cv

Luiz Felipe Vecchietti
Download CV (PDF)

felipe.vecchietti at mpi-sp.org

General Information

I am currently a Postdoctoral Researcher at the Max Planck Institute for Security and Privacy (MPI-SP), Bochum, Germany, with Director Meeyoung Cha.

Research Interests

  • Reinforcement Learning (Credit Assignment, Exploration, Goal-conditioned RL, Continual Learning)
  • Multi-Agent Systems (Collaborative, Collaborative-Competitive)
  • Robotics (Foundation Models, End-to-End Control, Safety and Risks)
  • AI for Science (Generative AI, Protein and Antibody Design, Drug Discovery, Graph Neural Networks, Diffusion Models)

Positions

2024.11–Present — Max Planck Institute for Security and Privacy (MPI-SP), Germany
Postdoctoral Researcher. Advisor: Meeyoung Cha

2021.10–2024.9 — Data Science Group, Institute for Basic Science (IBS), South Korea
Senior Researcher. Advisor: Meeyoung Cha

2021.3–2021.9 — Mechanical Engineering Research Institute, KAIST, South Korea
Postdoctoral Researcher. Advisor: Dongsoo Har

Education

2017–2021 — Korea Advanced Institute of Science and Technology (KAIST)
PhD in Green Transportation. Thesis: Performance Enhancement in Multigoal Reinforcement Learning using Hindsight Experience Replay Advisor: Dongsoo Har

2015–2017 — Federal University of Rio de Janeiro (UFRJ)
Master’s Degree in Electrical Engineering. Dissertation: Comparison between rule-based and data-driven NLP algorithms for Brazilian Portuguese speech synthesis Advisor: Fernando Gil Vianna Resende Junior

2013 — Korea Advanced Institute of Science and Technology (KAIST)
Exchange Student, Electrical Engineering Department

2009–2015 — Federal University of Rio de Janeiro (UFRJ)
Bachelor’s Degree in Electronic and Computer Engineering

Internships

Summer 2013 — Hyundai Motor Company, Namyang R&D Center
Eco Vehicle Control System Development Team

Publications

International Conferences

  1. Exploring LLM Behavior in Relational Moral Dilemmas: Moral Rightness, Predicted Human Behavior, and Model Decisions
    ACL Findings, 2026
  2. Dropouts in Confidence: Moral Uncertainty in Human-LLM Alignment
    Kwon, J., Vecchietti, L. F. et al.
    Proceedings of the AAAI Conference on Artificial Intelligence, AI Alignment Track, 2026
    paper
  3. Robust Optimization in Protein Fitness Landscapes Using Reinforcement Learning in Latent Space
    Vecchietti*, L. F., Lee*, M. et al.
    Proceedings of the International Conference on Machine Learning (ICML), 2024 — Spotlight Poster, co-first authors
    paper code

Journals

  1. Interpretable Machine Learning for Protein Science: Structure, Function, and Interactions
    Vecchietti, L. F. et al.
    ACM Computing Surveys, 2026
    paper
  2. Artificial intelligence-driven computational methods for antibody design and optimization
    Vecchietti, L. F., Wijaya, B. N. et al.
    mAbs, 2025
    paper
  3. Computational Design and Glycoengineering of Interferon-Lambda for Nasal Prophylaxis against Respiratory Viruses
    Yun, J., Yang, S., Kwon, J. H., Vecchietti, L. F., Lee, M. et al.
    Advanced Science, 2025
    paper
  4. Overabundance of abelisaurid teeth in the Açu Formation (Albian-Cenomanian), Potiguar Basin, Northeastern Brazil: morphometric, cladistic and machine learning approaches
    Ribeiro, T. B., Vecchietti, L. F. et al.
    Journal of Vertebrate Paleontology, 2025
    paper
  5. Sensing accident-prone features in urban scenes for proactive driving and accident prevention
    Mishra, S., Rajendran, P. K., Vecchietti, L. F. et al.
    IEEE Transactions on Intelligent Transportation Systems, 2023 — Selected as featured research in KAIST Breakthroughs Magazine 2023
  6. AI World Cup: Robot Soccer-Based Competitions
    Hong, C., Jeong, I., Vecchietti, L. F. et al.
    IEEE Transactions on Games, 2021 — Main simulation environment for the AI World Cup competitions
    paper
  7. Two-stage training algorithm for AI robot soccer
    Kim, T., Vecchietti, L. F. et al.
    PeerJ Computer Science, 2021
    paper
  8. Cooperative decentralized peer-to-peer electricity trading of nanogrid clusters based on predictions of load demand and PV power generation using a gated recurrent unit model
    Lee, S., Jin, H., Vecchietti, L. F. et al.
    IET Renewable Power Generation, 2021
  9. Sampling Rate Decay in Hindsight Experience Replay for Robot Control
    Vecchietti, L. F., Seo, M. et al.
    IEEE Transactions on Cybernetics, 2020
    paper
  10. Batch Prioritization in Multigoal Reinforcement Learning
    Vecchietti, L. F. et al.
    IEEE Access, 2020
    paper
  11. Power Management by LSTM Network for Nanogrids
    Lee, S., Vecchietti, L. F. et al.
    IEEE Access, 2020
  12. Short-term predictive power management of PV-powered nanogrids
    Lee, S., Jin, H., Vecchietti, L. F. et al.
    IEEE Access, 2020
  13. Machine Learning for Advanced Wireless Sensor Networks: A Review
    Kim, T., Vecchietti, L. F. et al.
    IEEE Sensors Journal, 2020
    paper
  14. Pose Estimation Utilizing a Gated Recurrent Unit Network for Visual Localization
    Kim, S., Kim, I., Vecchietti, L. F. et al.
    Applied Sciences, 2020
  15. Rewards Prediction Based Credit Assignment for Reinforcement Learning with Sparse Binary Rewards
    Seo, M., Vecchietti, L. F. et al.
    IEEE Access, 2019 — Selected as featured research in KAIST Breakthroughs Magazine 2020
    paper

Domestic Conferences and Workshops

  1. Longitudinal Identification of Critical Factors in Nurse Turnover for Supporting Workforce Well-Being
    Wijaya, B. N., Vecchietti, L. F. et al.
    Proceedings of HCI Korea, 2026
  2. Exploring persona-dependent LLM alignment for the moral machine experiment
    Kim, J., Kwon, J., Vecchietti, L. F. et al.
    ICLR BiAlign Workshop, 2025
  3. Evaluation of Antibody Structure Reconstruction with an SE(3)-Equivariant Graph Neural Network
    Wijaya, B. N., Vecchietti, L. F. et al.
    Korea Software Congress (KSC), 2023 — Excellence Award
  4. Protein Structure Tokenizer for Efficient Learning
    Jung, H., Vecchietti, L. F. et al.
    Peptalk, 2023
  5. Antibody Sequence Design With Graph-Based Deep Learning Methods
    Hangeldiyev, B., Rzayev, A., Armanuly, A., Jung, H., Vecchietti, L. F. et al.
    Korea Software Congress (KSC), 2022
  6. Protein Sequence Design in a Latent Space via Model-based Reinforcement Learning
    Lee, M., Vecchietti, L. F. et al.
    NeurIPS Machine Learning in Structural Biology (MLSB) Workshop, 2022 — Co-first authors
  7. Structure-based representation for protein functionality prediction using machine learning
    Lee, M., Rzayev, A., Jung, H., Vecchietti, L. F. et al.
    Korea Computer Congress (KCC), 2022 — Excellence Award
  8. RelMobNet: End-to-end relative camera pose estimation using a robust two-stage training
    Rajendran, P. K., Mishra, S., Vecchietti, L. F. et al.
    ECCV IWDSC Workshop, 2022

Preprints

  1. Predicting Individual Life Trajectories: Addressing Uncertainty in Social Employment Transitions
    Vecgaile, L., Spata, A., Vecchietti, L. F., Zagheni, E.
    SocArXiv, 2025

Academic Services

Reviewer — Journals: IEEE Transactions on Cybernetics, IEEE Transactions on Games, IEEE Sensors, Frontiers in Robotics and AI

Program Committee — Conferences: AAAI ICWSM 2022, NeurIPS 2024, ACM WSDM 2025, ICLR 2025, AISTATS 2025, ICML 2025, NeurIPS 2025, AAAI 2026, ICLR 2026, Machine Behavior (Ma+Be) 2026, ICML 2026

Program Committee — Workshops: ICML LatinX 2021, ICLR Reincarnating RL 2023, NeurIPS MLSB 2023, ICML ML4LMS 2024, NeurIPS MLSB 2024, NeurIPS MLSB 2025, ICLR MALGAI 2026

Board Member: Diversity Board Member at the Max Planck Institute for Security and Privacy (MPI-SP)

Invited Talks

[1] From self-organized networks to deep reinforcement learning: perspectives on AI research Center for Neuroscience-inspired AI, KAIST, South Korea, October 2025.

[2] LLMs outside Natural Language Processing applications Ruhr University Bochum (RUB), Germany, July 2025.

[3] Integrating data science and AI methods in multidisciplinary research to make discoveries with social impact WebImmunization Seminar, University of Oslo, Norway, December 2024.

[4] Robust optimization in protein fitness landscapes using reinforcement learning in latent space Cradle Bio, Zurich, Switzerland, November 2024.

[5] Developing and applying deep learning methods for protein design Graduate School of AI, Gwangju Institute of Science and Technology (GIST), Gwangju, South Korea, July 2023.

[6] Developing and applying deep learning methods to facilitate new scientific discoveries Max Planck Institute for Security and Privacy (MPI-SP), Bochum, Germany, May 2023.

[7] Target-conditioned protein and antibody design for drug discovery IBS Winter School on AI-Boosted Basic Science, Institute for Basic Science, Daejeon, South Korea, December 2022. Co-delivered with Prof. Ho Min Kim (KAIST)

[8] Identifying the key actions that lead an agent to accomplish a task in model-based reinforcement learning School of AI Convergence, Chonnam National University, Gwangju, South Korea, November 2021.

[9] Performance enhancement in multigoal model-based deep reinforcement learning Cho Chun Shik Graduate School of Mobility, KAIST, Daejeon, South Korea, October 2021.

[10] Identifying the key actions that lead an agent to accomplish a task in model-based reinforcement learning Data Science Group, Institute for Basic Science, Daejeon, South Korea, April 2021.

Mentored Students

It is a great pleasure to work with very talented and hardworking students.

I am very thankful for the support and trust given from my advisors throughout my career: Prof. Fernando Gil Vianna Resende Junior (MsC), Prof. Dongsoo Har (PhD), and currently Prof. Ho Min Kim and Prof. Meeyoung Cha.

Current

Bryan Nathanael Wijaya (2023–present) — PhD Candidate, MPI-SP.
Topic: Applied AI for Longitudinal Data, Generative AI, AI for Science. Published a first-author paper in mAbs.

Begench Hangeldiyev (2022–present) — MSc Candidate, KAIST.
Topic: Antibody Sequence Design with Graph-Based Methods. Published first paper on antibody design at KSC 2023.

Niklas Koeppe (2025–present) — PhD Candidate, KAIST.
Topic: Continual Learning. Submitted first author paper to ICML 2026.

Alumni

Jiseon Kim (2024–2025) — PhD Candidate, KAIST.
Topic: Human-AI Alignment. Published first-author paper at ACL Findings.

Hyunkyu Jung (2021–2025, now PhD Candidate at KAIST) — PhD Candidate, KAIST.
Topic: Protein-Protein Interactions using Equivariant Point Cloud Transformers. Co-authored two journals and one ICML paper.

Anar Rzayev (2022–2025, now Intern at ISTA) — CS Undergraduate, KAIST.
Topic: Antibody Structure Representation Learning. Co-authored two domestic conferences papers.

Sangmin Lee (2023) — CS Undergraduate, KAIST.
Topic: AI-based methods for thermostable protein design.

Maxim Krassimirov Mintchev (2022, now Research Associate at TU Berlin) — ME MSc Candidate, KIT/KAIST (Double Degree). Topic: Recommendation Systems for Logistics. Successfully defended master’s thesis.

Minji Lee (2022, now PhD Candidate at Columbia University) — CS Undergraduate, KAIST.
Topic: Protein Optimization using Deep RL. First-author paper at ICML 2024 (Spotlight). Papers at KCC and NeurIPS MLSB Workshop 2022.

Lucas Santiago Peixoto (2022) — Computer Engineering Undergraduate, UFRJ.
Topic: Sentence-level Text Analysis using Transformers. Successfully defended undergraduate thesis.

Matheus Tymburiba Elian (2021–2022, now Faculty at UFMG) — Industrial Design PhD Candidate, University of Tsukuba.
Topic: Gender-Ambiguous Voice Agents. Published first-author paper in Estudos em Design 2025.

Kien Hoang (2021–2022, now MsC Candidate at EPFL) — Mathematics Undergraduate, KAIST.
Topic: Graph structure optimization with Deep RL.

Sumit Mishra (2020–2022, now PhD Candidate at KAIST) — Robotics MSc Candidate, KAIST.
Topic: Intelligent Transportation Systems. First-author paper in IEEE Transactions on ITS.

Praveen Kumar Rajendran (2020–2022, now CV Engineer at Neubility) — Future Vehicle MSc Candidate, KAIST.
Topic: Camera Pose Estimation. First-author paper at ECCV IWDSC Workshop 2022.

Taeyoung Kim (2019–2021, now PhD Candidate at KAIST) — Green Transportation MSc Candidate, KAIST.
Topic: Deep RL, Cooperative-Competitive Multi-agent Systems. First-author review paper in IEEE Sensors Journal; first-author paper in PeerJ Computer Science.

Kyujin Choi (2019–2020, now ML Engineer at KT) — Green Transportation MSc Candidate, KAIST.
Topic: Deep RL, Cooperative-Competitive Multi-agent Systems. Co-authored two journal papers.

Minah Seo (2018–2019, now ML Engineer at KT) — Green Transportation MSc Candidate, KAIST.
Topic: Credit Assignment in Deep RL. First-author paper in IEEE Access.