Our paper, “WattLayer: Get Layers Right to Estimate Inference Energy of Neural Networks,” was accepted to SuRE'26, the 1st Workshop on Sustainability and Resource-Efficiency of Artificial Intelligence, held alongside IJCAI-ECAI 2026.

WattLayer is a method for estimating the inference …

Talk presented at GreenDays 2026 in Sophia-Antipolis, on the 10th and 11th of March, on estimating neural network architecture energy consumption.

• Slides (PDF)
• Video recording

Poster presented at GreenDays 2025 in Rennes, on the 25th and 26th of March, on energy efficient management and provisioning of generative AI services for 6G networks.

• Poster (PDF)

Master’s thesis completed as part of my M.Sc. program, in collaboration with the UMR Génétique Quantitative et Evolution – Le Moulon joint research unit of AgroParisTech, INRAE, CNRS and Université Paris-Saclay, under the supervision of Dr. Tristan Mary-Huard and Dr. Laurence Moreau.

We built …