Rajmund Nagy

PhD student at KTH Royal Institute of Technology, Sweden

prof_pic.jpg

I am a first-year PhD student at KTH Royal Institute of Technology, advised by Gustav Eje Henter.

My research is focused on deep generative models such as GANs, normalising flows and denoising diffusion models. I am currently working on developing new deep learning models to solve animation problems, such as humanoid motion synthesis. Previously, I worked on speech-driven gesture generation.

As a Master’s student in machine learning, I completed three internships at KTH in the Robotics, Perception, Learning and Speech, Music, Hearing departments. Before that, I was a C++ software engineer at evosoft Hungary. I obtained my Bachelor’s degree in Computer Science from Eötvös Loránd University, Budapest, with a specialisation in mathematical modelling.

Publications

  1. AAMAS ’22
    Multimodal analysis of the predictability of hand-gesture properties
    Taras Kucherenko,  Rajmund Nagy, Michael Neff, Hedvig Kjellström, and Gustav Eje Henter
    In Proceedings of the 21st International Conference on Autonomous Agents and Multiagent Systems 2022
  2. IVA ’21
    Speech2Properties2Gestures: Gesture-Property Prediction as a Tool for Generating Representational Gestures from Speech
    Taras Kucherenko,  Rajmund Nagy, Patrik Jonell, Michael Neff, Hedvig Kjellström, and Gustav Eje Henter
    In Proceedings of the 21th ACM International Conference on Intelligent Virtual Agents 2021
  3. AAMAS ’21
    A Framework for Integrating Gesture Generation Models into Interactive Conversational Agents
    Rajmund Nagy*, Taras Kucherenko*, Birger Moell, André Pereira, Hedvig Kjellström, and Ulysses Bernardet
    In Proceedings of the 20th International Conference on Autonomous Agents and MultiAgent Systems 2021