← Search

Si-Yang Liu

2 accepted papers

2026

SwiftPFN: Revisiting Row-Wise Attention–Only Tabular Foundation Models with Adaptive Early Exit

ICML 2026spotlight

Tabular foundation models, exemplified by TabPFN, perform prediction via in-context learning, inferring test labels directly from labeled training examples. They have demonstrated competitive performance, particularly on small-to-medium datasets. However, recent tabular foundation models often impro…

Cited by 0SourceScholar
2025

A Closer Look at TabPFN v2: Understanding Its Strengths and Extending Its Capabilities

NeurIPS 2025poster

Tabular datasets are inherently heterogeneous, presenting significant challenges for developing pre-trained foundation models. The recently introduced transformer-based Tabular Prior-data Fitted Network v2 (TabPFN v2) achieves unprecedented *in-context learning* performance across diverse downstream…

Cited by 0SourceScholar