cv
Basics
Name | Bálint Gyevnár |
Label | PhD Candidate |
balint.gyevnar@ed.ac.uk | |
Url | https://gbalint.me/ |
Summary | A UK-based researcher of trustworthy explainable autonomous agency in multi-agent systems for achieving safer AI, with applications to autonomous vehicles. |
Projects
- 2025.01 - Present
Combining Multi-Step LLM Reasoning with World Simulators for Generating Complex Explanations
- Development of multi-step reasoning framework for complex explanation generation.
- Integration of LLM inference with world simulators in a RAG approach.
- Evaluation with a wide range of models (Llama, Qwen, Phi, GPT, etc.) and humans participants for autonomous driving.
- 2021.09 - 2024.10
Causal Explanations for Sequential Decision-Making in Multi-Agent Systems
- CEMA: Combining counterfactual causation with RL-based planning to create causally-grounded explanations in naturual language
- Two large human subjects studies to elicit and evaluate naturally occuring and automatically generated explanations
- HEADD: The Human Explanations for Autonomous Driving Decisions dataset
- 2024.07 - Present
Bridging Shared Research Challenges Amid Responsible AI Wars
- Curation of corpus of 3K+ papers on AI safety and AI ethics
- Data analysis and visualization techniques to identify overlapping and different topics in the literature
- Advocating for an epistemically inclusive approach to AI safety that considers long standing safe ML research and AI ethics
- 2020.05 - 2022.10
Interpretable and Verifiable Goal-Based Prediction and Planning for Autonomous Driving
- IGP2: Implementing rational inverse planning and Monte Carlo Tree Search for interpretable goal-based prediction and planning in autonomous vehicles
- GRIT: Training and evaluating decision tree-based verifiable goal recognition models for autonomous driving
Education
-
2021.09 - 2025.12 Edinburgh, Scotland
-
2018.08 - 2019.06 Singapore
-
2016.09 - 2021.05 Edinburgh, Scotland
Work
-
2025.09 - Present Postdoctoral Research Associate
Carnegie Mellon University
Safeguarding scientific integrity in the age of AI co-scientists: how they can amplify existing biases, create epistemic blind spots, and potentially homogenise research approaches across disciplines.
-
2023.07 - 2024.12 Research Assistant
University of Edinburgh
Researching the intersection of AI safety and AI ethics through content analysis methods. Assistant to Dr. Atoosa Kasirzadeh of Carnegie Mellon University.
- Large scale quantitative literature analysis with unsupervised natural language processing tools.
- Curation, topic coding, and qualitative analysis of large corpora of papers.
-
2020.09 - 2025.09 Teaching Assistant
University of Edinburgh
Teaching assistant helping with the delivery and teaching of university courses.
- Assistant supervisor for two master's students.
- Online tutorial sessions to ~12 students for introductory machine learning course.
- Coursework and exam marker for courses in the School of Informatics, including Doing Research in NLP, Reinforcement Learning, Computer Systems, and Machine Learning.
-
2020.05 - 2020.10 Research Intern
FiveAI
Development and evaluation of novel planning and prediction algorithm for autonomous vehicles.
- Developed and evaluated IGP2, a goal-based interpretable prediction and planning system for autonomous vehicles with intuitive explanations.
- Publication at International Conference on Robotics and Automation (ICRA), 2021.
Volunteer
-
2022.09 - 2025.06 Edinburgh, Scotland
Vice President
Edinburgh University Volleyball Club
Vice president of EUVC responsible for the execution of the club's volleyball programme to more than 200 members.
- Responsible for public outreach to and networking with alumni members and organizing a two-day event series.
- Large-scale event organization, public speaking, timetabling, and human resource management of 8 teams, 10 coaches, and 220+ members.
- Managing a cash flow of approximately £70k, setting up an annual budget, and managing thousands of transactions.
Awards
- 2024.06.09
Colours Award
Edinburgh University Sports Union
Colours reward those individuals have given time and effort above and beyond the call of duty to their chosen sport or Club. University Sport could not operate without these volunteers organising and co-ordinating Clubs and the Colours award recognises this endeavour.
- 2023.08.01
AI100 Early Career Essay Competition
AI100 Committee at Stanford University
Researchers from 18 countries answered the call, offering intriguing perspectives on AI and its impacts on society. In addition to the winner, AI100 selected a collection of five essays that thoughtfully consider AI at the intersection of morality, regulation, love, labor, and religion. Balint's essay was selected as one of the five finalists, titled 'Love, Sex, and AI'.
- 2022.07.01
Trustworthy Autonomous Systems Early Career Research Award, Knowledge Transfer Track
United Kingdom Research and Innovation (UKRI)
The inaugural TAS Early Career Researcher (ECR) Awards were initiated to celebrate outstanding contributions made by PhD students and postdoctoral researchers to any area of Trustworthy Autonomous Systems research in the last three years. Balint was awarded £4000 by the UKRI TAS Hub to achieve his vision for more trustworthy autonomous systems (TAS) through explainability and conversations.
- 2021.06.01
"Shape the Future of ITS" Competition
IEEE Intelligent Transportation Systems Society (ITSS)
In 2021, the Intelligent Transportation Systems Society (ITSS) organized a competition on the topic “Shape the Future of ITS” by asking participants to present a futuristic vision on transportation systems, the way they will operate, and the product and services they will provide. Bálint Gyevnár's vision was selected as a 3rd place winner, titled 'Cars that Explain: Building Trust in Autonomous Vehicles through Explanations and Conversations'.
Publications
-
2025.05.25 Integrating Counterfactual Simulations with Language Models for Explaining Multi-Agent Behaviour
Under review
Bálint Gyevnár and Christopher G. Lucas and Stefano V. Albrecht and Shay B. Cohen
-
2025.02.25 -
2025.02.03 Objective Metrics for Human-Subjects Evaluation in Explainable Reinforcement Learning
Multi-Disciplinary Conference on Reinforcement Learning and Decision Making, RLDM 2025
Bálint Gyevnár and Mark Towers
-
2024.12.01 People Attribute Purpose to Autonomous Vehicles When Explaining Their Behavior: Insights from Cognitive Science for Explainable AI
ACM CHI conference on Human Factors in Computing Systems
Bálint Gyevnár and Stephanie Droop and Tadeg Quillien and Shay B. Cohen and Neil R. Bramley and Christopher G. Lucas and Stefano V. Albrecht
-
2024.12.01 Explainable AI for Safe and Trustworthy Autonomous Driving: A Systematic Review
IEEE Transactions on Intelligent Transportation Systems
Anton Kuznietsov* and Bálint Gyevnár* and Cheng Wang and Steven Peters and Stefano V. Albrecht
-
2024.05.01 Causal Explanations for Sequential Decision-Making in Multi-Agent Systems
23rd International Conference on Autonomous Agents and Multiagent Systems, AAMAS 2024
Bálint Gyevnár and Cheng Wang and Christopher G. Lucas and Shay B. Cohen and Stefano V. Albrecht
-
2024.03.01 Towards Trustworthy Autonomous Systems via Conversations and Explanations
38th AAAI Conference on Artificial Intelligence, AAAI 2024
Bálint Gyevnár
-
2023.05.01 Bridging the Transparency Gap: What Can Explainable AI Learn From the AI Act?
26th European Conference on Artificial Intelligence, ECAI 2023
Bálint Gyevnár and Nick Ferguson and Burkhard Schafer
-
2022.05.01 A Human-Centric Method for Generating Causal Explanations in Natural Language for Autonomous Vehicle Motion Planning
IJCAI 2022 Workshop on Artificial Intelligence for Autonomous Driving, AI4AD 2022
Bálint Gyevnár and Massimiliano Tamborski and Cheng Wang and Christopher G. Lucas and Shay B. Cohen and Stefano V. Albrecht
-
2021.05.01 Interpretable Goal-based Prediction and Planning for Autonomous Driving
IEEE International Conference on Robotics and Automation, ICRA 2021
Stefano V. Albrecht and Cillian Brewitt and John Wilhelm and Bálint Gyevnár and Francisco Eiras and Mihai Dobre and Subramanian Ramamoorthy
-
2021.05.01 GRIT: Fast, Interpretable, and Verifiable Goal Recognition with Learned Decision Trees for Autonomous Driving
IEEE/RSJ International Conference on Intelligent Robots and Systems, IROS 2021
Cillian Brewitt and Bálint Gyevnár and Samuel Garcin and Stefano V. Albrecht
Skills
Data Analysis | |
Human Subjects Studies | |
Text Analysis | |
Unsupervised Topic Modelling | |
Mixed Effects Modelling | |
Statistical Hypothesis Testing | |
Data Visualization |
Programming | |
Python (PyTorch, Transformers, vLLM, Pandas, Matplotlib, uv, etc.) | |
R (dplyr, ggplot2, rlmer, brms, etc.) | |
C# | |
C++ |
Artificial Intelligence | |
Natural Language Processing | |
Inference with LLMs (Llama, Qwen, Phi, GPT, etc.) | |
Reinforcement Learning (MCTS, PPO, DQN, etc.) | |
Explainable AI (SHAP, LIME, etc.) | |
Autonomous Vehicles |
Soft Skills | |
Responsible Leadership | |
Event Organization | |
Public Speaking | |
Presentation Skills |
Languages
Hungarian | |
Native speaker |
English | |
Fluent |
German | |
Fluent |
Japanese | |
Advanced |
Chinese | |
Beginner |
Polish | |
Beginner |
Interests
Explainable AI (XAI) | |
Classical XAI | |
Human-Centered XAI | |
Explainable Reinforcement Learning | |
Human-Computer Interaction |
Deep Learning | |
Large Language Models | |
Grounding LLMs | |
Human-LLM Interaction | |
In-Context Causal Learning |
Robotics | |
Reinforecement Learning | |
Autonomous Vehicles | |
Multi-Agent Systems |
AI Safety | |
Epistemic Foundations of AI Safety | |
AI Safety and Ethics | |
Agentic Systems |
References
On Request | |
Please get in touch with me for references. |