Institution profile

Layer 6 AI

Industry researchnorthamerica · ca
Official website
Research library36linked papers
Opportunities0open roles
Selected work

Representative Papers

TabDPT: Scaling Tabular Foundation Models

Oct 23, 2024arXiv.org

Tabular data exhibit strong heterogeneity, and existing models suffer from poor generalization and difficulty in zero-shot adaptation to new tasks. Method: We propose the Discriminative Tabular Pre-trained Transformer (TabDPT), the first framework integrating real-table-driven self-supervised pretraining with retrieval-augmented in-context learning (ICL). It introduces numerical-aware embedding and attention mechanisms, alongside a lightweight discriminative architecture. Contribution/Results: TabDPT achieves true zero-shot cross-task generalization without fine-tuning—overcoming a key bottleneck in large language models’ handling of structured numerical tables. It attains state-of-the-art zero-shot performance on the CC18 classification and CTR23 regression benchmarks. Performance scales consistently with both model and data size, while maintaining efficient inference and strong scalability.

8 citations2 influentialRead paper

Causal Foundation Models

Sep 02, 2026

该研究通过预训练神经网络(因果基础模型CFMs)在不更新模型的情况下估计新的数据集中的因果量,如平均治疗效果,来解决传统因果推理需要为每个新问题定制流程的问题。

0 citationsRead paper
Recent publications

Latest Papers

Causal Foundation Models

Sep 02, 2026

该研究通过预训练神经网络(因果基础模型CFMs)在不更新模型的情况下估计新的数据集中的因果量,如平均治疗效果,来解决传统因果推理需要为每个新问题定制流程的问题。

0 citationsRead paper

Training Fair Tabular Foundation Models

Aug 14, 2026

This study addresses the lack of fairness guarantees in tabular foundation models for high-stakes decision-making and the incompatibility of existing methods with in-context learning when sensitive attributes are unavailable. We propose FairTFM, a novel fair training strategy that embeds fairness constraints directly into the training process via synthetic fair tasks and gradient reversal layers. This approach enables representation debiasing and fair prediction within a single forward pass. Extensive experiments across 132 tasks demonstrate that FairTFM significantly improves fairness metrics while maintaining competitive predictive accuracy. Consequently, this work effectively resolves the challenges associated with restricted access to sensitive attributes and incompatibility with in-context learning, providing a robust solution for deploying equitable tabular foundation models in critical applications.

0 citationsRead paper