20 benchmarks

The '20 benchmarks' dataset consists of a variety of tasks used to evaluate the performance of models in learning complex probability distributions across different domains.

Papers using 20 benchmarks (2)

Fourier Head: Helping Large Language Models Learn Complex Probability Distributions2024 · 1 citesDDTime: Dataset Distillation with Spectral Alignment and Information Bottleneck for Time-Series Forecasting2025