I build AI that makes people's workdays easier and their personal lives more creative.

Currently, I drive agent post-training efforts for Microsoft Copilot: post-training OpenAI models to synergize better with Microsoft's tools, applications, and ecosystem, with a focus on enterprise and workplace scenarios.

Previously, I drove innovation at Samsung Research, prototyping advanced AI features for the next generation of smartphones, spanning everything from core productivity to digital entertainment.

I completed my PhD at KU Leuven in Belgium under Prof. Matthew Blaschko, contributing to many domains in AI, including image generation models, large language models, distributed learning and privacy-preserving machine learning. Before that, I earned my Master's degree from the Karlsruhe Institute of Technology in Germany, using AI to solve control and perception tasks of autonomous driving.

What I work on

Enterprise users ask, and the agent answers by grounding on workplace context (people, content, goals) and acting across Microsoft’s tools and apps. Post-training, guided by user feedback, is my focus.

News

May 17, 2026Our paper GraTAG: Production AI Search via Graph-Based Query Decomposition and Triplet Aligned Generation with Rich Multimodal Representations has been accepted to the KDD 2026 Applied Data Science (ADS) Track.
Apr 4, 2026Our paper Decoding Text Spans for Efficient and Accurate Named-Entity Recognition has been accepted to ACL 2026 Industry Track as an oral presentation.
Sep 14, 2025I am honored to serve as an Area Chair for CVPR 2026. I look forward to contributing to the community and supporting the review process in this role.
Sep 5, 2025Our paper Guided Model Merging for Hybrid Data Learning: Leveraging Centralized Data to Refine Decentralized Models has been accepted at WACV 2026 (Round 1, accceptance rate 6.3%).

Selected publications

All publications →