Marcelo Der Torossian Torres — accepted AI-conference papers

2026

Scaling Multi-Task Bayesian Optimization with Large Language Models

Yimeng Zeng, Natalie Maus, Haydn Thomas Jones, Jeffrey Tao, Fangping Wan, Marcelo Der Torossian Torres +4

ICLR 2026poster

In multi-task Bayesian optimization, the goal is to leverage experience from optimizing existing tasks to improve the efficiency of optimizing new ones. While approaches using multi-task Gaussian processes or deep kernel transfer exist, the performance improvement is marginal when scaling beyond a m…

Cited by 0 Source ↗code ↗Scholar ↗

2025

A Dataset for Distilling Knowledge Priors from Literature for Therapeutic Design

Haydn Thomas Jones, Natalie Maus, Josh magnus Ludan, Maggie Ziyu Huan, Jiaming Liang, Marcelo Der Torossian Torres +6

NeurIPS 2025poster

AI-driven discovery can greatly reduce design time and enhance new therapeutics' effectiveness. Models using simulators explore broad design spaces but risk violating implicit constraints due to a lack of experimental priors. For example, in a new analysis across diverse models on the GuacaMol bench…

Cited by 0 Source ↗Scholar ↗

2025

Covering Multiple Objectives with a Small Set of Solutions Using Bayesian Optimization

Natalie Maus, Kyurae Kim, Yimeng Zeng, Haydn Thomas Jones, Fangping Wan, Marcelo Der Torossian Torres +2

NeurIPS 2025poster

In multi-objective black-box optimization, the goal is typically to find solutions that optimize a set of $T$ black-box objective functions, $f_1, \ldots f_T$, simultaneously. Traditional approaches often seek a single Pareto-optimal set that balances trade-offs among all objectives. In contrast, w…

Cited by 0 Source ↗code ↗Scholar ↗