Workshop on Frugality and Explainability (Toulouse)

Invited Talks

1. Invited Talk: Adil Zouitine - Efficient Vision-Language-Action Model

M. Adil Zouitine (UMA)

06/10/2026 14:00

Title: Efficient Vision-Language-Action Model

Abstract: The talk asks how to make general-purpose robot policies usable without industrial-scale data or GPUs. Its answer is that low-resource robotics means choosing carefully where every parameter, demonstration and millisecond goes. It starts from first principles: a VLA is a policy that reads camera images, an instruction and the...

15. Invited Talk: Constance Douwes - Energy and environmental impacts of deep learning

Mme Constance Douwes (Centrale Méditerranée)

06/10/2026 15:00

Title: Energy and environmental impacts of deep learning

Abstract: In recent years, artificial intelligence based on deep learning models has become increasingly widespread across a wide range of applications, achieving ever-greater performance with ever-increasing computational cost. This growth drives higher energy consumption and carbon emissions, running counter the emission...

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

M. Alexandre Allauzen (ESPCI Paris - LAMSADE)

07/10/2026 09:00

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...

12. Léopold Maytié - Learning Universal Multimodal Representations via a Global Workspace with Minimal Paired Data

07/10/2026 10:30

Title: Learning Universal Multimodal Representations via a Global Workspace with Minimal Paired Data

Abstract: Learning multimodal representation using current deep learning methods requires a massive amount of multimodal paired data, relying on pure supervised learning. These paired data are difficult to obtain, limiting the possible amount available or requiring a lot of works to...

13. Laure Vieu - Environmental impacts: where is our responsibility?

07/10/2026 11:00

Title: Environmental impacts: where is our responsibility?

Abstract : In this talk, after briefly reviewing the environmental impacts of the AI industry at large, I'll point out that the urgently needed frugality goes beyond designing small models with low cost and consumption. Our responsibility as scientists also lie in controlling the uses of our results to achieve sufficiency....

14. Mathieu Serrurier - Is Trustworthy AI Compatible with Frugality in Machine Learning?

07/10/2026 13:30

Title: s Trustworthy AI Compatible with Frugality in Machine Learning?

Abstract: This presentation focuses on adversarial robustness in critical systems and its compatibility with frugality. We will examine the benefits, as well as the theoretical and practical limitations, of current adversarial robustness guarantees. Furthermore, we will explore how these guarantees interact with...

4. Invited Talk: Ronan Sicre, Moncef Garouani and Hajar Dekdegue

Mme Hajar Dekdegue (UT - IRIT), M. Moncef Garouani (Université Toulouse Capitole - IRIT), M. Ronan Sicre (University of Toulouse - IRIT)

07/10/2026 14:00

Title: Explainable AI (XAI) and visual recognition models

Abstract: First, a one hour presentation will provide details on the various types of explanations methods, pros and cons. XAI include two main types of methods: post-hoc or passive and transparency or active. Posthoc methods aims at explaining an already trained mode, while active methods aims at rendering the model more...

16. Clovis Varangot-Reille - LLM Routing: Selecting the Cheapest Capable LLM for Every Query

08/10/2026 09:30

Title: LLM Routing: Selecting the Cheapest Capable LLM for Every Query

Abstract: Most LLM-based applications route every query to a single generalist model, typically a very large one, so that quality holds across all incoming queries. In practice, many of those queries are simple enough that a much cheaper model would answer them just as well. LLM routing reframes model choice as a...

17. Grégoire Dhimoïla - Cross-Modal Redundancy and the Geometry of Vision–Language Embeddings

08/10/2026 10:00

Title: Cross-Modal Redundancy and the Geometry of Vision–Language Embeddings

Abstract: Vision–language models (VLMs) align images and text with remarkable success, yet the geometry of their shared embedding space remains poorly understood. To probe this geometry, we begin from the Iso-Energy Assumption, which exploits cross-modal redundancy: a concept that is truly shared should...

6. Invited Talk: Antonin Poché - Language models explainability

M. Antonin Poché (IRT Saint Exupéry - IRIT)

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 - Saisir l’IA générative avec justesse : RAG pour une IA plus frugale, souveraine et maîtrisée

M. Didier Schwab (UGA - LIG)

09/10/2026 09:30

Title: Saisir l’IA générative avec justesse : RAG pour une IA plus frugale, souveraine et maîtrisée

Abstract: Les systèmes d'IA générative sont souvent associés à des modèles toujours plus grands et plus coûteux. Pourtant, dans de nombreux contextes professionnels, la performance ne passe pas nécessairement par l'augmentation de la taille du modèle.
Cette présentation s'appuie sur...

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...