PUICL is a transformer pretrained on synthetic PU data from structural causal models that solves positive-unlabeled classification via in-context learning without gradient updates or fitting.
nanotabpfn: A lightweight and educa- tional reimplementation of tabpfn
3 Pith papers cite this work. Polarity classification is still indexing.
3
Pith papers citing it
years
2026 3verdicts
UNVERDICTED 3representative citing papers
KnowsTFM adapts small TabPFN- and TabICL-style models with knowledge-graph structural attention priors and low-rank updates, yielding gains in specialist tabular tasks but marginal benefits on general tasks.
O'Prior, a compositional synthetic prior with hierarchical SCMs, realism engines, stress modules, and curriculum protocols, improves tabular foundation model accuracy and robustness on real benchmarks when architecture and compute are held fixed.
citing papers explorer
-
In-Context Positive-Unlabeled Learning
PUICL is a transformer pretrained on synthetic PU data from structural causal models that solves positive-unlabeled classification via in-context learning without gradient updates or fitting.
-
KnowsTFM: Knowledge-Informed Fine-Tuning of Small Tabular Foundation Models
KnowsTFM adapts small TabPFN- and TabICL-style models with knowledge-graph structural attention priors and low-rank updates, yielding gains in specialist tabular tasks but marginal benefits on general tasks.
-
Shaping the Prior: How Synthetic Task Distributions Determine Tabular Foundation Model Quality
O'Prior, a compositional synthetic prior with hierarchical SCMs, realism engines, stress modules, and curriculum protocols, improves tabular foundation model accuracy and robustness on real benchmarks when architecture and compute are held fixed.