Search papers from top venues in machine learning (ML)
Search 97,246 papers on learning theory, deep learning, optimization, probabilistic methods and reinforcement learning from NeurIPS, ICML, ICLR, AISTATS, TMLR, JMLR, UAI and COLT, 2000 to 2026. Describe what you are looking for in your own words, or search with exact keywords. refract.science is free and runs privately in your browser.
Machine learning venues
6 conferences and 2 journals in refract.science. Each has a page with its papers per year and its latest papers.
- NeurIPS Conference on Neural Information Processing Systems
- ICML International Conference on Machine Learning
- ICLR International Conference on Learning Representations
- AISTATS International Conference on Artificial Intelligence and Statistics
- TMLR Transactions on Machine Learning Research
- JMLR Journal of Machine Learning Research
- UAI Conference on Uncertainty in Artificial Intelligence
- COLT Conference on Learning Theory
- Papers
- 97,246
- Venues
- 8
- Years
- 2000–2026
| Year | Papers |
|---|---|
| 2000 | 417 |
| 2001 | 459 |
| 2002 | 443 |
| 2003 | 578 |
| 2004 | 502 |
| 2005 | 601 |
| 2006 | 560 |
| 2007 | 651 |
| 2008 | 622 |
| 2009 | 745 |
| 2010 | 831 |
| 2011 | 810 |
| 2012 | 1032 |
| 2013 | 980 |
| 2014 | 1154 |
| 2015 | 1125 |
| 2016 | 1527 |
| 2017 | 1789 |
| 2018 | 2550 |
| 2019 | 3374 |
| 2020 | 4729 |
| 2021 | 5642 |
| 2022 | 6615 |
| 2023 | 8862 |
| 2024 | 11659 |
| 2025 | 15683 |
| 2026 | 23306 |
Example searches
Semantic search understands questions and descriptions. Try one of these on the machine learning venues:
- why does in-context learning work in large language models
- generalization bounds for overparameterized neural networks
- offline reinforcement learning with limited data
- uncertainty estimation for deep neural networks
For exact terms, authors and exhaustive lists, use keyword search, e.g. author:"…" AND venue:neurips.
Latest machine learning papers
-
TUR-DPO: Topology- and Uncertainty-Aware Direct Preference Optimization
-
The Riemannian Geometry Associated to Gradient Flows of Linear Convolutional Networks
-
Supervised Contrastive Learning of Environment-Invariant Representations
-
The Role of Contextual Information in Best Arm Identification
-
Distilling Safe LLM Systems via Soft Prompts for On Device Settings
-
3D Gaussian Splatting within Self-Learned Neural View-Dependent Color Fields
-
What Preferences Can—and Cannot—Predict in Multi-Agent Online Learning
-
LiveMoments: Reselected Key Photo Restoration in Live Photos via Reference-guided Diffusion
-
VIPaint: Image Inpainting with Pre-Trained Diffusion Models via Variational Inference
Questions
Which machine learning venues can I search?
Conference on Neural Information Processing Systems (NeurIPS, 2000–2026), International Conference on Machine Learning (ICML, 2000–2026), International Conference on Learning Representations (ICLR, 2013–2026), International Conference on Artificial Intelligence and Statistics (AISTATS, 2001–2026), Transactions on Machine Learning Research (TMLR, 2022–2026), Journal of Machine Learning Research (JMLR, 2000–2026), Conference on Uncertainty in Artificial Intelligence (UAI, 2000–2026) and Conference on Learning Theory (COLT, 2000–2026). Together they hold 97,246 papers with titles, authors and, for most papers, abstracts.
How do I find machine learning papers on a topic?
Describe the topic in your own words, as a question, a short description or a few keywords, for example "why does in-context learning work in large language models". Semantic search ranks the papers of NeurIPS, ICML, ICLR, AISTATS, TMLR, JMLR, UAI and COLT by how well their title and abstract match the meaning of your description, so you also find papers that use different terms.
Can I search a single machine learning venue?
Yes. Filter the results to the venues you want, or use keyword search with a venue field, e.g. venue:neurips AND title:"…". Each venue also has its own page with its papers per year and latest papers.
Can I search machine learning together with other fields?
Yes. refract.science covers 36 venues across computer science, including natural language processing, artificial intelligence, computer vision and information retrieval, web and data mining. Search them all at once to find related work across fields, or open similar papers from any result.
Can my AI agent search machine learning papers?
Yes. Agents that support the Model Context Protocol (MCP), such as Claude, Cursor or VS Code, can search the machine learning venues installed in your browser, follow similar papers and add them to your collections.
Is it free, and are my searches private?
It is free and needs no account. The papers and the search model are downloaded to your browser once, and every search runs there, so your queries stay on your device.