Frank Hutter

Where to Begin: Efficient Pretraining via Sub-network Selection and Distillation

$\alpha$-PFN: Fast Entropy Search via In-Context Learning

Improving LLM-based Global Optimization with Search Space Partitioning

Multi-objective Hyperparameter Optimization in the Age of Deep Learning

Selective Rotary Position Embedding

TempoPFN: Synthetic Pre-training of Linear RNNs for Zero-shot Time Series Forecasting

GAMformer: Bridging Tabular Foundation Models and Interpretable Machine Learning

DeltaProduct: Improving State-Tracking in Linear RNNs via Householder Products

Unlocking State-Tracking in Linear RNNs Through Negative Eigenvalues

Gompertz Linear Units: Leveraging Asymmetry for Enhanced Learning Dynamics

EquiTabPFN: A Target-Permutation Equivariant Prior Fitted Network

Do-PFN: In-Context Learning for Causal Effect Estimation

Learning in Compact Spaces with Approximately Normalized Transformer

Tuning LLM Judge Design Decisions for 1/1000 of the Cost

Multi-objective Differentiable Neural Architecture Search

Bayesian Neural Scaling Law Extrapolation with Prior-Data Fitted Networks

Beyond Random Augmentations: Pretraining with Hard Views

Diffusion-based Neural Network Weights Generation

KinPFN: Bayesian Approximation of RNA Folding Kinetics using Prior-Data Fitted Networks

FairPFN: A Tabular Foundation Model for Causal Fairness

RNAinformer: Generative RNA Design with Tertiary Interactions

RNAformer: Axial-Attention For Homology-Aware RNA Secondary Structure Prediction

GAMformer: In-Context Learning for Generalized Additive Models

Dynamic Post-Hoc Neural Ensemblers

One-shot World Models Using a Transformer Trained on a Synthetic Prior

Bayes' Power for Explaining In-Context Learning Generalizations

Large Language Models Engineer Too Many Simple Features for Tabular Data

LLMs Boost the Performance of Decision Trees on Tabular Data across Sample Sizes