Research Group
The OPTImization with Multiple Objectives (OptiMO) group works on the design, analysis and application of algorithms for multi-objective optimization and reinforcement learning. We are based at the Department of Computer Science, IIMAS-UNAM. The group currently supervises 13 students across BSc, MSc, and PhD levels, and is funded by PAPIIT and Google.
The group has open positions at all levels: BSc, MSc, PhD, and postdoctoral. Postdoctoral researchers are especially welcome. Write to carlos.hernandez at iimas.unam.mx if you are interested in joining, and include a brief description of your background and the topic that interests you. Current topics are listed here.
Current Students
The group currently has 6 PhD, 4 MSc, and 3 BSc students. Entries list the thesis topic and any co-advisors.
PhD students
- Rodrigo F. Velázquez Cruz. Robust neural architecture search for multi-objective problems.
- José Olivas Díaz. Multi-agent multi-objective reinforcement learning via evolutionary algorithms. Co-advised with Sebastian Rojas Gonzalez.
- Iván Alcalá Paz. Kolmogorov-Arnold networks for differential equations. Co-advised with Leonid Serkin.
- Daniel Alonso Bastos. Policy landscape modelling and navigation in reinforcement learning via graph neural network surrogate models.
- Ricardo D. Fernández Noguez. Preference-based multi-objective reinforcement learning. Co-advised with Gibran Fuentes.
- José A. Alonso González. Constrained multi-objective reinforcement learning. Co-advised with Paul Erick Méndez Monroy.
MSc students
- Pablo Uriel Benítez Ramírez. Multi-objective reinforcement learning based on Pareto Tracer for multimodal traffic management. Co-advised with Oliver Schütze.
- Fernando R. Valenzuela G. de León. AI assistant for dance choreography creation. Co-advised with Wendy Aguilar.
- Luz Itzel Valdeolivar Hernández. Hyperparameter tuning for the superiorization method via exploratory landscape analysis. Co-advised with Edgar Garduño.
- Baruch Mejía. Speech enhancement through multi-objective optimization in a contextual acoustic representation space. Co-advised with Caleb Rascón.
BSc students
- Alexandra Jiménez. Archivers for MORL: policy and objective spaces.
- Emma Jiménez. SPO+ for stochastic inventory management.
- Néstor Hernández. MORL benchmark with adjustable front geometries.
Graduated Students
Former members include a postdoctoral researcher and MSc and BSc graduates. Graduate entries link to the thesis in the UNAM thesis repository when one exists, and list the graduation date.
Postdoctoral researchers
- Gerardo Altamirano Gómez. Evolutionary design of deep invariance learning architectures for object recognition. 2024–2025.
MSc
- Teresa Becerril Torres. Particle swarm optimization for multi-objective reinforcement learning. August 2026. Thesis
- José A. Alonso González. Multi-objective optimization for water distribution network operation. July 2026. Co-advised with Cristina Verde. Thesis
- Alberto M. Millán Prado. Uncertainty quantification of the hypervolume in multi-objective reinforcement learning problems. February 2026. Thesis
- María Carmen Aguirre Delgado. When does the weighted sum method work well in multi-task learning? October 2025. Co-advised with Gibran Fuentes. Thesis
- José Olivas Díaz. Evaluation of multi-objective multi-agent reinforcement learning algorithms via weighted sum. August 2025. Thesis
- Sofía Borrel Miller. R2-based multi-objective reinforcement learning. June 2025. Thesis
- Rodrigo F. Velázquez Cruz. Cooperative multi-indicator ant colony optimization for multi-objective vehicle routing under uncertainty. December 2024. Thesis
- Víctor M. Sánchez Sánchez. Effect of temporal heterogeneity on selection pressure of evolutionary algorithms. November 2024. Co-advised with Carlos Gershenson. Thesis
- Juan A. López Rivera. Parameter optimization in weighted entropic associative memory systems. February 2024. Co-advised with Luis Pineda. Thesis
BSc
- Fernando Avitúa Varela. Objective reduction in multi-objective problems using quality indicators. November 2024. Thesis