{
  "source_file": "0930",
  "source_platform": "Substack",
  "author": "Mindful Modeler Christoph Molnar",
  "title_listed": "Tabular Foundation Models: The Tabular Revolution",
  "keywords": "表格基础模型,TabPFN,tabular",
  "domain": "机器学习",
  "content_type": "深度技术解析",
  "is_paid_flag": "否",
  "url": "https://mindfulmodeler.substack.com/p/tabular-foundation-models",
  "publish_date": "2024-11",
  "corpus_stage": "数据处理",
  "notes": "表格基础模型革命",
  "id": "c88507d419d1",
  "collected_at": "2026-10-01T20:28:38",
  "title": "Mindful Modeler | Christoph Molnar | Substack",
  "body_markdown": "[![Mindful Modeler](https://substackcdn.com/image/fetch/$s_!WtQm!,w_40,h_40,c_fill,f_auto,q_auto:good,fl_progressive:steep/https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2Fc3dc1d90-fb9f-4e3c-80d5-756a5d6e8495_500x500.png)](https://mindfulmodeler.substack.com/)\n# [Mindful Modeler](https://mindfulmodeler.substack.com/)\nSubscribeSign in\n[Home](https://mindfulmodeler.substack.com/)\n[Tabular Foundation Models](https://mindfulmodeler.substack.com/t/tabular-foundation-models)\n[Archive](https://mindfulmodeler.substack.com/archive)\n[About](https://mindfulmodeler.substack.com/about)\n## Page not found\nLatestTopDiscussions\n[Trends in tabular foundation research](https://mindfulmodeler.substack.com/p/trends-in-tabular-foundation-research)\n[Based on 151 papers from ICML workshop \"Foundation Models for Structured Data\"](https://mindfulmodeler.substack.com/p/trends-in-tabular-foundation-research)\nJul 22 • [Christoph Molnar](https://substack.com/@christophmolnar)\n28\n3\n[Time for a change](https://mindfulmodeler.substack.com/p/time-for-a-change)\n[After 4 years of writing, I'm exploring what's next for me in ML / data science / AI (or whatever you want to call it)](https://mindfulmodeler.substack.com/p/time-for-a-change)\nJul 16 • [Christoph Molnar](https://substack.com/@christophmolnar)\n31\n8\n![](../images/013.jpeg)\n[TabFM minus the hype](https://mindfulmodeler.substack.com/p/tabfm-minus-the-hype)\n[top performance on TabArena; large model; slow inference; non-commercial license](https://mindfulmodeler.substack.com/p/tabfm-minus-the-hype)\nJul 7 • [Christoph Molnar](https://substack.com/@christophmolnar)\n34\n### June 2026\n[Which ML models produce the best quantile estimates?](https://mindfulmodeler.substack.com/p/which-regressor-produces-the-best)\n[Results from ScoringBench](https://mindfulmodeler.substack.com/p/which-regressor-produces-the-best)\nJun 30 • [Christoph Molnar](https://substack.com/@christophmolnar)\n14\n2\n![](../images/031.png)\n[When trees still beat tabular foundation models](https://mindfulmodeler.substack.com/p/when-trees-still-beat-tabular-foundation)\n[As you might have noticed, I’m rather optimistic about tabular foundation models.](https://mindfulmodeler.substack.com/p/when-trees-still-beat-tabular-foundation)\nJun 23 • [Christoph Molnar](https://substack.com/@christophmolnar)\n30\n8\n1\n![](../images/body-046df6a26d0cb93d2488.png)\n[What is TabPFN's Thinking mode?](https://mindfulmodeler.substack.com/p/what-is-tabpfns-thinking-mode)\n[When I read the TabPFN-3 Technical Report, the benchmark for “TabPFN-3-Thinking” stood out: it appeared at the top of the TabArena benchmark for large…](https://mindfulmodeler.substack.com/p/what-is-tabpfns-thinking-mode)\nJun 16 • [Christoph Molnar](https://substack.com/@christophmolnar)\n16\n1\n2\n![](../images/body-ee0673943cbdb01b8702.png)\n[How TabICL and TabPFN handle missing values](https://mindfulmodeler.substack.com/p/how-tabicl-and-tabpfn-handle-missing)\n[You can give training or test data with missing values to the tabular foundation models TabPFN and TabICL, and the prediction will “just work”.](https://mindfulmodeler.substack.com/p/how-tabicl-and-tabpfn-handle-missing)\nJun 9 • [Christoph Molnar](https://substack.com/@christophmolnar)\n23\n1\n3\n[TabPFN and TabICL are not everything](https://mindfulmodeler.substack.com/p/tabpfn-and-tabicl-are-not-everything)\n[An overview of other families for tabular foundation models](https://mindfulmodeler.substack.com/p/tabpfn-and-tabicl-are-not-everything)\nJun 2 • [Christoph Molnar](https://substack.com/@christophmolnar)\n22\n2\n![](../images/body-2f890e121a5085a082b6.png)\n### May 2026\n[I’m writing a book on Tabular Foundation Models](https://mindfulmodeler.substack.com/p/im-writing-a-book-on-tabular-foundation)\n[tl;dr: In-progress book here: tabularfoundationmodels.com](https://mindfulmodeler.substack.com/p/im-writing-a-book-on-tabular-foundation)\nMay 26 • [Christoph Molnar](https://substack.com/@christophmolnar)\n33\n12\n2\n![](../images/body-12982a727befec6b17c8.png)\n[Tabular ML is entering a new benchmark era](https://mindfulmodeler.substack.com/p/tabular-ml-is-entering-a-new-benchmark)\n[From static and narrow benchmarks to live, capability-driven evaluation](https://mindfulmodeler.substack.com/p/tabular-ml-is-entering-a-new-benchmark)\nMay 19 • [Christoph Molnar](https://substack.com/@christophmolnar)\n16\n[How to make Tabular Foundation Model inference faster](https://mindfulmodeler.substack.com/p/making-tabular-foundation-models)\n[GPU, KV caching, context optimization, and other inference tricks](https://mindfulmodeler.substack.com/p/making-tabular-foundation-models)\nMay 12 • [Christoph Molnar](https://substack.com/@christophmolnar)\n21\n2\n1\n![](../images/body-481fb13c4b2e21ea704e.png)\n[Time series forecasting with tabular foundation models](https://mindfulmodeler.substack.com/p/time-series-forecasting-with-tabular)\n[This post is a quick primer on using tabular foundation models for time series forecasting.](https://mindfulmodeler.substack.com/p/time-series-forecasting-with-tabular)\nMay 5 • [Christoph Molnar](https://substack.com/@christophmolnar)\n19\n4\n3\n![](../images/body-448d720f9092778758f7.png)\n### April 2026\n[Train or Test for Feature Effect Estimation? We Finally Have an Answer](https://mindfulmodeler.substack.com/p/train-or-test-for-feature-effect)\n[A guest post by XAI researcher Timo Heiß](https://mindfulmodeler.substack.com/p/train-or-test-for-feature-effect)\nApr 28 • [Christoph Molnar](https://substack.com/@christophmolnar)\n16\n3\n3\n![](../images/body-f888e7ab5c600aa1582b.png)\n[Context is the new training](https://mindfulmodeler.substack.com/p/context-is-the-new-training)\n[Tabular foundation models replace retraining with editable inference-time data](https://mindfulmodeler.substack.com/p/context-is-the-new-training)\nApr 21 • [Christoph Molnar](https://substack.com/@christophmolnar)\n39\n1\n3\n![](../images/body-2a3aee0dac04ef1123b5.png)\n[Regression should predict full distributions](https://mindfulmodeler.substack.com/p/regression-should-predict-full-distributions)\n[A \"hidden\" feature of tabular foundation models](https://mindfulmodeler.substack.com/p/regression-should-predict-full-distributions)\nApr 14 • [Christoph Molnar](https://substack.com/@christophmolnar)\n39\n2\n1\n![](../images/body-60cc0828977045205fcc.png)\n### March 2026\n[TabArena explained](https://mindfulmodeler.substack.com/p/tabarena-explained)\n[What chess ratings tell us about ML models](https://mindfulmodeler.substack.com/p/tabarena-explained)\nMar 31 • [Christoph Molnar](https://substack.com/@christophmolnar)\n20\n4\n1\n![](../images/body-416bec0248c6f5d3e732.png)\n[The interpretability tax on tabular foundation models](https://mindfulmodeler.substack.com/p/tabular-foundation-models-break-the)\n[Model-agnostic interpretability for tabular foundation models](https://mindfulmodeler.substack.com/p/tabular-foundation-models-break-the)\nMar 24 • [Christoph Molnar](https://substack.com/@christophmolnar)\n25\n9\n1\n![](../images/body-66941eb114875939ad1f.png)\n[I’m betting on tabular foundation models](https://mindfulmodeler.substack.com/p/im-betting-on-tabular-foundation)\n[The shipping container moment of data science](https://mindfulmodeler.substack.com/p/im-betting-on-tabular-foundation)\nMar 17 • [Christoph Molnar](https://substack.com/@christophmolnar)\n66\n9\n9\n![](../images/body-3625aa898ddc4395ee89.png)\n[The Random Forest of the 2030s?](https://mindfulmodeler.substack.com/p/the-random-forest-of-the-2030s)\n[Three scenarios for the future of tabular ML, plus one that makes them all irrelevant](https://mindfulmodeler.substack.com/p/the-random-forest-of-the-2030s)\nMar 3 • [Christoph Molnar](https://substack.com/@christophmolnar)\n24\n2\n### February 2026\n[A regression example with TabICLv2](https://mindfulmodeler.substack.com/p/a-regression-example-with-tabiclv2)\n[Strong performance at a steep interpretability cost (at least on CPU)](https://mindfulmodeler.substack.com/p/a-regression-example-with-tabiclv2)\nFeb 24 • [Christoph Molnar](https://substack.com/@christophmolnar)\n27\n3\n1\n![](../images/body-71a8c6582e2d2490ec96.png)\n[The state of Tabular Foundation Models (2026)](https://mindfulmodeler.substack.com/p/the-state-of-tabular-foundation-models)\n[Pre-trained models, startups, and recommendation.](https://mindfulmodeler.substack.com/p/the-state-of-tabular-foundation-models)\nFeb 17 • [Christoph Molnar](https://substack.com/@christophmolnar)\n41\n7\n4\n![](../images/body-a7463d6bf7a12481dfa3.png)\n[How Tabular Foundation Models learn without real data](https://mindfulmodeler.substack.com/p/how-tabular-foundation-models-are)\n[The pre-training recipe behind TFMs](https://mindfulmodeler.substack.com/p/how-tabular-foundation-models-are)\nFeb 10 • [Christoph Molnar](https://substack.com/@christophmolnar)\n36\n2\n4\n![](../images/body-bc538b4e7ffa12b459cf.png)\n[The architecture behind TabPFN](https://mindfulmodeler.substack.com/p/the-architecture-behind-tabpfn)\n[How transformers learn from entire tables](https://mindfulmodeler.substack.com/p/the-architecture-behind-tabpfn)\nFeb 3 • [Christoph Molnar](https://substack.com/@christophmolnar)\n43\n7\n1\n![](../images/body-b47de25039bd1c8bf330.png)\n### January 2026\n[How PFNs make tabular foundation models work](https://mindfulmodeler.substack.com/p/how-pfns-make-tabular-foundation)\n[Bayesian logic, synthetic priors, and in-context learning](https://mindfulmodeler.substack.com/p/how-pfns-make-tabular-foundation)\nJan 21 • [Christoph Molnar](https://substack.com/@christophmolnar)\n62\n2\n4\n![](../images/body-da05da41155b04c02fdb.png)\n© 2026 Christoph Molnar · [Privacy](https://substack.com/privacy) ∙ [Terms](https://substack.com/tos) ∙ [Collection notice](https://substack.com/ccpa#personal-data-collected)\n[ Start your Substack](https://substack.com/signup?utm_source=substack&utm_medium=web&utm_content=footer)[Get the app](https://substack.com/app/app-store-redirect?utm_campaign=app-marketing&utm_content=web-footer-button)\n[Substack](https://substack.com) is the home for great culture\n",
  "metadata": {
    "title": "Mindful Modeler | Christoph Molnar | Substack",
    "description": "Tabular foundation models, ML interpretability, and beyond by a statistician turned machine learner. Click to read Mindful Modeler, by Christoph Molnar, a Substack publication with tens of thousands of subscribers.",
    "keywords": null,
    "author": "Christoph Molnar",
    "og:type": "article",
    "og:title": "Mindful Modeler | Christoph Molnar | Substack",
    "og:description": "Tabular foundation models, ML interpretability, and beyond by a statistician turned machine learner. Click to read Mindful Modeler, by Christoph Molnar, a Substack publication with tens of thousands of subscribers.",
    "og:image": "https://substackcdn.com/image/fetch/$s_!btbh!,f_auto,q_auto:best,fl_progressive:steep/https%3A%2F%2Fmindfulmodeler.substack.com%2Ftwitter%2Fsubscribe-card.jpg%3Fv%3D-467131775%26version%3D9",
    "og:url": "https://mindfulmodeler.substack.com/tabular-foundation-models",
    "twitter:title": "Mindful Modeler | Christoph Molnar | Substack",
    "twitter:description": "Tabular foundation models, ML interpretability, and beyond by a statistician turned machine learner. Click to read Mindful Modeler, by Christoph Molnar, a Substack publication with tens of thousands of subscribers.",
    "twitter:image": "https://substackcdn.com/image/fetch/$s_!btbh!,f_auto,q_auto:best,fl_progressive:steep/https%3A%2F%2Fmindfulmodeler.substack.com%2Ftwitter%2Fsubscribe-card.jpg%3Fv%3D-467131775%26version%3D9",
    "twitter:card": "summary_large_image"
  },
  "paywall": {
    "listed_paid": false,
    "detected": false,
    "marker": "",
    "public_only": false,
    "policy": "付费/会员内容只保留页面公开可见部分，不绕过付费墙"
  },
  "crawl": {
    "success": true,
    "status_code": 302,
    "error": ""
  },
  "code_blocks": [],
  "images": [
    {
      "status": "ok",
      "url": "https://substackcdn.com/image/fetch/$s_!iTaq!,w_320,h_213,c_fill,f_auto,q_auto:good,fl_progressive:steep,g_center/https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2Fe917e8f4-41be-4861-b507-0d730a2978aa_4000x3000.jpeg",
      "bytes": 12597,
      "reused": true,
      "local_path": "attachments/c88507d419d1/images/013.jpeg",
      "src": "https://substackcdn.com/image/fetch/$s_!iTaq!,w_320,h_213,c_fill,f_auto,q_auto:good,fl_progressive:steep,g_center/https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2Fe917e8f4-41be-4861-b507-0d730a2978aa_4000x3000.jpeg",
      "alt": "",
      "downloaded": true,
      "discovery": "saved_markdown"
    },
    {
      "status": "ok",
      "url": "https://substackcdn.com/image/fetch/$s_!YaZ6!,w_320,h_213,c_fill,f_auto,q_auto:good,fl_progressive:steep,g_center/https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2F9f34ec3a-89c7-470f-bdce-9f7dad26d3fe_1704x1438.png",
      "bytes": 16881,
      "reused": true,
      "local_path": "attachments/c88507d419d1/images/031.png",
      "src": "https://substackcdn.com/image/fetch/$s_!YaZ6!,w_320,h_213,c_fill,f_auto,q_auto:good,fl_progressive:steep,g_center/https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2F9f34ec3a-89c7-470f-bdce-9f7dad26d3fe_1704x1438.png",
      "alt": "",
      "downloaded": true,
      "discovery": "saved_markdown"
    },
    {
      "status": "ok",
      "url": "https://substackcdn.com/image/fetch/$s_!oYhD!,w_320,h_213,c_fill,f_auto,q_auto:good,fl_progressive:steep,g_center/https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2Fe50e172c-79da-4794-887b-985db0bf8975_958x600.png",
      "bytes": 51792,
      "reused": false,
      "content_type": "image/png",
      "local_path": "attachments/c88507d419d1/images/body-046df6a26d0cb93d2488.png",
      "src": "https://substackcdn.com/image/fetch/$s_!oYhD!,w_320,h_213,c_fill,f_auto,q_auto:good,fl_progressive:steep,g_center/https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2Fe50e172c-79da-4794-887b-985db0bf8975_958x600.png",
      "alt": "",
      "downloaded": true,
      "discovery": "saved_markdown"
    },
    {
      "status": "ok",
      "url": "https://substackcdn.com/image/fetch/$s_!gjiu!,w_320,h_213,c_fill,f_auto,q_auto:good,fl_progressive:steep,g_center/https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2F7023d57a-ef28-4666-84b8-4ccedca2e31f_1600x640.png",
      "bytes": 17820,
      "reused": false,
      "content_type": "image/jpeg",
      "local_path": "attachments/c88507d419d1/images/body-ee0673943cbdb01b8702.png",
      "src": "https://substackcdn.com/image/fetch/$s_!gjiu!,w_320,h_213,c_fill,f_auto,q_auto:good,fl_progressive:steep,g_center/https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2F7023d57a-ef28-4666-84b8-4ccedca2e31f_1600x640.png",
      "alt": "",
      "downloaded": true,
      "discovery": "saved_markdown"
    },
    {
      "status": "ok",
      "url": "https://substackcdn.com/image/fetch/$s_!6fms!,w_320,h_213,c_fill,f_auto,q_auto:good,fl_progressive:steep,g_center/https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2Fe281ed90-32d8-4349-ac3c-4a64c4b11bbc_1788x1246.png",
      "bytes": 14417,
      "reused": false,
      "content_type": "image/jpeg",
      "local_path": "attachments/c88507d419d1/images/body-2f890e121a5085a082b6.png",
      "src": "https://substackcdn.com/image/fetch/$s_!6fms!,w_320,h_213,c_fill,f_auto,q_auto:good,fl_progressive:steep,g_center/https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2Fe281ed90-32d8-4349-ac3c-4a64c4b11bbc_1788x1246.png",
      "alt": "",
      "downloaded": true,
      "discovery": "saved_markdown"
    },
    {
      "status": "ok",
      "url": "https://substackcdn.com/image/fetch/$s_!y3mi!,w_320,h_213,c_fill,f_auto,q_auto:good,fl_progressive:steep,g_center/https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2Fec1d5cb1-4679-4ecf-9439-c9cc6815d4b2_1536x1024.png",
      "bytes": 11793,
      "reused": false,
      "content_type": "image/jpeg",
      "local_path": "attachments/c88507d419d1/images/body-12982a727befec6b17c8.png",
      "src": "https://substackcdn.com/image/fetch/$s_!y3mi!,w_320,h_213,c_fill,f_auto,q_auto:good,fl_progressive:steep,g_center/https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2Fec1d5cb1-4679-4ecf-9439-c9cc6815d4b2_1536x1024.png",
      "alt": "",
      "downloaded": true,
      "discovery": "saved_markdown"
    },
    {
      "status": "ok",
      "url": "https://substackcdn.com/image/fetch/$s_!rUcO!,w_320,h_213,c_fill,f_auto,q_auto:good,fl_progressive:steep,g_center/https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2F1dfcc84c-a949-498f-af28-5073b11bca45_1491x1108.png",
      "bytes": 12596,
      "reused": false,
      "content_type": "image/jpeg",
      "local_path": "attachments/c88507d419d1/images/body-481fb13c4b2e21ea704e.png",
      "src": "https://substackcdn.com/image/fetch/$s_!rUcO!,w_320,h_213,c_fill,f_auto,q_auto:good,fl_progressive:steep,g_center/https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2F1dfcc84c-a949-498f-af28-5073b11bca45_1491x1108.png",
      "alt": "",
      "downloaded": true,
      "discovery": "saved_markdown"
    },
    {
      "status": "ok",
      "url": "https://substackcdn.com/image/fetch/$s_!V5E8!,w_320,h_213,c_fill,f_auto,q_auto:good,fl_progressive:steep,g_center/https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2Fb0c3443c-2245-4268-baf5-616381849210_1000x300.png",
      "bytes": 10590,
      "reused": false,
      "content_type": "image/jpeg",
      "local_path": "attachments/c88507d419d1/images/body-448d720f9092778758f7.png",
      "src": "https://substackcdn.com/image/fetch/$s_!V5E8!,w_320,h_213,c_fill,f_auto,q_auto:good,fl_progressive:steep,g_center/https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2Fb0c3443c-2245-4268-baf5-616381849210_1000x300.png",
      "alt": "",
      "downloaded": true,
      "discovery": "saved_markdown"
    },
    {
      "status": "ok",
      "url": "https://substackcdn.com/image/fetch/$s_!NrCF!,w_320,h_213,c_fill,f_auto,q_auto:good,fl_progressive:steep,g_center/https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2F267210ea-da1c-4986-914e-30f62e0d229b_2048x560.png",
      "bytes": 7522,
      "reused": false,
      "content_type": "image/jpeg",
      "local_path": "attachments/c88507d419d1/images/body-f888e7ab5c600aa1582b.png",
      "src": "https://substackcdn.com/image/fetch/$s_!NrCF!,w_320,h_213,c_fill,f_auto,q_auto:good,fl_progressive:steep,g_center/https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2F267210ea-da1c-4986-914e-30f62e0d229b_2048x560.png",
      "alt": "",
      "downloaded": true,
      "discovery": "saved_markdown"
    },
    {
      "status": "ok",
      "url": "https://substackcdn.com/image/fetch/$s_!Ulhx!,w_320,h_213,c_fill,f_auto,q_auto:good,fl_progressive:steep,g_center/https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2F1211af11-578b-48a9-bd81-8b452fb79103_1184x784.png",
      "bytes": 19011,
      "reused": false,
      "content_type": "image/jpeg",
      "local_path": "attachments/c88507d419d1/images/body-2a3aee0dac04ef1123b5.png",
      "src": "https://substackcdn.com/image/fetch/$s_!Ulhx!,w_320,h_213,c_fill,f_auto,q_auto:good,fl_progressive:steep,g_center/https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2F1211af11-578b-48a9-bd81-8b452fb79103_1184x784.png",
      "alt": "",
      "downloaded": true,
      "discovery": "saved_markdown"
    },
    {
      "status": "ok",
      "url": "https://substackcdn.com/image/fetch/$s_!Gx8X!,w_320,h_213,c_fill,f_auto,q_auto:good,fl_progressive:steep,g_center/https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2F2beb351b-2bac-4b18-8147-8d01d4517dbe_863x470.png",
      "bytes": 25321,
      "reused": false,
      "content_type": "image/jpeg",
      "local_path": "attachments/c88507d419d1/images/body-60cc0828977045205fcc.png",
      "src": "https://substackcdn.com/image/fetch/$s_!Gx8X!,w_320,h_213,c_fill,f_auto,q_auto:good,fl_progressive:steep,g_center/https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2F2beb351b-2bac-4b18-8147-8d01d4517dbe_863x470.png",
      "alt": "",
      "downloaded": true,
      "discovery": "saved_markdown"
    },
    {
      "status": "ok",
      "url": "https://substackcdn.com/image/fetch/$s_!hjDv!,w_320,h_213,c_fill,f_auto,q_auto:good,fl_progressive:steep,g_center/https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2Fa71d3775-e773-4dca-886f-318b69b3f6a7_1446x1156.png",
      "bytes": 23187,
      "reused": false,
      "content_type": "image/jpeg",
      "local_path": "attachments/c88507d419d1/images/body-416bec0248c6f5d3e732.png",
      "src": "https://substackcdn.com/image/fetch/$s_!hjDv!,w_320,h_213,c_fill,f_auto,q_auto:good,fl_progressive:steep,g_center/https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2Fa71d3775-e773-4dca-886f-318b69b3f6a7_1446x1156.png",
      "alt": "",
      "downloaded": true,
      "discovery": "saved_markdown"
    },
    {
      "status": "ok",
      "url": "https://substackcdn.com/image/fetch/$s_!0FrG!,w_320,h_213,c_fill,f_auto,q_auto:good,fl_progressive:steep,g_center/https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2F150a56bd-72a6-48e7-9489-4f74e15d4a0f_470x326.png",
      "bytes": 11404,
      "reused": false,
      "content_type": "image/png",
      "local_path": "attachments/c88507d419d1/images/body-66941eb114875939ad1f.png",
      "src": "https://substackcdn.com/image/fetch/$s_!0FrG!,w_320,h_213,c_fill,f_auto,q_auto:good,fl_progressive:steep,g_center/https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2F150a56bd-72a6-48e7-9489-4f74e15d4a0f_470x326.png",
      "alt": "",
      "downloaded": true,
      "discovery": "saved_markdown"
    },
    {
      "status": "ok",
      "url": "https://substackcdn.com/image/fetch/$s_!-ksB!,w_320,h_213,c_fill,f_auto,q_auto:good,fl_progressive:steep,g_center/https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2F0be3299c-0807-4bef-840b-9f4c129de249_1800x580.png",
      "bytes": 10948,
      "reused": false,
      "content_type": "image/png",
      "local_path": "attachments/c88507d419d1/images/body-3625aa898ddc4395ee89.png",
      "src": "https://substackcdn.com/image/fetch/$s_!-ksB!,w_320,h_213,c_fill,f_auto,q_auto:good,fl_progressive:steep,g_center/https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2F0be3299c-0807-4bef-840b-9f4c129de249_1800x580.png",
      "alt": "",
      "downloaded": true,
      "discovery": "saved_markdown"
    },
    {
      "status": "ok",
      "url": "https://substackcdn.com/image/fetch/$s_!M7CC!,w_320,h_213,c_fill,f_auto,q_auto:good,fl_progressive:steep,g_center/https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2F0ad63a8d-79be-4b78-8664-ea200a7e7e20_742x441.png",
      "bytes": 11568,
      "reused": false,
      "content_type": "image/jpeg",
      "local_path": "attachments/c88507d419d1/images/body-71a8c6582e2d2490ec96.png",
      "src": "https://substackcdn.com/image/fetch/$s_!M7CC!,w_320,h_213,c_fill,f_auto,q_auto:good,fl_progressive:steep,g_center/https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2F0ad63a8d-79be-4b78-8664-ea200a7e7e20_742x441.png",
      "alt": "",
      "downloaded": true,
      "discovery": "saved_markdown"
    },
    {
      "status": "ok",
      "url": "https://substackcdn.com/image/fetch/$s_!YTRY!,w_320,h_213,c_fill,f_auto,q_auto:good,fl_progressive:steep,g_center/https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2Fddcb6f80-9bd2-4ec7-b4a8-f40bceec1d90_1329x840.png",
      "bytes": 17562,
      "reused": false,
      "content_type": "image/jpeg",
      "local_path": "attachments/c88507d419d1/images/body-a7463d6bf7a12481dfa3.png",
      "src": "https://substackcdn.com/image/fetch/$s_!YTRY!,w_320,h_213,c_fill,f_auto,q_auto:good,fl_progressive:steep,g_center/https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2Fddcb6f80-9bd2-4ec7-b4a8-f40bceec1d90_1329x840.png",
      "alt": "",
      "downloaded": true,
      "discovery": "saved_markdown"
    },
    {
      "status": "ok",
      "url": "https://substackcdn.com/image/fetch/$s_!n20i!,w_320,h_213,c_fill,f_auto,q_auto:good,fl_progressive:steep,g_center/https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2F39f86456-9714-406d-9a88-a3001b046718_1026x627.png",
      "bytes": 30710,
      "reused": false,
      "content_type": "image/png",
      "local_path": "attachments/c88507d419d1/images/body-bc538b4e7ffa12b459cf.png",
      "src": "https://substackcdn.com/image/fetch/$s_!n20i!,w_320,h_213,c_fill,f_auto,q_auto:good,fl_progressive:steep,g_center/https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2F39f86456-9714-406d-9a88-a3001b046718_1026x627.png",
      "alt": "",
      "downloaded": true,
      "discovery": "saved_markdown"
    },
    {
      "status": "ok",
      "url": "https://substackcdn.com/image/fetch/$s_!GCOl!,w_320,h_213,c_fill,f_auto,q_auto:good,fl_progressive:steep,g_center/https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2F3950d661-5102-49f8-b48c-ac8bc693bc7e_518x642.png",
      "bytes": 47464,
      "reused": false,
      "content_type": "image/png",
      "local_path": "attachments/c88507d419d1/images/body-b47de25039bd1c8bf330.png",
      "src": "https://substackcdn.com/image/fetch/$s_!GCOl!,w_320,h_213,c_fill,f_auto,q_auto:good,fl_progressive:steep,g_center/https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2F3950d661-5102-49f8-b48c-ac8bc693bc7e_518x642.png",
      "alt": "",
      "downloaded": true,
      "discovery": "saved_markdown"
    },
    {
      "status": "ok",
      "url": "https://substackcdn.com/image/fetch/$s_!95JB!,w_320,h_213,c_fill,f_auto,q_auto:good,fl_progressive:steep,g_center/https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2F3bd93c38-a5df-459d-aa0c-9a75fb7a6dfd_1916x941.png",
      "bytes": 14197,
      "reused": false,
      "content_type": "image/jpeg",
      "local_path": "attachments/c88507d419d1/images/body-da05da41155b04c02fdb.png",
      "src": "https://substackcdn.com/image/fetch/$s_!95JB!,w_320,h_213,c_fill,f_auto,q_auto:good,fl_progressive:steep,g_center/https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2F3bd93c38-a5df-459d-aa0c-9a75fb7a6dfd_1916x941.png",
      "alt": "",
      "downloaded": true,
      "discovery": "saved_markdown"
    }
  ],
  "audio": [],
  "videos": [],
  "links": [
    {
      "type": "internal",
      "href": "https://mindfulmodeler.substack.com/"
    },
    {
      "type": "internal",
      "href": "https://mindfulmodeler.substack.com/t/tabular-foundation-models"
    },
    {
      "type": "internal",
      "href": "https://mindfulmodeler.substack.com/archive"
    },
    {
      "type": "internal",
      "href": "https://mindfulmodeler.substack.com/about"
    },
    {
      "type": "internal",
      "href": "https://mindfulmodeler.substack.com/p/trends-in-tabular-foundation-research"
    },
    {
      "type": "internal",
      "href": "https://substack.com/@christophmolnar"
    },
    {
      "type": "internal",
      "href": "https://mindfulmodeler.substack.com/p/time-for-a-change"
    },
    {
      "type": "internal",
      "href": "https://mindfulmodeler.substack.com/p/tabfm-minus-the-hype"
    },
    {
      "type": "internal",
      "href": "https://mindfulmodeler.substack.com/p/which-regressor-produces-the-best"
    },
    {
      "type": "internal",
      "href": "https://mindfulmodeler.substack.com/p/when-trees-still-beat-tabular-foundation"
    },
    {
      "type": "internal",
      "href": "https://mindfulmodeler.substack.com/p/what-is-tabpfns-thinking-mode"
    },
    {
      "type": "internal",
      "href": "https://mindfulmodeler.substack.com/p/how-tabicl-and-tabpfn-handle-missing"
    },
    {
      "type": "internal",
      "href": "https://mindfulmodeler.substack.com/p/tabpfn-and-tabicl-are-not-everything"
    },
    {
      "type": "internal",
      "href": "https://mindfulmodeler.substack.com/p/im-writing-a-book-on-tabular-foundation"
    },
    {
      "type": "internal",
      "href": "https://mindfulmodeler.substack.com/p/tabular-ml-is-entering-a-new-benchmark"
    },
    {
      "type": "internal",
      "href": "https://mindfulmodeler.substack.com/p/making-tabular-foundation-models"
    },
    {
      "type": "internal",
      "href": "https://mindfulmodeler.substack.com/p/time-series-forecasting-with-tabular"
    },
    {
      "type": "internal",
      "href": "https://mindfulmodeler.substack.com/p/train-or-test-for-feature-effect"
    },
    {
      "type": "internal",
      "href": "https://mindfulmodeler.substack.com/p/context-is-the-new-training"
    },
    {
      "type": "internal",
      "href": "https://mindfulmodeler.substack.com/p/regression-should-predict-full-distributions"
    }
  ],
  "repair_version": 2,
  "repaired_at": "2026-10-20T17:26:12Z",
  "source_url": "https://mindfulmodeler.substack.com/p/tabular-foundation-models",
  "delivery_status": "unverified",
  "discovery_status": "http_404",
  "missing_reason": "http_404",
  "repair_error": "",
  "actual_video_files": [],
  "expected_saved_body_images": 19,
  "image_discovery": "saved_markdown",
  "source_body_markdown": "[![Mindful Modeler](https://substackcdn.com/image/fetch/$s_!WtQm!,w_40,h_40,c_fill,f_auto,q_auto:good,fl_progressive:steep/https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2Fc3dc1d90-fb9f-4e3c-80d5-756a5d6e8495_500x500.png)](https://mindfulmodeler.substack.com/)\n# [Mindful Modeler](https://mindfulmodeler.substack.com/)\nSubscribeSign in\n[Home](https://mindfulmodeler.substack.com/)\n[Tabular Foundation Models](https://mindfulmodeler.substack.com/t/tabular-foundation-models)\n[Archive](https://mindfulmodeler.substack.com/archive)\n[About](https://mindfulmodeler.substack.com/about)\n## Page not found\nLatestTopDiscussions\n[Trends in tabular foundation research](https://mindfulmodeler.substack.com/p/trends-in-tabular-foundation-research)\n[Based on 151 papers from ICML workshop \"Foundation Models for Structured Data\"](https://mindfulmodeler.substack.com/p/trends-in-tabular-foundation-research)\nJul 22 • [Christoph Molnar](https://substack.com/@christophmolnar)\n28\n3\n[Time for a change](https://mindfulmodeler.substack.com/p/time-for-a-change)\n[After 4 years of writing, I'm exploring what's next for me in ML / data science / AI (or whatever you want to call it)](https://mindfulmodeler.substack.com/p/time-for-a-change)\nJul 16 • [Christoph Molnar](https://substack.com/@christophmolnar)\n31\n8\n![](https://substackcdn.com/image/fetch/$s_!iTaq!,w_320,h_213,c_fill,f_auto,q_auto:good,fl_progressive:steep,g_center/https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2Fe917e8f4-41be-4861-b507-0d730a2978aa_4000x3000.jpeg)\n[TabFM minus the hype](https://mindfulmodeler.substack.com/p/tabfm-minus-the-hype)\n[top performance on TabArena; large model; slow inference; non-commercial license](https://mindfulmodeler.substack.com/p/tabfm-minus-the-hype)\nJul 7 • [Christoph Molnar](https://substack.com/@christophmolnar)\n34\n### June 2026\n[Which ML models produce the best quantile estimates?](https://mindfulmodeler.substack.com/p/which-regressor-produces-the-best)\n[Results from ScoringBench](https://mindfulmodeler.substack.com/p/which-regressor-produces-the-best)\nJun 30 • [Christoph Molnar](https://substack.com/@christophmolnar)\n14\n2\n![](https://substackcdn.com/image/fetch/$s_!YaZ6!,w_320,h_213,c_fill,f_auto,q_auto:good,fl_progressive:steep,g_center/https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2F9f34ec3a-89c7-470f-bdce-9f7dad26d3fe_1704x1438.png)\n[When trees still beat tabular foundation models](https://mindfulmodeler.substack.com/p/when-trees-still-beat-tabular-foundation)\n[As you might have noticed, I’m rather optimistic about tabular foundation models.](https://mindfulmodeler.substack.com/p/when-trees-still-beat-tabular-foundation)\nJun 23 • [Christoph Molnar](https://substack.com/@christophmolnar)\n30\n8\n1\n![](https://substackcdn.com/image/fetch/$s_!oYhD!,w_320,h_213,c_fill,f_auto,q_auto:good,fl_progressive:steep,g_center/https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2Fe50e172c-79da-4794-887b-985db0bf8975_958x600.png)\n[What is TabPFN's Thinking mode?](https://mindfulmodeler.substack.com/p/what-is-tabpfns-thinking-mode)\n[When I read the TabPFN-3 Technical Report, the benchmark for “TabPFN-3-Thinking” stood out: it appeared at the top of the TabArena benchmark for large…](https://mindfulmodeler.substack.com/p/what-is-tabpfns-thinking-mode)\nJun 16 • [Christoph Molnar](https://substack.com/@christophmolnar)\n16\n1\n2\n![](https://substackcdn.com/image/fetch/$s_!gjiu!,w_320,h_213,c_fill,f_auto,q_auto:good,fl_progressive:steep,g_center/https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2F7023d57a-ef28-4666-84b8-4ccedca2e31f_1600x640.png)\n[How TabICL and TabPFN handle missing values](https://mindfulmodeler.substack.com/p/how-tabicl-and-tabpfn-handle-missing)\n[You can give training or test data with missing values to the tabular foundation models TabPFN and TabICL, and the prediction will “just work”.](https://mindfulmodeler.substack.com/p/how-tabicl-and-tabpfn-handle-missing)\nJun 9 • [Christoph Molnar](https://substack.com/@christophmolnar)\n23\n1\n3\n[TabPFN and TabICL are not everything](https://mindfulmodeler.substack.com/p/tabpfn-and-tabicl-are-not-everything)\n[An overview of other families for tabular foundation models](https://mindfulmodeler.substack.com/p/tabpfn-and-tabicl-are-not-everything)\nJun 2 • [Christoph Molnar](https://substack.com/@christophmolnar)\n22\n2\n![](https://substackcdn.com/image/fetch/$s_!6fms!,w_320,h_213,c_fill,f_auto,q_auto:good,fl_progressive:steep,g_center/https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2Fe281ed90-32d8-4349-ac3c-4a64c4b11bbc_1788x1246.png)\n### May 2026\n[I’m writing a book on Tabular Foundation Models](https://mindfulmodeler.substack.com/p/im-writing-a-book-on-tabular-foundation)\n[tl;dr: In-progress book here: tabularfoundationmodels.com](https://mindfulmodeler.substack.com/p/im-writing-a-book-on-tabular-foundation)\nMay 26 • [Christoph Molnar](https://substack.com/@christophmolnar)\n33\n12\n2\n![](https://substackcdn.com/image/fetch/$s_!y3mi!,w_320,h_213,c_fill,f_auto,q_auto:good,fl_progressive:steep,g_center/https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2Fec1d5cb1-4679-4ecf-9439-c9cc6815d4b2_1536x1024.png)\n[Tabular ML is entering a new benchmark era](https://mindfulmodeler.substack.com/p/tabular-ml-is-entering-a-new-benchmark)\n[From static and narrow benchmarks to live, capability-driven evaluation](https://mindfulmodeler.substack.com/p/tabular-ml-is-entering-a-new-benchmark)\nMay 19 • [Christoph Molnar](https://substack.com/@christophmolnar)\n16\n[How to make Tabular Foundation Model inference faster](https://mindfulmodeler.substack.com/p/making-tabular-foundation-models)\n[GPU, KV caching, context optimization, and other inference tricks](https://mindfulmodeler.substack.com/p/making-tabular-foundation-models)\nMay 12 • [Christoph Molnar](https://substack.com/@christophmolnar)\n21\n2\n1\n![](https://substackcdn.com/image/fetch/$s_!rUcO!,w_320,h_213,c_fill,f_auto,q_auto:good,fl_progressive:steep,g_center/https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2F1dfcc84c-a949-498f-af28-5073b11bca45_1491x1108.png)\n[Time series forecasting with tabular foundation models](https://mindfulmodeler.substack.com/p/time-series-forecasting-with-tabular)\n[This post is a quick primer on using tabular foundation models for time series forecasting.](https://mindfulmodeler.substack.com/p/time-series-forecasting-with-tabular)\nMay 5 • [Christoph Molnar](https://substack.com/@christophmolnar)\n19\n4\n3\n![](https://substackcdn.com/image/fetch/$s_!V5E8!,w_320,h_213,c_fill,f_auto,q_auto:good,fl_progressive:steep,g_center/https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2Fb0c3443c-2245-4268-baf5-616381849210_1000x300.png)\n### April 2026\n[Train or Test for Feature Effect Estimation? We Finally Have an Answer](https://mindfulmodeler.substack.com/p/train-or-test-for-feature-effect)\n[A guest post by XAI researcher Timo Heiß](https://mindfulmodeler.substack.com/p/train-or-test-for-feature-effect)\nApr 28 • [Christoph Molnar](https://substack.com/@christophmolnar)\n16\n3\n3\n![](https://substackcdn.com/image/fetch/$s_!NrCF!,w_320,h_213,c_fill,f_auto,q_auto:good,fl_progressive:steep,g_center/https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2F267210ea-da1c-4986-914e-30f62e0d229b_2048x560.png)\n[Context is the new training](https://mindfulmodeler.substack.com/p/context-is-the-new-training)\n[Tabular foundation models replace retraining with editable inference-time data](https://mindfulmodeler.substack.com/p/context-is-the-new-training)\nApr 21 • [Christoph Molnar](https://substack.com/@christophmolnar)\n39\n1\n3\n![](https://substackcdn.com/image/fetch/$s_!Ulhx!,w_320,h_213,c_fill,f_auto,q_auto:good,fl_progressive:steep,g_center/https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2F1211af11-578b-48a9-bd81-8b452fb79103_1184x784.png)\n[Regression should predict full distributions](https://mindfulmodeler.substack.com/p/regression-should-predict-full-distributions)\n[A \"hidden\" feature of tabular foundation models](https://mindfulmodeler.substack.com/p/regression-should-predict-full-distributions)\nApr 14 • [Christoph Molnar](https://substack.com/@christophmolnar)\n39\n2\n1\n![](https://substackcdn.com/image/fetch/$s_!Gx8X!,w_320,h_213,c_fill,f_auto,q_auto:good,fl_progressive:steep,g_center/https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2F2beb351b-2bac-4b18-8147-8d01d4517dbe_863x470.png)\n### March 2026\n[TabArena explained](https://mindfulmodeler.substack.com/p/tabarena-explained)\n[What chess ratings tell us about ML models](https://mindfulmodeler.substack.com/p/tabarena-explained)\nMar 31 • [Christoph Molnar](https://substack.com/@christophmolnar)\n20\n4\n1\n![](https://substackcdn.com/image/fetch/$s_!hjDv!,w_320,h_213,c_fill,f_auto,q_auto:good,fl_progressive:steep,g_center/https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2Fa71d3775-e773-4dca-886f-318b69b3f6a7_1446x1156.png)\n[The interpretability tax on tabular foundation models](https://mindfulmodeler.substack.com/p/tabular-foundation-models-break-the)\n[Model-agnostic interpretability for tabular foundation models](https://mindfulmodeler.substack.com/p/tabular-foundation-models-break-the)\nMar 24 • [Christoph Molnar](https://substack.com/@christophmolnar)\n25\n9\n1\n![](https://substackcdn.com/image/fetch/$s_!0FrG!,w_320,h_213,c_fill,f_auto,q_auto:good,fl_progressive:steep,g_center/https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2F150a56bd-72a6-48e7-9489-4f74e15d4a0f_470x326.png)\n[I’m betting on tabular foundation models](https://mindfulmodeler.substack.com/p/im-betting-on-tabular-foundation)\n[The shipping container moment of data science](https://mindfulmodeler.substack.com/p/im-betting-on-tabular-foundation)\nMar 17 • [Christoph Molnar](https://substack.com/@christophmolnar)\n66\n9\n9\n![](https://substackcdn.com/image/fetch/$s_!-ksB!,w_320,h_213,c_fill,f_auto,q_auto:good,fl_progressive:steep,g_center/https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2F0be3299c-0807-4bef-840b-9f4c129de249_1800x580.png)\n[The Random Forest of the 2030s?](https://mindfulmodeler.substack.com/p/the-random-forest-of-the-2030s)\n[Three scenarios for the future of tabular ML, plus one that makes them all irrelevant](https://mindfulmodeler.substack.com/p/the-random-forest-of-the-2030s)\nMar 3 • [Christoph Molnar](https://substack.com/@christophmolnar)\n24\n2\n### February 2026\n[A regression example with TabICLv2](https://mindfulmodeler.substack.com/p/a-regression-example-with-tabiclv2)\n[Strong performance at a steep interpretability cost (at least on CPU)](https://mindfulmodeler.substack.com/p/a-regression-example-with-tabiclv2)\nFeb 24 • [Christoph Molnar](https://substack.com/@christophmolnar)\n27\n3\n1\n![](https://substackcdn.com/image/fetch/$s_!M7CC!,w_320,h_213,c_fill,f_auto,q_auto:good,fl_progressive:steep,g_center/https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2F0ad63a8d-79be-4b78-8664-ea200a7e7e20_742x441.png)\n[The state of Tabular Foundation Models (2026)](https://mindfulmodeler.substack.com/p/the-state-of-tabular-foundation-models)\n[Pre-trained models, startups, and recommendation.](https://mindfulmodeler.substack.com/p/the-state-of-tabular-foundation-models)\nFeb 17 • [Christoph Molnar](https://substack.com/@christophmolnar)\n41\n7\n4\n![](https://substackcdn.com/image/fetch/$s_!YTRY!,w_320,h_213,c_fill,f_auto,q_auto:good,fl_progressive:steep,g_center/https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2Fddcb6f80-9bd2-4ec7-b4a8-f40bceec1d90_1329x840.png)\n[How Tabular Foundation Models learn without real data](https://mindfulmodeler.substack.com/p/how-tabular-foundation-models-are)\n[The pre-training recipe behind TFMs](https://mindfulmodeler.substack.com/p/how-tabular-foundation-models-are)\nFeb 10 • [Christoph Molnar](https://substack.com/@christophmolnar)\n36\n2\n4\n![](https://substackcdn.com/image/fetch/$s_!n20i!,w_320,h_213,c_fill,f_auto,q_auto:good,fl_progressive:steep,g_center/https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2F39f86456-9714-406d-9a88-a3001b046718_1026x627.png)\n[The architecture behind TabPFN](https://mindfulmodeler.substack.com/p/the-architecture-behind-tabpfn)\n[How transformers learn from entire tables](https://mindfulmodeler.substack.com/p/the-architecture-behind-tabpfn)\nFeb 3 • [Christoph Molnar](https://substack.com/@christophmolnar)\n43\n7\n1\n![](https://substackcdn.com/image/fetch/$s_!GCOl!,w_320,h_213,c_fill,f_auto,q_auto:good,fl_progressive:steep,g_center/https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2F3950d661-5102-49f8-b48c-ac8bc693bc7e_518x642.png)\n### January 2026\n[How PFNs make tabular foundation models work](https://mindfulmodeler.substack.com/p/how-pfns-make-tabular-foundation)\n[Bayesian logic, synthetic priors, and in-context learning](https://mindfulmodeler.substack.com/p/how-pfns-make-tabular-foundation)\nJan 21 • [Christoph Molnar](https://substack.com/@christophmolnar)\n62\n2\n4\n![](https://substackcdn.com/image/fetch/$s_!95JB!,w_320,h_213,c_fill,f_auto,q_auto:good,fl_progressive:steep,g_center/https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2F3bd93c38-a5df-459d-aa0c-9a75fb7a6dfd_1916x941.png)\n© 2026 Christoph Molnar · [Privacy](https://substack.com/privacy) ∙ [Terms](https://substack.com/tos) ∙ [Collection notice](https://substack.com/ccpa#personal-data-collected)\n[ Start your Substack](https://substack.com/signup?utm_source=substack&utm_medium=web&utm_content=footer)[Get the app](https://substack.com/app/app-store-redirect?utm_campaign=app-marketing&utm_content=web-footer-button)\n[Substack](https://substack.com) is the home for great culture\n",
  "body_base_path": "attachments/c88507d419d1/pages/",
  "body_markdown_path": "attachments/c88507d419d1/pages/archived-body.md",
  "local_html": "attachments/c88507d419d1/pages/archived-body.html",
  "body_source": "prior_capture"
}