Gianluca Bencomo — accepted AI-conference papers

2025

Hindsight Merging: Diverse Data Generation with Language Models

Veniamin Veselovsky, Benedikt Stroebl, Gianluca Bencomo, Dilip Arumugam, Lisa Schut, Arvind Narayanan +1

UAI 2025

Pre-training a language model equips it with a broad understanding of the world, while fine- tuning refines it into a helpful assistant. However, fine-tuning does not exclusively enhance task- specific behaviors but also suppresses some of the beneficial variability from pre-training. This reduction

Cited by 0 Source ↗PDF ↗Scholar ↗

2024

A Metalearned Neural Circuit for Nonparametric Bayesian Inference

Jake Snell, Gianluca Bencomo, Thomas L. Griffiths

NeurIPS 2024poster

Most applications of machine learning to classification assume a closed set of balanced classes. This is at odds with the real world, where class occurrence statistics often follow a long-tailed power-law distribution and it is unlikely that all classes are seen in a single sample. Nonparametric Bay…

Cited by 2 Source ↗PDF ↗code ↗Scholar ↗

2024

Implicit Maximum a Posteriori Filtering via Adaptive Optimization

Gianluca Bencomo, Jake Snell, Thomas L. Griffiths

ICLR 2024poster

Bayesian filtering approximates the true underlying behavior of a time-varying system by inverting an explicit generative model to convert noisy measurements into state estimates. This process typically requires matrix storage, inversion, and multiplication or Monte Carlo estimation, none of which a…

Cited by 2 Source ↗PDF ↗code ↗Scholar ↗