Portrait of Dmytro Kuzmenko

Dmytro Kuzmenko

Senior Research Engineer @ OnlyMonster · PhD Candidate @ NaUKMA · Torino, Italy
Email Scholar GitHub LinkedIn X

I am a research engineer working at the intersection of reinforcement learning, robotics, foundation models, and human-robot interaction, with a focus on building efficient and reliable intelligent systems.

I am a founding AI engineer and senior individual contributor at OnlyMonster, where I work on production LLM systems for real-time assistance, multilingual translation, safety, and AI-driven product features.

I am also pursuing a PhD in Computer Science at NaUKMA. My research focuses on efficient learning for perception, control, and human-robot interaction, with particular interest in data- and compute-efficient methods and the role of trust and safety in deployed systems.

Outside of work, I enjoy playing shogi, collecting vinyl records, and experimenting in the kitchen.

Interests: HRI, embodied AI, efficient RL, multi-task control, world foundation models.

News

Publications

EED Gym thumbnail
When Robots Say No: The Empathic Ethical Disobedience Benchmark
D. Kuzmenko, N. Shvai
ACM/IEEE International Conference on Human-Robot Interaction (HRI), 2026 (accepted)
arXiv Code Website Bib 
@article{kuzmenko2025eedgym,
          title   = {When Robots Say No: The Empathic Ethical Disobedience Benchmark},
          author  = {Kuzmenko, Dmytro and Shvai, Nadiya},
          year    = {2025},
          note    = {Accepted at the ACM/IEEE International Conference on Human-Robot Interaction (HRI 2026). Preprint: arXiv:2512.18474},
          doi     = {10.48550/arXiv.2512.18474},
        }
Energy conservation thumbnail
Energy Conservation for Autonomous Agents Using Reinforcement Learning
V. Beimuk, D. Kuzmenko
NaUKMA Research Papers: Computer Science, 2025
DOI Bib 
@article{beimuk2025energy,
                  title={Energy conservation for autonomous agents using reinforcement learning},
                  author={Beimuk, V. and Kuzmenko, D.},
                  journal={NaUKMA Research Papers. Computer Science},
                  volume={8},
                  pages={68--75},
                  year={2025},
                  doi={10.18523/2617-3808.2025.8.68-75}
                }
MoIRA preprint thumbnail
MoIRA: Modular Instruction Routing Architecture for Multi-Task Robotics
D. Kuzmenko, N. Shvai
Preprint (under review), 2025
arXiv Bib 
@misc{kuzmenko2025moiramodularinstructionrouting,
                      title={MoIRA: Modular Instruction Routing Architecture for Multi-Task Robotics}, 
                      author={Dmytro Kuzmenko and Nadiya Shvai},
                      year={2025},
                      eprint={2507.01843},
                      archivePrefix={arXiv},
                      primaryClass={cs.RO},
                      url={https://arxiv.org/abs/2507.01843}, 
                }
TD-MPC-Opt preprint thumbnail
TD-MPC-Opt — Distillation & Quantization for Efficient Multi-Task Model-Based RL
D. Kuzmenko, N. Shvai
Preprint (under review), 2025
arXiv GitHub Bib 
@misc{kuzmenko2025tdmpcoptdistillingmodelbasedmultitask,
                      title={TD-MPC-Opt: Distilling Model-Based Multi-Task Reinforcement Learning Agents}, 
                      author={Dmytro Kuzmenko and Nadiya Shvai},
                      year={2025},
                      eprint={2507.01823},
                      archivePrefix={arXiv},
                      primaryClass={cs.LG},
                      url={https://arxiv.org/abs/2507.01823}, 
                }
AAMAS 2025 thumbnail
Knowledge Transfer in Model-Based Reinforcement Learning Agents for Efficient Multi-Task Learning
D. Kuzmenko, N. Shvai
International Conference on Autonomous Agents and Multiagent Systems (AAMAS), 2025
ACM DL arXiv Bib 
@inproceedings{10.5555/3709347.3743949,
                  author = {Kuzmenko, Dmytro and Shvai, Nadiya},
                  title = {Knowledge Transfer in Model-Based Reinforcement Learning Agents for Efficient Multi-Task Learning},
                  year = {2025},
                  isbn = {9798400714269},
                  publisher = {International Foundation for Autonomous Agents and Multiagent Systems},
                  address = {Richland, SC},
                  booktitle = {Proceedings of the 24th International Conference on Autonomous Agents and Multiagent Systems},
                  pages = {2597-2599},
                  numpages = {3},
                  keywords = {efficient rl agents, knowledge distillation, model compression, model-based reinforcement learning, multi-task learning},
                  location = {Detroit, MI, USA},
                  series = {AAMAS '25}
                }
ICTERI 2024 thumbnail
Balancing Performance and Efficiency in Zero-Shot Robotic Navigation
D. Kuzmenko, N. Shvai
ICTERI 2024, Communications in Computer and Information Science (Springer), 2025
DOI arXiv Bib 
@incollection{KuzmenkoShvai2025ZeroShotNavigation,
                title     = {Balancing Performance and Efficiency in Zero-Shot Robotic Navigation},
                author    = {Kuzmenko, Dmytro and Shvai, Nadiya},
                booktitle = {Information and Communication Technologies in Education, Research, and Industrial Applications},
                series    = {Communications in Computer and Information Science},
                volume    = {2359},
                pages     = {370--381},
                year      = {2025},
                publisher = {Springer, Cham},
                doi       = {10.1007/978-3-031-81372-6\_28},
                url       = {https://doi.org/10.1007/978-3-031-81372-6_28}
              }
StairNet thumbnail
StairNet: Visual Recognition of Stairs for Human-Robot Locomotion
A. G. Kurbis, D. Kuzmenko, B. Ivanyuk-Skulskiy, A. Mihailidis, B. Laschowski
BioMedical Engineering OnLine, 2024
DOI arXiv Bib 
@article{Kurbis2024StairNet,
                    title   = {StairNet: Visual Recognition of Stairs for Human-Robot Locomotion},
                    author  = {Kurbis, Andrew Garrett and Kuzmenko, Dmytro and Ivanyuk-Skulskiy, Bogdan and Mihailidis, Alex and Laschowski, Brokoslaw},
                    journal = {BioMedical Engineering OnLine},
                    volume  = {23},
                    number  = {20},
                    year    = {2024},
                    doi     = {10.1186/s12938-024-01216-0},
                    url     = {https://doi.org/10.1186/s12938-024-01216-0}
                  }
IROS 2023 thumbnail
Efficient Visual Perception of Human–Robot Walking Environments Using Semi-Supervised Learning
D. Kuzmenko, O. Tsepa, A. G. Kurbis, A. Mihailidis, B. Laschowski
IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), 2023
DOI biorXiv Bib 
@INPROCEEDINGS{10341654,
                  author={Kuzmenko, Dmytro and Tsepa, Oleksii and Kurbis, Andrew Garrett and Mihailidis, Alex and Laschowski, Brokoslaw},
                  booktitle={2023 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)}, 
                  title={Efficient Visual Perception of Human-Robot Walking Environments Using Semi-Supervised Learning}, 
                  year={2023},
                  volume={},
                  number={},
                  pages={6544-6549},
                  keywords={Legged locomotion;Training;Supervised learning;Semisupervised learning;Transformers;Real-time systems;Standards},
                  doi={10.1109/IROS55552.2023.10341654}}

Academic Service

Teaching