PulseAugur
中
实时 00:38:57

新研究推动表格基础模型实现高效和鲁棒性

多篇研究论文探讨了表格基础模型(TFMs)的进展,重点关注提高其效率、鲁棒性和适应性。知识蒸馏等技术正被用于从大型TFM创建更小、更快的学生模型,而RelICL和VIP-COP等新方法则解决了关系学习和上下文优化中的挑战。此外,研究正在探索架构选择和参数高效适应策略,以增强TFM在亚群体偏移和大规模数据集等各种数据条件下的性能。 AI

影响 这些进展旨在使表格基础模型在更广泛的实际应用中更高效、更鲁棒、更具适应性。

排序理由 多篇在arXiv上发表的研究论文,详细介绍了表格基础模型的新方法和模型。

在 arXiv cs.LG 阅读 →

AI 生成摘要 · Google Gemini · 来自 18 个来源。 我们如何撰写摘要 →

新研究推动表格基础模型实现高效和鲁棒性

本文如何被排名

Signal score
0 / 100
Composite score across the factors below. Higher = stronger signal that this story matters right now.
Newsworthiness bucket
Research
多篇在arXiv上发表的研究论文,详细介绍了表格基础模型的新方法和模型。
Source corroboration
18 independent sources
Strong cross-source corroboration — multiple independent publishers covered this within the clustering window.
Topics
paper, model release
Editorial topic classification. Feeds into how the story surfaces on /topic/<slug> hub pages and into the per-entity coverage mix.
AI-industry relevance
High
Clearly on-topic for AI-industry coverage.
Story freshness
50 days old
Aged out of breaking-news scoring windows; ranking reflects the durable signal from the full source set.
Coverage growth since scoring
+4 source(s) since last score
New sources have picked up this story since our last re-score. Score will update on the next scoring pass.

完整方法见我们的编辑标准。

报道来源 [18]

  1. arXiv cs.LG TIER_1 English(EN) · Kanghui Ning, Marin Bilo\v{s}, James T. Wilson, Yilang Zhang, Kashif Rasul, Dongjin Song, Anderson Schneider, Yuriy Nevmyvaka ·

    表格基础模型的测试时间计算:机制、收益和局限性

    arXiv:2610.12005v1 Announce Type: new Abstract: Which forms of test-time compute improve the predictions of strong pretrained tabular foundation models (TFMs)? We systematically study this along three axes: adaptation, aggregation, and context construction. Our evaluation spans m…

  2. arXiv cs.LG TIER_1 English(EN) · Hao-Run Cai, Si-Yang Liu, Zi-Jian Cheng, Kun-Yang Yu, Jin-Hao Sheng, Guo Yu, Chonghan Liu, Zhi Zhou, Jun-Peng Jiang, Lan-Zhe Guo, Han-Jia Ye ·

    深度思考:表格基础模型的追溯推理

    arXiv:2610.10317v1 Announce Type: new Abstract: Tabular foundation models (TFMs) are pretrained across diverse tabular tasks and make predictions on a new table at inference time using its labeled examples as context. Most recent TFMs perform such in-context prediction with stack…

  3. arXiv cs.LG TIER_1 English(EN) · Mohamed Bouadi, Nassim Bouarour, Shivam Dubey, Aditya Tanna, Vinay Kumar Sankarapu ·

    从行为到出处:将表格基础模型归因于合成预训练数据

    arXiv:2610.02347v1 Announce Type: new Abstract: Training-data attribution aims to identify which training examples shape model behavior, yet validating such claims is difficult because causal training influence is rarely observable. We argue that controlled synthetic pretraining …

  4. arXiv cs.LG TIER_1 English(EN) · Minho Jeong, Dooho Lee, Jinmo Lee, Jaemin Yoo ·

    将表格基础模型蒸馏成高效预测器

    arXiv:2610.01435v1 Announce Type: new Abstract: Tabular foundation models (TFMs) achieve strong predictive performance through in-context learning, yet repeatedly conditioning on labeled data makes inference expensive. Knowledge distillation can reduce this cost by transferring t…

  5. arXiv cs.LG TIER_1 English(EN) · Simon Forbat, Rainer Gemulla ·

    RelICL:基于表格基础模型的无训练关系学习

    arXiv:2610.01725v1 Announce Type: new Abstract: Tabular foundation models achieve state-of-the-art performance on single-table tasks without any training. Recent work suggests that they are also well-suited for relational learning via deep feature synthesis (DFS), which flattens …

  6. arXiv cs.AI TIER_1 English(EN) · Seonghwi Kim, Sung Ho Jo, Minwoo Chae ·

    参数高效的分布鲁棒性表格基础模型在子群体迁移下的适应性

    arXiv:2610.01143v1 Announce Type: cross Abstract: Despite strong mean accuracy, tabular foundation models (TFMs) can perform poorly on underrepresented groups under subpopulation shift, where group proportions change between training and deployment. We propose DR-TFM, a parameter…

  7. arXiv cs.LG TIER_1 English(EN) · Pengfei Li, Mohammad Khalil ·

    MIND:混合类型表格生成的边际不变神经依赖扩散

    arXiv:2609.39628v1 Announce Type: new Abstract: This paper proposes MIND, a marginal-invariant neural dependency diffusion model for mixed-type tabular data. MIND does not directly learn the joint distribution in the original heterogeneous feature space. Instead, it first maps di…

  8. arXiv cs.LG TIER_1 English(EN) · Yilong Chen, Xueying Ding, Leman Akoglu ·

    VIP-COP:表格基础模型的上下文优化

    arXiv:2605.12904v2 Announce Type: replace Abstract: Tabular foundation models (TFMs) have emerged as a powerful paradigm for in-context learning on structured data, enabling direct prediction on new tabular tasks without task-specific training. However, their effectiveness is con…

  9. arXiv cs.LG TIER_1 English(EN) · Weihao Kong, Erez Louidor Ilan, Shuxin Nie, Taman Narayan, Rajat Sen, Yichen Zhou, Deqing Fu, Samet Oymak, Abhimanyu Das ·

    TabFM:用于表格数据的零样本基础模型

    arXiv:2609.37959v1 Announce Type: new Abstract: Tabular machine learning typically relies on per-dataset workflows, fitting tree ensembles or running AutoML searches from scratch for every task. We present TabFM, a 400M-parameter tabular foundation model that formulates supervise…

  10. arXiv cs.LG TIER_1 English(EN) · Tianqi Zhao, Tianyi Zhuang, Shuo Duan, Guanyang Wang, Yan Shuo Tan, Qiong Zhang ·

    面向表格基础模型的稀疏先验的架构对齐

    arXiv:2609.36883v1 Announce Type: new Abstract: Tabular foundation models (TFMs) are increasingly popular because they deliver strong predictions on new datasets through in-context learning, without task-specific training or extensive tuning. Yet released TFMs differ simultaneous…

  11. arXiv cs.LG TIER_1 English(EN) · David Schnurr, Felix Sarnthein, Thomas Hofmann, Imanol Schlag ·

    为表格上下文学习适配线性时间架构

    arXiv:2609.36337v1 Announce Type: new Abstract: Tabular foundation models achieve strong performance by conditioning on labelled examples in context, but softmax attention limits their use on large datasets. Existing linear-time alternatives, however, are mostly causal, and their…

  12. arXiv cs.LG TIER_1 English(EN) · Deqing Fu, Huangyuan Su, Rajat Sen, Taman Narayan, Sujay Sanghavi, Abhimanyu Das, Weihao Kong ·

    TabFM-Auto:表格基础模型的自演化流水线

    arXiv:2609.37989v1 Announce Type: new Abstract: Tabular foundation models achieve strong zero-shot accuracy on structured data by pretraining on synthetic tables, but they ignore the column names, task descriptions, and auxiliary files that carry dataset semantics. Meanwhile, sel…

  13. arXiv cs.LG TIER_1 English(EN) · Tian Zhou, Beverly Jin, Linxiao Yang, Xue Wang, Wenwei Wang, Bingqing Peng, Mengni Ye, Jinjie Gu, Liang Sun ·

    表格基础模型在上下文中计算什么?通过注意力门控更新进行原地表征细化

    arXiv:2609.27679v2 Announce Type: replace Abstract: A tabular foundation model must discover which distinctions matter for each new table without updating its parameters. We develop in-situ representation refinement: support labels guide changes to the episode's representations, …

  14. arXiv cs.LG TIER_1 English(EN) · Maximilian Schambach, Clemens Biehl, Sam Thelin ·

    基准测试表格基础模型的注意力机制

    arXiv:2609.31306v2 Announce Type: new Abstract: Tabular in-context learners such as TabPFN, Mitra, or ConTextTab rely on alternating row and column attention over 2D sequences of latent embeddings. These attention patterns differ markedly from the one-dimensional case in language…

  15. arXiv cs.LG TIER_1 English(EN) · Tian Zhou, Beverly Jin, Xue Wang, Linxiao Yang, Wenwei Wang, Bingqing Peng, Mengni Ye, Jinjie Gu, Liang Sun ·

    支持编译的特征折叠:表格基础模型在较低内存下提供更多证据

    arXiv:2609.28208v2 Announce Type: replace Abstract: Wide tables offer tabular foundation models more evidence, but accessing it can exhaust their memory: full-width pairwise mixing grows quadratically with the number of columns, while feature selection makes inputs affordable by …

  16. Hugging Face Daily Papers TIER_1 English(EN) ·

    TabFM-Auto:表格基础模型的自演化管道

    Tabular foundation models achieve strong zero-shot accuracy on structured data by pretraining on synthetic tables, but they ignore the column names, task descriptions, and auxiliary files that carry dataset semantics. Meanwhile, self-evolving machine learning engineering (MLE) ag…

  17. Hugging Face Daily Papers TIER_1 English(EN) ·

    TabFM:用于表格数据的零样本基础模型

    Tabular machine learning typically relies on per-dataset workflows, fitting tree ensembles or running AutoML searches from scratch for every task. We present TabFM, a 400M-parameter tabular foundation model that formulates supervised tabular prediction as in-context learning. Tab…

  18. arXiv cs.CV TIER_1 English(EN) · Zhenghao Zhao, Chi Zhang, Qingshuang Chen, Yelin Kim ·

    GRAFT:通过持续教师蒸馏增长集聚基础模型

    arXiv:2610.02597v1 Announce Type: new Abstract: Vision foundation models such as DINOv2, SigLIP2, and MASt3R develop complementary capabilities from different pretraining objectives, yet their knowledge remains distributed across separate, specialized models. Multi-teacher knowle…