cv

Post-doctoral Researcher

IRIT Computer Science Research Institute of Toulouse

Concept Probing and Learning with Large Language Models (LLMs).

• LLMs

PhD

IMT Mines Ales

Machine Learning

• Machine learning

Master Research 2

University of Bretagne Occidental

Signal and Telecommunication

• Signal Processing

Engineer

National Advanced School of Engineering (ENSAM)

Electromechanical Systems

• Math, Physics

1st at Challenge AffectMove2021

Challenge team organisers

We win Task 1 of this AffectMove challenge: Protective Behaviour Detection based on Multimodal Body Movement Data. The aim of this task is to advance continuous detection of protective behaviours, i.e., bodily-expressed pain behaviours, in people with chronic musculoskeletal pain.

Transformer with Controlled Attention for Synchronous Motion Captioning

AAAI2026

Our method introduces mechanisms to control self- and cross-attention distributions of the Transformer, allowing interpretability and time-aligned text generation. We achieve this through masking strategies and structuring losses that push the model to maximize attention only on the most important frames contributing to the generation of a motion word.

Guided Attention for Interpretable Motion Captioning

BMVC-2024

We introduce a novel architecture design that enhances text generation quality by emphasizing interpretability through spatio-temporal and adaptive attention mechanisms. To encourage human-like reasoning, we propose methods for guiding attention during training, emphasizing relevant skeleton areas over time and distinguishing motion-related words.

Motion2language, unsupervised learning of synchronized semantic motion segmentation

Neural Computing and Applications

We investigate building a sequence to sequence architecture for motion-to-language translation and synchronization. The aim is to translate motion capture inputs into English natural-language descriptions, such that the descriptions are generated synchronously with the actions performed, enabling semantic segmentation as a byproduct, but without requiring synchronized training data.

Motion Captioning

We propose a new recurrent formulation of local attention that is suited for synchronous text generation, as well as an improved motion encoder architecture better suited to smaller data and for synchronous generation. We evaluate both contributions in individual experiments, using the standard BLEU4 metric, as well as a simple semantic equivalence measure, on the KIT motion language dataset.

• Synchronization
• Text generation