Segmentation 45 Image Restoration 26 Remote Sensing 12 Human Understanding 21 Video Understanding 39

Decision & Embodied

Autonomous Driving 47 Robotics & Embodied AI 75 Reinforcement Learning 143 Recommender Systems 24

Foundations & Theory

Self-Supervised Learning 35 Optimization & Theory 126 Learning Theory 25 Causal Inference 20 Interpretability 80 Model Compression 143 Graph Learning 54 Time Series 54

Science & Cross-Disciplinary

Medical Imaging 77 Medical LLM 17 Computational Biology 76 Physics & Scientific Computing 57 Earth Science 6 Signal & Communications 5 Social Computing 20 AI Safety 73

Others

Others 121

📹 ICCV2025

1315 notes · 44 areas

LLM

LLM Reasoning 3 LLM Agent 4 Alignment & RLHF 2 LLM Safety 10 Hallucination Detection 5 LLM Evaluation 27 LLM Efficiency 1 Pretraining 9 LLM (Other) 6

LLM Applications

NLP Understanding 1 Text Generation 1 Multilingual & Translation 1 Information Retrieval & RAG 5 Code Intelligence 1

Generation & Multimodal

Image Generation 213 Video Generation 49 Multimodal VLM 119 VLM Reasoning 15 VLM Efficiency 11 Audio & Speech 11

Visual Perception

3D Vision 267 Object Detection 28 Segmentation 73 Image Restoration 31 Remote Sensing 11 Human Understanding 41 Video Understanding 56

Decision & Embodied

Autonomous Driving 91 Robotics & Embodied AI 26 Reinforcement Learning 7

Foundations & Theory

Self-Supervised Learning 13 Optimization & Theory 7 Causal Inference 2 Interpretability 10 Model Compression 52 Graph Learning 1 Time Series 4

Science & Cross-Disciplinary

Medical Imaging 31 Computational Biology 4 Physics & Scientific Computing 2 Signal & Communications 3 Social Computing 4 AI Safety 24

Others

Others 33

🧪 ICML2025

1060 notes · 50 areas

LLM

LLM Reasoning 19 LLM Agent 11 Multi-Agent 7 Alignment & RLHF 16 LLM Safety 41 Hallucination Detection 3 LLM Evaluation 22 LLM Efficiency 12 Pretraining 31 Knowledge Editing 2 LLM (Other) 28

LLM Applications

NLP Understanding 1 Text Generation 1 Dialogue Systems 2 Multilingual & Translation 1 Information Retrieval & RAG 6 Code Intelligence 9

Generation & Multimodal

Image Generation 92 Video Generation 7 Multimodal VLM 42 VLM Reasoning 5 VLM Efficiency 3 Audio & Speech 15

Visual Perception

3D Vision 17 Object Detection 12 Segmentation 18 Image Restoration 5 Remote Sensing 7 Human Understanding 3 Video Understanding 4

Decision & Embodied

Autonomous Driving 10 Robotics & Embodied AI 20 Reinforcement Learning 69 Recommender Systems 17

Foundations & Theory

Self-Supervised Learning 22 Optimization & Theory 61 Learning Theory 16 Causal Inference 17 Interpretability 31 Model Compression 74 Graph Learning 31 Time Series 21

Science & Cross-Disciplinary

Medical Imaging 21 Medical LLM 4 Computational Biology 48 Physics & Scientific Computing 20 Signal & Communications 3 Social Computing 6 AI Safety 37

Others

Others 90

💬 ACL2025

1853 notes · 47 areas

LLM

LLM Reasoning 54 LLM Agent 55 Multi-Agent 8 Alignment & RLHF 82 LLM Safety 55 Hallucination Detection 27 LLM Evaluation 89 LLM Efficiency 42 Pretraining 40 Knowledge Editing 19 LLM (Other) 442

LLM Applications

NLP Understanding 30 Text Generation 27 Dialogue Systems 18 Multilingual & Translation 86 Information Retrieval & RAG 84 Code Intelligence 28

Generation & Multimodal

Image Generation 9 Video Generation 2 Multimodal VLM 111 VLM Reasoning 18 VLM Efficiency 8 Audio & Speech 46 AIGC Detection 15

Visual Perception

3D Vision 1 Object Detection 2 Segmentation 4 Image Restoration 3 Human Understanding 2 Video Understanding 8

Decision & Embodied

Autonomous Driving 1 Robotics & Embodied AI 7 Reinforcement Learning 8 Recommender Systems 7

Foundations & Theory

Self-Supervised Learning 7 Optimization & Theory 3 Causal Inference 10 Interpretability 22 Model Compression 78 Graph Learning 24 Time Series 7

Science & Cross-Disciplinary

Medical LLM 31 Computational Biology 6 Signal & Communications 1 Social Computing 28 AI Safety 14

Others

Others 184

📷 CVPR2025

1819 notes · 47 areas

LLM

LLM Reasoning 7 LLM Agent 9 Multi-Agent 3 Alignment & RLHF 5 LLM Safety 14 Hallucination Detection 9 LLM Evaluation 4 LLM Efficiency 5 Pretraining 15 Knowledge Editing 1 LLM (Other) 15

LLM Applications

Text Generation 2 Multilingual & Translation 1 Information Retrieval & RAG 12

Generation & Multimodal

Image Generation 305 Video Generation 85 Multimodal VLM 136 VLM Reasoning 13 VLM Efficiency 3 Audio & Speech 19 AIGC Detection 3

Visual Perception

3D Vision 364 Object Detection 38 Segmentation 94 Image Restoration 41 Remote Sensing 11 Human Understanding 73 Video Understanding 69

Decision & Embodied

Autonomous Driving 89 Robotics & Embodied AI 40 Reinforcement Learning 4 Recommender Systems 1

Foundations & Theory

Self-Supervised Learning 26 Optimization & Theory 11 Causal Inference 4 Interpretability 21 Model Compression 66 Graph Learning 7 Time Series 5

Science & Cross-Disciplinary

Medical Imaging 78 Computational Biology 7 Physics & Scientific Computing 7 Earth Science 1 Signal & Communications 5 Social Computing 6 AI Safety 27

Others

Others 58

🎞️ ECCV2024

869 notes · 42 areas

LLM

LLM Reasoning 1 LLM Agent 3 LLM Safety 1 Hallucination Detection 2 LLM Evaluation 19 Pretraining 8 LLM (Other) 11

LLM Applications

NLP Understanding 1 Dialogue Systems 1 Information Retrieval & RAG 3 Code Intelligence 1

Generation & Multimodal

Image Generation 117 Video Generation 14 Multimodal VLM 44 VLM Reasoning 1 VLM Efficiency 4 Audio & Speech 8

Visual Perception

3D Vision 181 Object Detection 31 Segmentation 54 Image Restoration 32 Remote Sensing 6 Human Understanding 54 Video Understanding 51

Decision & Embodied

Autonomous Driving 53 Robotics & Embodied AI 13 Reinforcement Learning 3 Recommender Systems 1

Foundations & Theory

Self-Supervised Learning 16 Optimization & Theory 2 Causal Inference 4 Interpretability 5 Model Compression 24 Graph Learning 4 Time Series 3

Science & Cross-Disciplinary

Medical Imaging 28 Physics & Scientific Computing 1 Earth Science 1 Signal & Communications 6 Social Computing 2 AI Safety 13

Others

Others 42