Jul 2026
TabPFN beyond Tabular Data: Calibration and Accuracy on Multimodal Embeddings
Together, these results identify when TabPFN can serve as a training-free head for calibration-sensitive multimodal classification and show that representation adaptation and reliable head choice are complementary.
Jingxiang Zhang, Lu-Jia Zhong, Zijie Zhu et al.
· arXiv.org · 0 citations