paper-with-me

Papers

Speedrunning Tabular Foundation Model Pretraining

2026-06-02 · Salih Bora Ozturk, Alexander Pfefferle, Frank Hutter arxiv

Pretraining cost is a major bottleneck for research on tabular foundation models, slowing the iteration cycle for new architectures, priors, and optimization ideas. Yet the community lacks a simple way to compare and accumulate pretraining speedups. We introduce a community speedrun for nanoTabPFN: contributors modify a single-file training script and compete to reach a fixed downstream ROC AUC target on subsampled TabArena using one NVIDIA L40S GPU. The current best record reaches the target in 0.92 minutes, an 81x speedup over the 74.32 minute baseline while using 22x fewer synthetic datasets. The speedrun format provides a simple protocol for the community to add, verify, and stack pretraining improvements, with the leaderboard open to contributions. Code and records are available at https://github.com/borawhocodess/modded-nanotabpfn.

📄 PDF Abstract BibTeX arXiv:2606.03681

Code (0)

등록된 구현이 없습니다.

Similar Papers 제목 키워드 기반

TabICLv2: A better, faster, scalable, and open tabular foundation model

2026-02-11 · Jingang Qu, David Holzmüller, Gaël Varoquaux, Marine Le Morvan arxiv

Tabular foundation models, such as TabPFNv2 and TabICL, have recently dethroned gradient-boosted trees at the top of predictive benchmarks, demonstrating the value of in-context learning for tabular data. We introduce Ta…

Synthetic Data Generation

Towards Cross-Table Masked Pretraining for Web Data Mining

2023-07-10 · Chao Ye, Guoshan Lu, Haobo Wang, Liyao Li 외

Tabular data pervades the landscape of the World Wide Web, playing a foundational role in the digital architecture that underpins online information. Given the recent influence of large-scale pretrained models like ChatG…

Contrastive Learning

When Tabular Foundation Models Meet Strategic Tabular Data: A Prior Alignment Approach

2026-05-19 · Xinpeng Lv, Yunxin Mao, Renzhe Xu, Chunyuan Zheng 외 arxiv

Tabular foundation models based on pretrained prior-data fitted networks~(PFNs) have shown strong generalization on diverse tabular tasks, but they are typically designed for \emph{non-strategic} settings where data dist…

TabTune: A Unified Library for Inference and Fine-Tuning Tabular Foundation Models

2025-11-04 · Aditya Tanna, Pratinav Seth, Mohamed Bouadi, Utsav Avaiya 외 arxiv

Tabular foundation models represent a growing paradigm in structured data learning, extending the benefits of large-scale pretraining to tabular domains. However, their adoption remains limited due to heterogeneous prepr…

parameter-efficient fine-tuning

nanoTabPFN: A Lightweight and Educational Reimplementation of TabPFN

2025-11-05 · Alexander Pfefferle, Johannes Hog, Lennart Purucker, Frank Hutter arxiv

Tabular foundation models such as TabPFN have revolutionized predictive machine learning for tabular data. At the same time, the driving factors of this revolution are hard to understand. Existing open-source tabular fou…