01
Agentic & Multimodal AI
AI systems that connect perception, reasoning, memory, and tool use across language, vision, and structured data.
Read the research directionAI · Agency · Mobility
I build AI systems that understand people, place, and motion.
My research explores agentic and multimodal AI for intelligent mobility, human–vehicle collaboration, and decision-making in the real world.
Postdoctoral Researcher · SnT, University of Luxembourg
Researching the next interaction model between people, AI, and mobility.
Focus Agentic & multimodal AI
Context Intelligent mobility
Approach Research through working systems
Research agenda
Three connected questions.
How can AI perceive richer contexts, reason more deliberately, and collaborate with people where decisions have real consequences?
02
Intelligent & Human-Centered Mobility
Vehicles and transportation systems that understand context, communicate naturally, and work with—not merely around—people.
Read the research direction03
Applied AI Systems
Turning research ideas into working systems for information retrieval, decision support, privacy, and automation.
Read the research directionSelected work
A research trajectory, not just a paper list.
Agentic Vehicles for Human-Centered Mobility: Definition, Prospects, and Synergistic Co-Development with Vehicle Autonomy
arXiv:2507.04996
A framework distinguishing vehicle agency from autonomy and describing how both can co-develop for human-centered mobility.
MILD: Mediator Agent System with Bidirectional Perception and Multi-Layered Alignment for Human-Vehicle Collaboration
arXiv:2605.01507
An agentic mediator that aligns driver needs, vehicle perception, safety rules, and explainable driving strategies.
Driver Identification only using GPS trajectories: A Deep Learning Approach
This is one of my latest works in which I apply deep learning to problem of driver identification using GPS data collected from smartphone.
Systems & experiments
Ideas become clearer when they work.
Selected systems that translate research into usable tools, datasets, and demonstrations.
Project
KITT - A Conversational Voice Assistant for Vehicles
KITT is a conversational voice assistant for vehicles, capable of answering questions related to routing, finding points of interest, and is aware of the local weather and traffic …
ExploreProject
Driver Identification (Fingerprinting)
Machine-learning methods that identify and model drivers from vehicle dynamics and GPS trajectories without intrusive sensors.
ExploreAbout
Research depth, systems perspective.
I am a computer scientist working at the intersection of artificial intelligence and mobility. My current research studies how multimodal models and AI agents can perceive complex environments, reason with tools and external knowledge, and collaborate safely with people.
My work combines research depth with experience building real systems—from driver modeling and connected vehicles to conversational assistants, retrieval systems, and on-device AI.
Writing
Notes from research and building.
Aug 2024
Towards a Conversational LLM-Based Voice Assistant for Transportation Applications
KITT is an in-car assistant capable of verbally communicating with the driver, and by utilizing external APIs, it can answer questions related to routing, finding points of interest, and is …
ExploreOct 2024
Dataset Tracking With DVC: A Practical Guide for MLOps
A comprehensive guide to implementing Data Version Control (DVC) in your machine learning workflow. Learn how to set up DVC with DigitalOcean Spaces, track datasets efficiently, and maintain …
ExploreOct 2024
Solving Memory Issues When Loading Parquet Files into Pandas DataFrames
A practical guide to solving memory optimization issues when working with Parquet files in Pandas. Learn how to handle dictionary columns efficiently, reduce memory consumption from 90GB to …
ExploreCollaborate