6 papers
Rethinking Training & Inference for Forecasting: Linking Winner-Take-All back to GMMs
Qiyuan Wu, Katie Z Luo, Bharath Hariharan +2
Trajectory forecasting for autonomous driving has advanced rapidly, yet representative models often produce uninformative posteriors over forecast modes, causing problems for mode…
Beyond Flat Labels: Level-Restricted Contrastive Learning for Hierarchical Fine-Grained Vision Classification
Zhiyuan Tao, Srikumar Sastry, Matthew J Thompson +9
Multimodal contrastive learning has enabled zero-shot visual classification by aligning images with textual categories. However, in hierarchically structured label spaces, existing…
Revisiting Model Stitching In the Foundation Model Era
Zheda Mai, Ke Zhang, Fu-En Wang +6
Model stitching, connecting early layers of one model (source) to later layers of another (target) via a light stitch layer, has served as a probe of representational compatibility…
A Closer Look at TabPFN v2: Understanding Its Strengths and Extending Its Capabilities
Han-Jia Ye, Si-Yang Liu, Wei-Lun Chao
Tabular datasets are inherently heterogeneous, presenting significant challenges for developing pre-trained foundation models. The recently introduced transformer-based Tabular Pri…
Revisiting Nearest Neighbor for Tabular Data: A Deep Tabular Baseline Two Decades Later
Han-Jia Ye, Huai-Hong Yin, De-Chuan Zhan +1
The widespread enthusiasm for deep learning has recently expanded into the domain of tabular data. Recognizing that the advancement in deep tabular methods is often inspired by cla…
Rethinking Pre-Training in Tabular Data: A Neighborhood Embedding Perspective
Han-Jia Ye, Qi-Le Zhou, Huai-Hong Yin +2
Pre-training is prevalent in deep learning for vision and text data, leveraging knowledge from other datasets to enhance downstream tasks. However, for tabular data, the inherent h…