Workshop on Frugality and Explainability (Toulouse)

Invited Talks

1. Invited Talk: Adil Zouitine - Scaling Tiny Vision-Language-Action Models to Real-Time Edge Robotics

06/10/2026 14:00

Title: Scaling Tiny Vision-Language-Action Models to Real-Time Edge Robotics

Bio: Adil Zouitine is a founding research scientist at UMA, where he works on general-purpose mobile and humanoid robots capable of learning in real time. He holds a PhD in robust reinforcement learning, supervised by Emmanuel Rachelson. His research focuses on robustness to disturbances, sample efficiency,...

3. Invited Talk: Alexandre Allauzen - Towards Frugal Deep Learning: Alternative to backprop, Data Sketching, and Causal Attention

07/10/2026 09:30

Title: Towards Frugal Deep Learning: Alternative to backprop, Data Sketching, and Causal Attention

Abstract: This talk presents recent research conducted by the MILES team, within the framework of the PEPR SHARP project, toward the development of frugal deep learning. As contemporary AI systems continue to grow in scale, computational cost, and energy consumption, there is a need...

11. Clovis Varangot-Reille

07/10/2026 11:00

Clovis Varangot-Reille, Wikit & Laboratoire Hubert Curien

Abstract (TBA): Présentation générale du routing, avec un focus sur un routeur low-resource

12. Léopold Maytié

07/10/2026 11:20

Abstract: TBA

13. Laure Vieu

07/10/2026 11:40

Abstract: TBA

14. Mathieu Serrurier

07/10/2026 13:30

Abstract: TBA

4. Invited Talk: Ronan Sicre and Moncef Garouani

07/10/2026 14:00

Title: TBA

Abstract; TBA

Bio:
Moncef Garouani is an Associate Professor of Computer Science at Université Toulouse Capitole and a researcher at IRIT. His research interests lie at the intersection of Machine Learning, Explainable Artificial Intelligence (XAI), multimodal learning, and Responsible AI. His work focuses on developing transparent, trustworthy, and human-centered...

5. Invited Talk: Meriem Belloucif - Low-Resource Preference Adaptation for LLMs

08/10/2026 09:30

Title: Low-Resource Preference Adaptation for LLMs

Abstract:

Adapting large language models to user-specific preferences is often constrained by the cost of
human annotation, making preference optimisation impractical in low-resource settings where
preferences cannot be reliably labelled by LLMs
themselves, e.g., due to cultural, subjective, or personalised contexts. I...

6. Invited Talk: Antonin Poché - Language models explainability

08/10/2026 14:00

Title: Language models explainability

Summary: We will examine the specificity of language in explainability for both classification and generation. Study how explainability methods are adapted to text and what the state of the art currently is. Finally, through a tutorial, we will apply the methods seen in theory, notably with a bias detection use case.

Bio: Antonin is a...

7. Invited Talk: Didier Schwab

09/10/2026 09:30

Title: TBA

Bio: Professeur des universités (CNU 27) -- Titulaire de la chaire AugmentIA pour l'humain augmenté par Intelligence Artificielle (Recherche, Innovation, Enseignement) -- Responsable de l'équipe GETALP (Groupe d’Étude en Traduction Automatique/Traitement Automatisé des Langues et de la Parole) du Laboratoire d'Informatique de Grenoble (~50 membres --permanent·e·s,...

8. Invited Talk: Lihu Chen - Knowledge Boundary Awareness in Large Language Models

Lihu Chen

09/10/2026 11:00

Title: Knowledge Boundary Awareness in Large Language Models

Abstract: Large language models (LLMs) possess remarkable knowledge and reasoning capabilities, yet their capabilities are bounded. A fundamental challenge for trustworthy and efficient AI is enabling models to identify the limits of their own knowledge before producing an answer. In this talk, I will present our recent...

10. Test session

Oral presentations