6 papers
Layer by layer, module by module: Choose both for optimal OOD probing of ViT
Ambroise Odonnat, Vasilii Feofanov, Laetitia Chapel +2
Recent studies have observed that intermediate layers of foundation models often yield more discriminative representations than the final layer. While initially attributed to autor…
Provable Benefits of In-Tool Learning for Large Language Models
Sam Houliston, Ambroise Odonnat, Charles Arnal +1
Tool-augmented language models, equipped with retrieval, memory, or external APIs, are reshaping AI, yet their theoretical advantages remain underexplored. In this paper, we addres…
CauKer: Classification Time Series Foundation Models Can Be Pretrained on Synthetic Data
Shifeng Xie, Vasilii Feofanov, Ambroise Odonnat +7
Time series foundation models (TSFMs) have recently gained significant attention due to their strong zero-shot capabilities and widespread real-world applications. Such models typi…
Easing Optimization Paths: a Circuit Perspective
Ambroise Odonnat, Wassim Bouaziz, Vivien Cabannes
Gradient descent is the method of choice for training large artificial intelligence systems. As these systems become larger, a better understanding of the mechanisms behind gradien…
Zero-shot Model-based Reinforcement Learning using Large Language Models
Abdelhakim Benechehab, Youssef Attia El Hili, Ambroise Odonnat +6
The emerging zero-shot capabilities of Large Language Models (LLMs) have led to their applications in areas extending well beyond natural language processing tasks. In reinforcemen…
Large Language Models as Markov Chains
Oussama Zekri, Ambroise Odonnat, Abdelhakim Benechehab +3
Large language models (LLMs) are remarkably efficient across a wide range of natural language processing tasks and well beyond them. However, a comprehensive theoretical analysis o…