David Saikali

2 accepted papers

2026

Constrained Molecule Generation Modelled Using the Grammar Constraint

AAAI 2026technical

Drug discovery is a very time-consuming and costly endeavour due to its huge design space and to the lengthy and failure-fraught process of bringing a product to market. Automating the generation of candidate molecules exhibiting some of the desired properties can help. Among the standard formats to

Cited by 0 Source ↗PDF ↗Scholar ↗

2025

Constrained Sequential Inference in Machine Learning Using Constraint Programming

Virasone Manibod, David Saikali, Gilles Pesant

IJCAI 2025

Sequence models in machine learning often struggle to exhibit long-term structure. We consider this problem at inference time in the context of enforcing constraints that are not necessarily featured in the dataset on which the generative model was trained. The difficulty lies in imposing previously

Cited by 0 Source ↗PDF ↗code ↗Scholar ↗