Itsuki·4d agoSwiftUI: Table + TabularData = Handling Unknown DynamicA simple CSV Editor in PURE SwiftUI! Dynamic Tables. Edit, Sort, Append, Delete.
ComfyAI·Oct 24TabPFN-MT: One Forward Pass, Every TargetTables often come with several related prediction targets. A clinical trial tracks multiple key endpoints. In finance, you might want to…
ComfyAI·Oct 22Is Tabular Data Generation Really “Nearly Perfect,” or Are the Metrics Just Too Easy?Tabular data generation is widely seen as having made huge strides in recent years. Diffusion models like TabDiff and TabSyn now score…
ComfyAI·Oct 18TabDiff: Teaching Diffusion Models That Every Column Is DifferentTabDiff tackles tabular data generation, and tables are hard to generate because they don’t behave like images or text.
ComfyAI·Oct 17TabSyn: Bringing Diffusion Models to Mixed-Type Tabular Data Through a Latent SpaceTabSyn is about tabular data synthesis: training a model to generate rows realistic enough to pass for the real thing, whether to augment a…
ComfyAI·Oct 15CTSyn: Toward a Foundation Model for Generating Tabular DataImages and text both have powerful generative foundation models. Tabular data, however, has always been the awkward one. Tables differ…
ComfyAI·Oct 5TSPFN: Bringing Tabular Foundation Models to Physiological Time Series ClassificationThis paper takes the idea behind tabular foundation models and applies it to physiological time series classification, meaning…
Rayan Yassminh·Oct 1The Right Data Structure Starts With the QuestionHow to choose between tabular, tree, and graph data
ComfyAI·Sep 25LimiX-2: When a Tabular Foundation Model Learns to See CausalityThe mainstream approach to tabular foundation models — TabPFN and its lineage — follows the PFN playbook: pretrain on synthetic tasks, then…
ComfyAI·Sep 24TabPFN-3.5: Closing the Gap Between Clean Benchmarks and Messy RealityPrior Labs just dropped the TabPFN-3.5 technical report, and its central thread is moving from clean data to real-world data.
