{"about":{"site":"https://codewithpapers.app","non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page"},"url":"/paper/tabpfn-one-model-to-rule-them-all","title":"TabPFN: One Model to Rule Them All?","arxiv_id":"2505.20003","date":"2025-05-26","proceeding":null,"authors":["Qiong Zhang","Yan Shuo Tan","Qinglong Tian","Pengfei Li"],"abstract":"Hollmann et al. (Nature 637 (2025) 319-326) recently introduced TabPFN, a transformer-based deep learning model for regression and classification on tabular data, which they claim \"outperforms all previous methods on datasets with up to 10,000 samples by a wide margin, using substantially less training time.\" Furthermore, they have called TabPFN a \"foundation model\" for tabular data, as it can support \"data generation, density estimation, learning reusable embeddings and fine-tuning\". If these statements are well-supported, TabPFN may have the potential to supersede existing modeling approaches on a wide range of statistical tasks, mirroring a similar revolution in other areas of artificial intelligence that began with the advent of large language models. In this paper, we provide a tailored explanation of how TabPFN works for a statistics audience, by emphasizing its interpretation as approximate Bayesian inference. We also provide more evidence of TabPFN's \"foundation model\" capabilities: We show that an out-of-the-box application of TabPFN vastly outperforms specialized state-of-the-art methods for semi-supervised parameter estimation, prediction under covariate shift, and heterogeneous treatment effect estimation. We further show that TabPFN can outperform LASSO at sparse regression and can break a robustness-efficiency trade-off in classification. All experiments can be reproduced using the code provided at https://github.com/qinglong-tian/tabpfn_study (https://github.com/qinglong-tian/tabpfn_study).","url_abs":"https://arxiv.org/abs/2505.20003v1","url_pdf":"https://arxiv.org/pdf/2505.20003v1.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[{"paper_slug":"tabpfn-one-model-to-rule-them-all","repo_url":"https://github.com/qinglong-tian/tabpfn_study","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"none","reach":null}],"tasks":[{"task_slug":"all","task_name":"All"},{"task_slug":"bayesian-inference","task_name":"Bayesian Inference"},{"task_slug":"density-estimation","task_name":"Density Estimation"},{"task_slug":"heterogeneous-treatment-effect-estimation","task_name":"Heterogeneous Treatment Effect Estimation"},{"task_slug":"model","task_name":"model"},{"task_slug":"parameter-estimation","task_name":"parameter estimation"}],"methods":[{"method_slug":"tabpfn","method_name":"TABPFN"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2505.20003","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}