Nikolaos Tsagkas

Postdoctoral Researcher at the University of Amsterdam
PhD Candidate at the University of Edinburgh

Nikolaos Tsagkas

I am a Postdoctoral Researcher at the University of Amsterdam, working with Prof. Efstratios Gavves on Physical AI. I am currently completing my PhD at the School of Informatics, University of Edinburgh, with my thesis defence on leveraging pre-trained visual representations for robot learning coming up soon. My PhD was funded by the Edinburgh Centre for Robotics, and I was privileged to be advised by Prof. Chris Xiaoxuan Lu (UCL) and Prof. Oisin Mac Aodha (University of Edinburgh). Along the way, I was fortunate to collaborate with Alexandros Kouris from the Samsung AI Center Cambridge, where I also interned in late 2025, working on compositional generalization in Vision-Language-Action models.

Before my PhD, I completed an MSc in Artificial Intelligence with distinction at the University of Edinburgh, where I worked on Generative Capsule Models under the supervision of Prof. Chris Williams. I also hold a BSc and MSc in Electrical and Computer Engineering from the University of Patras, Greece.

  1. w2vla_thumbnail_smaller.gif
    Decoupling the Declarative from the Procedural in Vision-Language-Action Models
    Nikolaos Tsagkas, Andreas Sochopoulos, Chris Xiaoxuan Lu, Oisin Mac Aodha, and Alexandros Kouris
    In ArXiv Preprint , 2026
    arXiv HTML New!
  2. Optimal Transport Q-Learning for Flow Policy Steering and Acceleration
    Optimal Transport Q-Learning for Flow Policy Steering and Acceleration
    Andreas Sochopoulos , Esmeralda S. Whitammer , Nikolaos Tsagkas , JoΓ£o Moura , Michael Gienger , and Sethu Vijayakumar
    In Conference on Robot Learning (CoRL), Austin, Texas, USA , 2026
    arXiv HTML
  3. afa_thumbnail_smaller.gif
    Attentive Feature Aggregation, Or: How Policies Learn to Stop Worrying about Robustness and Attend to Task-Relevant Visual Cues
    Nikolaos Tsagkas , Andreas Sochopoulos , Duolikun Danier , Sethu Vijayakumar , Alexandros Kouris , Oisin Mac Aodha , and Chris Xiaoxuan Lu
    In IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), Pittsburgh, USA, 2026
    arXiv HTML Code
  4. temporal_thumbnail.gif
    The Temporal Trap: Entanglement in Pre-Trained Visual Representations for Visuomotor Policy Learning
    Nikolaos Tsagkas , Andreas Sochopoulos , Duolikun Danier , Chris Xiaoxuan Lu , and Oisin Mac Aodha
    In International Conference on Robotics and Automation (ICRA), Vienna, Austria , 2026
    arXiv HTML Code
  5. zipper_16fps_240.gif
    Fast Flow-based Visuomotor Policies via Conditional Optimal Transport Couplings
    Andreas Sochopoulos , Nikolay Malkin , Nikolaos Tsagkas , JoΓ£o Moura , Michael Gienger , and Sethu Vijayakumar
    In Conference on Robot Learning (CoRL), Seoul, South Korea , 2025
    arXiv HTML Code
  6. pvrobo_thumbnail_distractors_short.gif
    When Pre-trained Visual Representations Fall Short: Limitations in Visuo-Motor Robot Learning
    Nikolaos Tsagkas , Andreas Sochopoulos , Duolikun Danier , Sethu Vijayakumar , Chris Xiaoxuan Lu , and Oisin Mac Aodha
    In EAI@Computer Vision and Pattern Recognition (CVPR) , 2025
    HTML Code Spotlight Talk
  7. affordance_thumbnail_150.gif
    Learning Precise Affordances from Egocentric Videos for Robotic Manipulation
    Gen Li , Nikolaos Tsagkas , Jifei Song , Ruaridh Mon-Williams , Sethu Vijayakumar , Kun Shao , and Laura Sevilla-Lara
    In IEEE/CVF International Conference on Computer Vision (ICCV), Hawaii, USA , 2025
    arXiv HTML
  8. c2g_thumbnail_150.gif
    Click to Grasp: Zero-Shot Precise Manipulation via Visual Diffusion Descriptors
    Nikolaos Tsagkas , Jack Rome , Subramanian Ramamoorthy , Oisin Mac Aodha , and Chris Xiaoxuan Lu
    In IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), Abu Dhabi, UAE , 2024
    arXiv HTML Code Oral Pitch
  9. vl-fields_thumbnail.gif
    VL-Fields: Towards Language-Grounded Neural Implicit Spatial Representations
    Nikolaos Tsagkas , Oisin Mac Aodha , and Chris Xiaoxuan Lu
    In International Conference on Robotics and Automation (ICRA) Workshops, London, UK , 2023
    arXiv HTML Spotlight Talk
  10. ecgm_thumbnail.gif
    Inference and Learning for Generative Capsule Models
    Alfredo Nazabal* , Nikolaos Tsagkas* , and Christopher K. I. Williams
    Neural Computation, 2023
    arXiv Code
  11. semg_thumbnail.gif
    On the Use of Deeper CNNs in Hand Gesture Recognition Based on sEMG Signals
    Nikolaos Tsagkas , Panagiotis Tsinganos , and Athanassios Skodras
    In 10th International Conference on Information, Intelligence, Systems and Applications (IISA), Patras, Greece , 2019
    PDF Code Oral