Portrait of Diego Calanzone

Diego Calanzone

PhD - Université de Montréal
Supervisor
Pierre-Luc Bacon
Research Topics
Computational Biology
Reinforcement Learning
Website
Google Scholar
GitHub

Publications

Mol-MoE: Training Preference-Guided Routers for Molecule Generation
Diego Calanzone
Pierluca D'Oro
Pierre-Luc Bacon
Recent advances in language models have enabled framing molecule generation as sequence modeling. However, existing approaches often rely on… (see more) single-objective reinforcement learning, limiting their applicability to real-world drug design, where multiple competing properties must be optimized. Traditional multi-objective reinforcement learning (MORL) methods require costly retraining for each new objective combination, making rapid exploration of trade-offs impractical. To overcome these limitations, we introduce Mol-MoE, a mixture-of-experts (MoE) architecture that enables efficient test-time steering of molecule generation without retraining. Central to our approach is a preference-based router training objective that incentivizes the router to combine experts in a way that aligns with user-specified trade-offs. This provides improved flexibility in exploring the chemical property space at test time, facilitating rapid trade-off exploration. Benchmarking against state-of-the-art methods, we show that Mol-MoE achieves superior sample quality and steerability.
2025-03-05
ICLR.cc/2025/Workshop/GEM (published)
doi.org
openreview.net
Mol-MoE: Training Preference-Guided Routers for Molecule Generation
Diego Calanzone
Pierluca D'Oro
Pierre-Luc Bacon
Recent advances in language models have enabled framing molecule generation as sequence modeling. However, existing approaches often rely on… (see more) single-objective reinforcement learning, limiting their applicability to real-world drug design, where multiple competing properties must be optimized. Traditional multi-objective reinforcement learning (MORL) methods require costly retraining for each new objective combination, making rapid exploration of trade-offs impractical. To overcome these limitations, we introduce Mol-MoE, a mixture-of-experts (MoE) architecture that enables efficient test-time steering of molecule generation without retraining. Central to our approach is a preference-based router training objective that incentivizes the router to combine experts in a way that aligns with user-specified trade-offs. This provides improved flexibility in exploring the chemical property space at test time, facilitating rapid trade-off exploration. Benchmarking against state-of-the-art methods, we show that Mol-MoE achieves superior sample quality and steerability.
2025-02-08
ArXiv (preprint)
arxiv.org
arxiv.org