The recipe uses the full labeled training set as teacher context and trains students solely on teacher predictions for observed and synthetic queries, and improves matched default students on 236-258 of 300 datasets and reduces median primary error.
Minho Jeong, Dooho Lee, Jin-Mo Lee et al.· 0 citations
Can a pretrained graph model replace training and tuning a separate predictor for each dataset? Answering this requires evaluating prediction quality alongside computational cost. We present NodeGround, a node classification benchmark that puts graph foundation models (GFMs) and dataset-specific supervised learning und...
The results show that explicit molecular comparisons can strengthen tabular in-context learning for structural generalization while keeping the molecular encoder and pretrained model weights fixed.
Ephris is a new graph in-context learner built on sparse message passing, scaling linearly with the number of node-feature entries and graph edges, demonstrating that strong graph ICL does not require dense attention.
Causilo, a tabular foundation model (TFM) that combines frontier predictive performance with exceptionally fast inference, achieves frontier-level performance with substantially faster inference, placing it on the performance--efficiency Pareto frontier.
Minyong Cho, Minho Jeong, Dooho Lee et al.· 3 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.