{"data":{"slug":"eugeneyan-ml-surveys","name":"ml-surveys","tagline":"Survey papers summarizing advances in various AI domains","github_url":"https://github.com/eugeneyan/ml-surveys","owner":"eugeneyan","repo":"ml-surveys","owner_avatar_url":"https://avatars.githubusercontent.com/u/6831355?v=4","primary_language":null,"stars":2902,"forks":292,"topics":["computer-vision","deep-learning","embeddings","machine-learning","nlp","recommender-system","reinforcement-learning","survey"],"archived":false,"github_pushed_at":"2023-03-17T05:00:49+00:00","maintenance_label":"Dormant","stars_delta_30d":0,"url":"https://www.graphcanon.com/tools/eugeneyan-ml-surveys","markdown_url":"https://www.graphcanon.com/tools/eugeneyan-ml-surveys.md","api_url":"https://www.graphcanon.com/api/graphcanon/tools/eugeneyan-ml-surveys","graph_url":"https://www.graphcanon.com/api/graphcanon/graph?tool=eugeneyan-ml-surveys","description":"📋 Survey papers summarizing advances in deep learning, NLP, CV, graphs, reinforcement learning, recommendations, graphs, etc.","homepage_url":null,"license":"MIT","open_issues":2,"watchers":150,"ai_summary":"A collection of survey papers that cover advancements and research in deep learning, natural language processing, computer vision, graphs, reinforcement learning, recommendations, among other areas within the field of artificial intelligence.","readme_excerpt":"# ml-surveys\n\nIt's hard to keep up with the latest and greatest in machine learning. Here's a selection of **survey papers summarizing the advances in the field**.\n\n\n\nFiguring out how to implement your ML project? Learn how other organizations did it 👉[`applied-ml`](https://github.com/eugeneyan/applied-ml)\n\n**Table of Contents**\n\n- [Recommendation](#recommendation)\n- [Deep Learning](#deep-learning)\n- [Natural Language Processing](#natural-language-processing)\n- [Computer Vision](#computer-vision)\n- [Vision and Language](#vision-and-language)\n- [Reinforcement Learning](#reinforcement-learning)\n- [Graph](#graph)\n- [Embeddings](#embeddings)\n- [Meta-learning and Few-shot Learning](#meta-learning-and-few-shot-Learning)\n- [Others](#others)\n\n## Recommendation\n- Algorithms: [Recommender systems survey (2013)](http://irntez.ir/wp-content/uploads/2016/12/sciencedirec.pdf)\n- Algorithms: [Deep Learning based Recommender System: A Survey and New Perspectives (2019)](https://arxiv.org/pdf/1707.07435.pdf)\n- Algorithms: [Are We Really Making Progress? An Analysis of Neural Recommendation Approaches (2019)](https://arxiv.org/pdf/1907.06902.pdf)\n- Serendipity: [A Survey of Serendipity in Recommender Systems (2016)](https://www.researchgate.net/publication/306075233_A_Survey_of_Serendipity_in_Recommender_Systems)\n- Diversity: [Diversity in Recommender Systems – A survey (2017)](https://papers-gamma.link/static/memory/pdfs/153-Kunaver_Diversity_in_Recommender_Systems_2017.pdf)\n- Explanations: [A Survey of Explanations in Recommender Systems (2007)](http://citeseerx.ist.psu.edu/viewdoc/download?doi=10.1.1.418.9237&rep=rep1&type=pdf)\n\n## Deep Learning\n- Architecture: [A State-of-the-Art Survey on Deep Learning Theory and Architectures (2019)](https://www.mdpi.com/2079-9292/8/3/292/htm)\n- Knowledge distillation: [Knowledge Distillation: A Survey (2021)](https://arxiv.org/pdf/2006.05525.pdf)\n- Model compression: [Compression of Deep Learning Models for Text: A Survey (2020)](https://arxiv.org/pdf/2008.05221.pdf)\n- Transfer learning: [A Survey on Deep Transfer Learning (2018)](https://arxiv.org/pdf/1808.01974.pdf)\n- Neural architecture search: [A Comprehensive Survey of Neural Architecture Search (2021)](https://arxiv.org/abs/2006.02903)\n- Neural architecture search: [Neural Architecture Search: A Survey (2019)](https://arxiv.org/abs/1808.05377)\n\n## Natural Language Processing\n- Deep Learning: [Recent Trends in Deep Learning Based Natural Language Processing (2018)](https://arxiv.org/pdf/1708.02709.pdf)\n- Classification: [Deep Learning Based Text Classification: A Comprehensive Review (2021)](https://arxiv.org/pdf/2004.03705)\n- Generation: [Survey of the SOTA in Natural Language Generation: Core tasks, applications and evaluation (2018)](https://www.jair.org/index.php/jair/article/view/11173/26378)\n- Generation: [Neural Language Generation: Formulation, Methods, and Evaluation (2020)](https://arxiv.org/pdf/2007.15780.pdf)\n- Transfer learning: [Exploring Transfer Learning with T5: the Text-To-Text Transfer Transformer (2020)](https://arxiv.org/abs/1910.10683)\n- Transformers: [Efficient Transformers: A Survey (2020)](https://arxiv.org/pdf/2009.06732.pdf)\n- Metrics: [Beyond Accuracy: Behavioral Testing of NLP Models with CheckList (2020)](https://arxiv.org/pdf/2005.04118.pdf)\n- Metrics: [Evaluation of Text Generation: A Survey (2020)](https://arxiv.org/pdf/2006.14799.pdf)\n\n## Computer Vision\n- Object detection: [Object Detection in 20 Years (2019)](https://arxiv.org/pdf/1905.05055.pdf)\n- Adversarial attacks: [Threat of Adversarial Attacks on Deep Learning in Computer Vision (2018)](https://ieeexplore.ieee.org/stamp/stamp.jsp?arnumber=8294186)\n- Autonomous vehicles: [Computer Vision for Autonomous Vehicles: Problems, Datasets and SOTA (2021)](https://arxiv.org/pdf/1704.05519.pdf)\n- Image Captioning: [A Comprehensive Survey of Deep Learning for Image Captioning (2018)](https://arxiv.org/pdf/1810.04020.pdf)\n- Instance Segmentation: [A Survey on Instance Se","github_created_at":"2020-08-08T01:35:06+00:00","created_at":"2026-07-11T11:29:18.432478+00:00","updated_at":"2026-08-22T06:01:09.575355+00:00","categories":[{"slug":"computer-vision","name":"Computer Vision","url":"https://www.graphcanon.com/categories/computer-vision","markdown_url":"https://www.graphcanon.com/categories/computer-vision.md","api_url":"https://www.graphcanon.com/api/graphcanon/categories/computer-vision"},{"slug":"evaluation-observability","name":"Evaluation & Observability","url":"https://www.graphcanon.com/categories/evaluation-observability","markdown_url":"https://www.graphcanon.com/categories/evaluation-observability.md","api_url":"https://www.graphcanon.com/api/graphcanon/categories/evaluation-observability"},{"slug":"model-training","name":"Model Training","url":"https://www.graphcanon.com/categories/model-training","markdown_url":"https://www.graphcanon.com/categories/model-training.md","api_url":"https://www.graphcanon.com/api/graphcanon/categories/model-training"}],"tags":[{"slug":"computer-vision","name":"computer-vision"},{"slug":"deep-learning","name":"deep-learning"},{"slug":"embeddings","name":"embeddings"},{"slug":"machine-learning","name":"machine-learning"},{"slug":"nlp","name":"nlp"},{"slug":"recommender-system","name":"recommender-system"},{"slug":"reinforcement-learning","name":"reinforcement-learning"},{"slug":"survey","name":"survey"}],"trust":{"provenance":{"is_fork":false,"github_id":285951873,"owner_type":"User","methodology":"github_public_v1","parent_repo":null,"near_duplicate_slugs":[]},"computed_at":"2026-08-22T06:01:08.865Z","maintenance":{"label":"Dormant","score":18,"methodology":"github_public_v1","releases_90d":0,"days_since_push":1254,"last_release_at":null,"stars_delta_30d":0,"open_issues_delta_30d":0},"security_summary":{"status":"no_lockfile","scanner":null,"low_count":0,"high_count":0,"last_scan_at":"2026-07-11T11:29:19.681Z","medium_count":0,"scan_profile":"none","critical_count":0}},"capability_facts":{"scan":{"source":"repo_scan","observed_at":"2026-08-22T06:01:09.303Z"},"license_spdx":{"value":"MIT","source":"github.license","observed_at":"2026-08-22T06:01:09.303Z"}},"decision_facts":{"hosting":null,"pricing":null,"requirements":null,"constraints":null,"when_to_use":["When you need comprehensive overviews and summaries of the latest research trends in multiple areas within machine learning","For researchers or practitioners looking to quickly catch up on recent developments across various subfields of AI without reading each original paper"],"when_not_to_use":["If you are seeking detailed technical details, original experiments, or specific algorithm implementations as ml-surveys focuses more on synthesis and summary","In cases where deep-dive analysis is required into a single niche topic, as ml-surveys provides broad overviews rather than in-depth coverage of individual niches"],"source":"enrich:decision_facts","observed_at":"2026-07-12T14:06:32.502Z"},"constraint_facets":null,"decision_summary":[{"label":"Adopt for","value":"ml-surveys is a collection of detailed review papers summarizing advancements in various AI domains such as deep learning, NLP, CV, graphs, reinforcement learning, and recommendation systems."}]}}