Dr Fares Abawi

Hamburg

Hello! I’m Fares Abawi (فارس عبوي). I studied electronic and communication engineering before specializing in intelligent adaptive systems, where I discovered my passion for machine learning and AI. After working as a sensor fusion and algorithm engineer, I returned to academia for doctoral research in robotics and AI, focusing on modeling human attention in social settings through deep learning and exploring how humanoid robots can control their gaze by mimicking human attention patterns (thesis).

I actively maintain several open-source projects:

TeXlyre: A local-first LaTeX and Typst web editor with collaborative editing and offline support (resources at texlyre.org)
Wrapyfi: A framework for integrating robots and devices across multiple middleware including ROS, ROS 2, YARP, ZeroMQ, MQTT, and more (resources at modular.ml)
Llama with Wrapyfi: Distributed deployment of Llama LLM using the Wrapyfi framework
ImageBind-LoRA: Parameter-efficient fine-tuning for Meta’s ImageBind multimodal model

news

May 21, 2025	Presenting at ICRA 2025 (Atlanta, GA, USA) tomorrow (22.05) @ 8:50 AM ET in Room A307 at the Georgia World Congress Center, Atlanta, GA.
Jan 21, 2025	Our paper was accepted at the ICRA 2025 (Atlanta, GA, USA) conference. See you in Atlanta!
Dec 16, 2024	On the 16th of December, 2024 @ 12:00 PM, I successfully defended my doctoral dissertation, fulfilling the requirements of the Dr. rer. nat degree [dissertation]. Review committee: Prof. Stefan Wermter (advisor, reviewer), Prof. Frank Steinicke (deputy chair, reviewer), and Prof. Timo Gerkmann (chair)
Aug 26, 2024	We won the Best Paper Award at RO-MAN 2024 InterAI (Los Angeles, CA, USA) sponsored by Duckietown. “HRI-Free Evaluation of Embodied Social Attention Models Through Cognitive Robotic Simulation” [paper] (password: InterAI_HRI24)
Jan 11, 2024	Our human participant study based on the Wrapyfi [code][paper] framework was accepted at the HRI 2024 (Boulder, CO, USA) conference Late-Breaking Results (LBR)
Dec 16, 2023	Wrapyfi [code][paper] is now available on PyPi https://pypi.org/project/wrapyfi and the documentation on readthedocs https://wrapyfi.readthedocs.io
Dec 1, 2023	The Wrapyfi [code][paper] code contribution was accepted at the HRI 2024 (Boulder, CO, USA) conference and will appear as an SC alongside the full-paper proceedings in March 2024

selected publications

Unified Dynamic Scanpath Predictors Outperform Individually Trained Neural Models

Fares Abawi, Di Fu, and Stefan Wermter

CoRR, 2025

arXiv Bib PDF Code

@article{abawi2025usp,
  title = {{Unified Dynamic Scanpath Predictors Outperform Individually Trained Neural Models}},
  author = {Abawi, Fares and Fu, Di and Wermter, Stefan},
  journal = {CoRR},
  year = {2025},
  doi = {10.48550/arXiv.2405.02929},
}

HRI-Free: Cognitive Robotic Simulation for Evaluating Embodied Social Attention Models

Fares Abawi, and Di Fu

In Proceedings of the IEEE International Conference on Robotics and Automation (ICRA), 2025

Bib PDF Video Poster

@inproceedings{abawi2025hrifree,
  title = {{HRI-Free: Cognitive Robotic Simulation for Evaluating Embodied Social Attention Models}},
  author = {Abawi, Fares and Fu, Di},
  booktitle = {Proceedings of the IEEE International Conference on Robotics and Automation (ICRA)},
  pages = {11249--11255},
  year = {2025},
  organization = {IEEE},
  doi = {10.1109/ICRA55743.2025.11127539},
  final_pdf = {https://1drv.ms/b/c/68347683875c28db/EaH4ETicMrRPmWQI8gSyNLIBwVegv4zBQ-aWMvKWH_Vf2g?e=fl6L8i},
}

Wrapyfi: A Python Wrapper for Integrating Robots, Sensors, and Applications across Multiple Middleware

Fares Abawi, Philipp Allgeuer, Di Fu, and 1 more author

In Proceedings of the ACM/IEEE International Conference on Human-Robot Interaction (HRI ’24), 2024

arXiv Bib HTML PDF Code Poster

@inproceedings{abawi2024wrapyfi,
  title = {{Wrapyfi: A Python Wrapper for Integrating Robots, Sensors, and Applications across Multiple Middleware}},
  author = {Abawi, Fares and Allgeuer, Philipp and Fu, Di and Wermter, Stefan},
  booktitle = {Proceedings of the ACM/IEEE International Conference on Human-Robot Interaction (HRI '24)},
  pages = {860--864},
  year = {2024},
  organization = {ACM},
  isbn = {979-8-4007-0322-5/24/03},
  doi = {10.1145/3610977.3637471},
}

GASP: Gated Attention for Saliency Prediction

Fares Abawi, Tom Weber, and Stefan Wermter

In Proceedings of the International Joint Conference on Artificial Intelligence (IJCAI-21), 2021

arXiv Bib HTML PDF Video Code Poster

@inproceedings{abawi2021gasp,
  title = {{GASP: Gated Attention for Saliency Prediction}},
  author = {Abawi, Fares and Weber, Tom and Wermter, Stefan},
  booktitle = {Proceedings of the International Joint Conference on Artificial Intelligence (IJCAI-21)},
  pages = {584--591},
  year = {2021},
  organization = {IJCAI Organization},
  doi = {10.24963/ijcai.2021/81},
}