Tabular foundation models excel on tiny- to medium-sized IID data but are outperformed by traditional tree-based and deep learning models on non-IID, large, and high-dimensional datasets, based on evaluations across 11 models and 142 datasets in the new BeyondArena benchmark.
Tabpfn: One model to rule them all?
8 Pith papers cite this work. Polarity classification is still indexing.
8
Pith papers citing it
citation-role summary
background 1
citation-polarity summary
verdicts
UNVERDICTED 8roles
background 1polarities
background 1representative citing papers
Transformers can implement gradient descent targeting posterior predictive mean and variance followed by binning to approximate PPDs in-context for Gaussian process regression.
PFN-TS converts PFN posterior predictives into mean-reward samples for Thompson sampling using a subsampled predictive CLT, with consistency proofs, regret bounds, and strong empirical performance on synthetic and real bandit benchmarks.
POLAR uses pretrained predictive foundation models as fixed belief-state encoders and trains only a lightweight policy head on top for amortised Bayesian experimental design, optimisation, and active learning.
Complementing tabular foundation model pretraining with LSBO-specific synthetic tasks and a regularizer yields strong performance on held-out molecular optimization benchmarks.
TabPFN-2.5 scales tabular foundation models to 20x larger datasets, outperforms tuned tree models on TabArena, achieves near-perfect win rates against default XGBoost, and adds a distillation engine for fast production deployment.
Adaptive distance learning via scoring rules for out-of-sample performance improves ABC and localized NPE-PFN on misspecified time series and connects to linear pooling of forecasts.
A review organizes externally controlled trial methodology through causal estimands and identifiability assumptions for single-arm and hybrid designs with borrowing strategies.
citing papers explorer
-
Beyond IID: How General Are Tabular Foundation Models, Really?
Tabular foundation models excel on tiny- to medium-sized IID data but are outperformed by traditional tree-based and deep learning models on non-IID, large, and high-dimensional datasets, based on evaluations across 11 models and 142 datasets in the new BeyondArena benchmark.
-
Transformers Can Learn Posterior Predictive Distributions In-Context
Transformers can implement gradient descent targeting posterior predictive mean and variance followed by binning to approximate PPDs in-context for Gaussian process regression.
-
PFN-TS: Thompson Sampling for Contextual Bandits via Prior-Data Fitted Networks
PFN-TS converts PFN posterior predictives into mean-reward samples for Thompson sampling using a subsampled predictive CLT, with consistency proofs, regret bounds, and strong empirical performance on synthetic and real bandit benchmarks.
-
Efficient Adaptive Data Acquisition via Pretrained Belief Representations
POLAR uses pretrained predictive foundation models as fixed belief-state encoders and trains only a lightweight policy head on top for amortised Bayesian experimental design, optimisation, and active learning.
-
In-Context Learning for Latent Space Bayesian Optimization
Complementing tabular foundation model pretraining with LSBO-specific synthetic tasks and a regularizer yields strong performance on held-out molecular optimization benchmarks.
-
TabPFN-2.5: Advancing the State of the Art in Tabular Foundation Models
TabPFN-2.5 scales tabular foundation models to 20x larger datasets, outperforms tuned tree models on TabArena, achieves near-perfect win rates against default XGBoost, and adds a distillation engine for fast production deployment.
-
Learning the distance for ABC and localized neural posterior estimation
Adaptive distance learning via scoring rules for out-of-sample performance improves ABC and localized NPE-PFN on misspecified time series and connects to linear pooling of forecasts.
-
Externally Controlled Trials: A Review of Design and Borrowing Through a Causal Lens
A review organizes externally controlled trial methodology through causal estimands and identifiability assumptions for single-arm and hybrid designs with borrowing strategies.