Understand this story
In an ICML 2026 blog post, LG AI Research pointed out that tabular foundation models such as TabPFN suffer from label shift: among 253 OpenML datasets, about 85% (214) are class-imbalanced, and in extreme cases 98.3% of test samples were predicted as the majority class, with minority-class recall nearly collapsing. To address this, LG AI Research proposed DistPFN, which at inference time multiplies predicted probabilities by a correction factor based on relative training class proportions, requiring no architecture changes, retraining, or estimation of the test label distribution. The work is currently published as an official blog post, with no further progress disclosed.
AI-generated from public reports
Latest development · Report
LG AI Research at ICML 2026: Structured Data Foundation Models and the State of Time-Series Deep LearningDevelopments
1 confirmed developments
LG AI Research proposes DistPFN to mitigate label shift in tabular models
Source:English text is being prepared.
Reports and discussion timeline
Browse reports and discussion by time. Their evidence levels remain distinct.
Nov 3
LG AI Research official blogFirst-party
LG AI Research at ICML 2026: Structured Data Foundation Models and the State of Time-Series Deep Learning
In its ICML 2026 blog, LG AI Research points out that tabular foundation models such as TabPFN suffer from label shift: among 253 OpenML datasets, about 85% (214) are class-imbalanced, and in extreme cases 98.3% of test samples are predicted as the majority class, with minority-class recall nearly collapsing. The team proposes DistPFN, which at inference time multiplies predicted probabilities by a correction factor based on relative training class proportions, without changing the architecture, retraining, or estimating the test label distribution. ICML 2026 received a total of 23,918 submissions and accepted 6,352, for an acceptance rate of 26.6%.