Ambroise Odonnat

According to our database, Ambroise Odonnat authored at least 18 papers between 2024 and 2026.

Collaborative distances:

• Dijkstra number of four.
• Erdős number of four.

2026

Layer by layer, module by module: Choose both for optimal OOD probing of ViT.

Ambroise Odonnat, Vasilii Feofanov, Laetitia Chapel, Romain Tavenard, Ievgen Redko

CoRR, March, 2026

Vision Transformer Finetuning Benefits from Non-Smooth Components.

Ambroise Odonnat, Laetitia Chapel, Romain Tavenard, Ievgen Redko

CoRR, February, 2026

2025

Optimal Self-Consistency for Efficient Reasoning with Large Language Models.

Austin Feng, Marius Alonso, Ambroise Odonnat

CoRR, November, 2025

Provable Benefits of In-Tool Learning for Large Language Models.

Sam Houliston, Ambroise Odonnat, Charles Arnal, Vivien Cabannes

CoRR, August, 2025

CauKer: classification time series foundation models can be pretrained on synthetic data only.

Shifeng Xie, Vasilii Feofanov, Marius Alonso, Ambroise Odonnat, Jianfeng Zhang, Themis Palpanas, Ievgen Redko

CoRR, August, 2025

Leveraging Gradients for Unsupervised Accuracy Estimation under Distribution Shift.

Renchunzi Xie, Ambroise Odonnat, Vasilii Feofanov, Ievgen Redko, Jianfeng Zhang, Bo An

Trans. Mach. Learn. Res., 2025

SKADA-Bench: Benchmarking Unsupervised Domain Adaptation Methods with Realistic Validation On Diverse Modalities.

Yanis Lalou, Théo Gnassounou, Antoine Collas, Antoine de Mathelin, Ambroise Odonnat, Thomas Moreau, Alexandre Gramfort, Rémi Flamary

Trans. Mach. Learn. Res., 2025

Zero-shot Model-based Reinforcement Learning using Large Language Models.

Abdelhakim Benechehab, Youssef Attia El Hili, Ambroise Odonnat, Oussama Zekri, Albert Thomas, Giuseppe Paolo, Maurizio Filippone, Ievgen Redko, Balázs Kégl

Proceedings of the Thirteenth International Conference on Learning Representations, 2025

Easing Optimization Paths: a Circuit Perspective.

Ambroise Odonnat, Wassim Bouaziz, Vivien Cabannes

Proceedings of the 2025 IEEE International Conference on Acoustics, 2025

2024

A Visual Case Study of the Training Dynamics in Neural Networks.

Ambroise Odonnat, Wassim Bouaziz, Vivien Cabannes

CoRR, 2024

Large Language Models as Markov Chains.

Oussama Zekri, Ambroise Odonnat, Abdelhakim Benechehab, Linus Bleistein, Nicolas Boullé, Ievgen Redko

CoRR, 2024

SKADA-Bench: Benchmarking Unsupervised Domain Adaptation Methods with Realistic Validation.

Yanis Lalou, Théo Gnassounou, Antoine Collas, Antoine de Mathelin, Oleksii Kachaiev, Ambroise Odonnat, Alexandre Gramfort, Thomas Moreau, Rémi Flamary

CoRR, 2024

Unlocking the Potential of Transformers in Time Series Forecasting with Sharpness-Aware Minimization and Channel-Wise Attention.

Romain Ilbert, Ambroise Odonnat, Vasilii Feofanov, Aladin Virmaux, Giuseppe Paolo, Themis Palpanas, Ievgen Redko

CoRR, 2024

Characterising Gradients for Unsupervised Accuracy Estimation under Distribution Shift.

Renchunzi Xie, Ambroise Odonnat, Vasilii Feofanov, Ievgen Redko, Jianfeng Zhang, Bo An

CoRR, 2024

MaNo: Exploiting Matrix Norm for Unsupervised Accuracy Estimation Under Distribution Shifts.

Renchunzi Xie, Ambroise Odonnat, Vasilii Feofanov, Weijian Deng, Jianfeng Zhang, Bo An

Proceedings of the Advances in Neural Information Processing Systems 37: Annual Conference on Neural Information Processing Systems 2024, 2024

Analysing Multi-Task Regression via Random Matrix Theory with Application to Time Series Forecasting.

Romain Ilbert, Malik Tiomoko, Cosme Louart, Ambroise Odonnat, Vasilii Feofanov, Themis Palpanas, Ievgen Redko

Proceedings of the Advances in Neural Information Processing Systems 37: Annual Conference on Neural Information Processing Systems 2024, 2024

SAMformer: Unlocking the Potential of Transformers in Time Series Forecasting with Sharpness-Aware Minimization and Channel-Wise Attention.

Romain Ilbert, Ambroise Odonnat, Vasilii Feofanov, Aladin Virmaux, Giuseppe Paolo, Themis Palpanas, Ievgen Redko

Proceedings of the Forty-first International Conference on Machine Learning, 2024

Leveraging Ensemble Diversity for Robust Self-Training in the Presence of Sample Selection Bias.

Ambroise Odonnat, Vasilii Feofanov, Ievgen Redko

Proceedings of the International Conference on Artificial Intelligence and Statistics, 2024