Future Thinking
Hello, I’m Maxence.
I am a PhD candidate at King’s College London, working with the SIE-CAI4CAI Lab since 2021 under the supervision of Prof. Sebastien Ourselin. My goal is to develop superintelligent and autonomous machines that make the world a better place.
Prior to my doctoral studies, I earned an MSc in Machine Learning, Computer Vision, and Robotics from the University of Surrey, where I conducted research at the CVSSP Lab under the guidance of Prof. Kevin Wells. My work is currently supported by UKRI funding.
Research Interests
- Surgical Video Understanding: Recognising the surgical environment from endoscopic videos to enable general understanding of the anatomical structures and procedural steps [ LoViT ].
- Expert Imitation Learning: Generating expert-like sequences of actions using video recordings from expert surgeons to train a basemodel with supervised fine-tuning [ SuPRA, SWAG ].
- Workflow Discovery and Planning: Generate multiple paths with a basemodel and use reinforcement learning to discover workflows that maximises the desired procedural outcomes for the patient, beyond human imagination [ In progress ].
Featured Projects
View All Projects
APPLICATION
Surgical Assistant App
Claude Language Model for Translating predictions into Recommendations.
COMPUTER VISION
Swarm Aerial Intelligence
Autonomous Drone (in progress)
ROBOTICS - DRONE
FPV Drone
Printing and Assembling a custom FPV eVTOL Drone
ROBOTICS - HUMANOID
Robotic Arm
Printing, Assembling and Training a LeRobot Arm
Short Biography
Maxence is a PhD candidate in artificial intelligence at King's College London, working under the guidance of experts in the field. His research focuses on AI applications for surgical action generation from robotic endoscopic video recordings. His work aims to develop intelligent systems that predict surgical actions by combining general world models with anticipatory decision-making, even in the absence of fully interactive simulations. Maxence is especially interested in integrating 'system 1' and 'system 2' thinking into AI for surgical tasks to enhance real-time decision-making. His previous publications include work on surgical phase recognition using transformers, and he is currently exploring offline reinforcement learning techniques using static datasets. Maxence holds a strong vision for advancing AI in healthcare and is committed to overcoming the challenges of static data environments.