# Towards Universal Neural Likelihood Inference

arXiv: https://arxiv.org/abs/2508.09100 · HTML: https://mlsanity.com/paper/2508.09100/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 12 Aug 2025.

## Built on by (most cited first, 1 of 1)

- [GOTabPFN: From Feature Ordering to Compact Tokenization for Tabular Foundation Models on High-Dimensional Data](https://mlsanity.com/paper/2606.05441/) (2026)

## Abstract (arXiv)

We introduce universal neural likelihood inference (UNLI): enabling a single model to provide data-grounded, conditional likelihood predictions for arbitrary targets given any collection of observed features, across diverse domains and tasks. To achieve UNLI over heterogeneous tabular data, we develop the Arbitrary Set-based Permutation-Invariant Reasoning Engine (ASPIRE) model. Our design addresses critical gaps in existing approaches to merge semantic-understanding capabilities and generalised numerical feature reasoning within a zero-shot capable framework. Trained on over 1,400 real diverse datasets spanning various domains, ASPIRE achieves 15% higher F1 scores and 85% lower RMSE than existing tabular foundation models in zero-shot and few-shot settings. Lastly, this work introduces open-world active feature acquisition, where we leverage the UNLI capabilities of ASPIRE to adeptly determine next feature-values to observe to improve inference time prediction accuracies.