Alexandre Duplessis — accepted AI-conference papers

2026

MacroGuide: Topological Guidance for Macrocycle Generation

Alicja Maksymiuk, Alexandre Duplessis, Ismail Ceylan, Alexander Tong, Fernanda Duarte, Michael Bronstein

ICML 2026poster

Macrocycles are ring-shaped molecules that offer a promising alternative to small-molecule drugs due to their enhanced selectivity and binding affinity against difficult targets. Despite their chemical value, they remain underexplored in generative modeling, likely owing to their scarcity in public …

Cited by 0 Source ↗Scholar ↗

2025

Unlearning-based Neural Interpretations

Ching Lam Choi, Alexandre Duplessis, Serge Belongie

ICLR 2025oral

Gradient-based interpretations often require an anchor point of comparison to avoid saturation in computing feature importance. We show that current baselines defined using static functions—constant mapping, averaging or blurring—inject harmful colour, texture or frequency assumptions that deviate f…

Cited by 0 Source ↗PDF ↗Scholar ↗

2024

On the Stability of Iterative Retraining of Generative Models on their own Data

Quentin Bertrand, Joey Bose, Alexandre Duplessis, Marco Jiralerspong, Gauthier Gidel

ICLR 2024spotlight

Deep generative models have made tremendous progress in modeling complex data, often exhibiting generation quality that surpasses a typical human's ability to discern the authenticity of samples. Undeniably, a key driver of this success is enabled by the massive amounts of web-scale data consumed by…

Cited by 45 Source ↗PDF ↗code ↗Scholar ↗