Maëlic Neau

About Me

Computer Vision & Machine Learning Research Scientist

  • Age:
  • Degree: PhD in Computer Science
  • Current: Postdoctoral Fellow
  • Phone: +46 (0)7 36 18 46 94
  • Email: maelicneau@gmail.com
  • City: Umeå, Sweden

I am a Computer Vision and Machine Learning Research Scientist, currently a Postdoctoral Fellow at Umeå University, Sweden (since May 2025), working with Assoc. Prof. Zoe Falomir in the UMU Spatial Lab. I hold a joint PhD (cotutelle) from ENIB, France and Flinders University, Australia (2025), with 5+ years of hands-on experience building real-time perception systems using object detection, Vision-Language Models, and autonomous robots with PyTorch, HuggingFace, ROS, etc. I am the author of REACT (Oral at BMVC 2025) and SGG-Benchmark, the first open-source framework for real-time Scene Graph Generation. I am a 2× World Champion of the RoboCup@Home competition (2022 & 2023) with the RoboBreizh team.

I am open to Postdoctoral fellow, Research Scientist and ML/CV Engineer roles across Europe. Feel free to reach out!



Latest News

Achievements

Awards

  • Higher Degree by Research (HDR) Leadership and Scholarly Excellence Award - Flinders University, 2023

Robotics Competitions

Research

Projects


  • All
  • Current
  • Past

GraSP-VLA

Graph-based Symbolic Action Representation for Long-Horizon Planning with VLA Policies

REACT

Real-time Efficiency and Accuracy Compromise for Tradeoffs in Scene Graph Generation

PhD Thesis

Scene Graph Generation and Commonsense Reasoning for Service Robots

ROBOBREIZH

French-Australian Team for the RoboCup@Home Competition

Master Thesis

Grasping Solutions for Domestic Service Robots

Social Dialogue

Commonsense Reasoning and Natural Language Processing

Students Supervision


  • Nuria Millet Research Internship, Umeå University.  2025
  • Alistair MacVicar Visual Question-Answering from Scene Graphs.  2024
  • Nilesh Ramgolan Real-time object detection in the RoboCup@Home competition: the few-shot learning perspective.  2023
  • Sinuo Wang RoboNLU: Advancing Command Understanding with a Novel Lightweight BERT-based Approach for Service Robotics.  2023
  • Thomas Ung Development and integration of onboard ROS modules for an autonomous agent participating in the RoboCup@Home.  2022
  • Valentin Lopez & Trajano Mena Speech-To-Text on the edge: benchmarking solutions for the Pepper robot.   2022

Scientific Publications

2026

2025

2024

2023

2022

Resume

Download: CV (PDF)

Summary

Maëlic Neau

Computer Vision & ML Research Scientist with a joint PhD and 5+ years building real-time perception systems, Vision-Language Models, and autonomous robots. Research experience across France, Australia, Japan, and Sweden. Open to industry roles.

  • Umeå, Sweden
  • +46 (0)7 36 18 46 94
  • maelicneau@gmail.com

Education

PhD in Computer Science

October 2021 - March 2025

ENIB, Brest - France / Flinders University, Adelaide - Australia

Topic: "Real-Time And Efficient Scene Graph Generation for Real-World Applications: An End-to-End Investigation"

Supervisors: Cédric Buche (CNRS / ENIB), Paulo E. Santos (Flinders University), Anne-Gwenn Bosser (ENIB) and Karl Sammut (Flinders University)

Master of Computer Science

2019 - 2021

Université de Bretagne Occidentale, Brest - France / Umeå University, Umeå - Sweden

Artificial Intelligence and Robotics

Bachelor of Computer Science

2018 - 2019

Université de Bretagne Occidentale, Brest - France

2 years degree in Computer Science

2016 - 2018

IUT de Lannion, Lannion - France

Professional Experience

Postdoctoral Fellow

May 2025 - Current

Computing Science Department, Umeå University, Sweden

  • Spatially-Aware Vision-Language Action Models for Robotic Manipulation
  • Supervisor: Assoc. Pr. Zoe Falomir

Research Intern

October 2024 - March 2025

National Institute of Informatics, Tokyo, Japan

  • Toward Open-Vocabulary Scene Graph Generation with Vision-Language Models
  • Supervisor: Pr. Akihiro Sugimoto

Casual Academic

February - June 2023

Flinders University, South Australia

  • Tutoring for lab session
  • Course: COMP8802 Fundamentals of Computational Intelligence

Research Intern

February - August 2021

Lab-STICC / ENIB - Plouzané, France

  • Objects Recognition and Manipulation with Toyota HSR robot
  • Third place at the 2021 RoboCup@Home Competition
  • Supervisor: Pr. Cédric Buche

Research Intern

April - August 2020

Lab-STICC / ENIB - Plouzané, France

  • Simultaneous Localization And Mapping (SLAM) and Social Dialogue (NLP / Commonsense Reasoning) with ROS for the Pepper robot.
  • Best Performance Award at the 2020 RoboCup@Home Education Challenge.
  • Supervisor: Pr. Cédric Buche

Research Intern

May - July 2018

Northern Kentucky University - Highland Heights, USA

  • Artificial Intelligence applied to Software Engineering
  • Supervisor: Pr. Richard Fox

Contact

LinkedIn:

Maëlic Neau

Email:

maelic.neau@umu.se

Phone:

+46 (0)7 36 18 46 94

Location:

Mit-huset, Campustorget 5, 901 87, Umeå, Sweden