Marcos M. Raimundo

Professor of Machine Learning and Optimization

Institute of Computing - University of Campinas

Marcos M. Raimundo is an Assistant Professor at University of Campinas (UNICAMP), in the Institute of Computing (IC). He is also a faculty member of the REasoning for COmplex Data laboratory (Recod.ai). His research interests include Machine Learning, Multi-objective Optimization, Ethical AI, Mathematical Programming.

Teaching

SEE ALL →

Projects

Multi-Objective Dynamics of Learning

2026 – ongoing
Multi-Objective Optimization
Deep Learning
Representation Learning
Learning Dynamics
Pareto Sensitivity
Optimization Algorithms

A research line that studies learning as an inherently multi-objective process, seeking to understand how objectives compete and cooperate while a representation is being formed, and how to steer training so that the learned space improves all objectives rather than trading one for another.

Mechanistic Interpretability and Latent Controllability in Large Language Models

2026 – ongoing
Mechanistic Interpretability
Representation Engineering
Large Language Models
Activation Steering
Latent Geometry
AI Safety
Fairness

Research on mechanistic interpretability, representation engineering (RepE), and attention steering in foundation models — investigating internal activation geometry to detect hallucinations, prevent scope drift, mitigate demographic bias, and enforce safe behavioral alignment without full-model retraining.

Long-Term Impacts of Machine Learning-Supported Decisions

2026 – ongoing
Responsible AI
Long-Term Fairness
Sequential Decision-Making
Multi-Objective Optimization
Offline Reinforcement Learning
Contextual Bandits
Performative Prediction

A two-stage sequential decision-making framework combining offline reinforcement learning, contextual bandits, and multi-objective optimization to eliminate harmful feedback loops, mitigate selective labels (reject inference), and ensure long-term fairness and policy flexibility.

No matching items

SEE ALL →

Latest Publications

SEE ALL PUBLICATIONS →

Meet the team

A growing group of students and collaborators working on machine learning, optimization, and fairness.

Meet the team →