Paul Caillon

According to our database, Paul Caillon authored at least 13 papers between 2021 and 2026.

Collaborative distances:

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

2026

Trading Complexity for Expressivity Through Structured Generalized Linear Token Mixing.

Erwan Fagnou, Paul Caillon, Blaise Delattre, Alexandre Allauzen

CoRR, May, 2026

Structured-Sparse Attention for Entity Tracking with Subquadratic Sequence Complexity.

Hangyue Zhao, Paul Caillon, Erwan Fagnou, Alexandre Allauzen

CoRR, May, 2026

Certified Robustness under Heterogeneous Perturbations via Hybrid Randomized Smoothing.

Blaise Delattre, Hengyu Wu, Paul Caillon, Wei Yang Bryan Lim, Yang Cao

CoRR, May, 2026

2025

Fast Training of Recurrent Neural Networks with Stationary State Feedbacks.

Paul Caillon, Erwan Fagnou, Alexandre Allauzen

CoRR, March, 2025

Attention Chaînée et Causale pour un Suivi Efficace des Entités.

Erwan Fagnou, Paul Caillon, Blaise Delattre, Alexandre Allauzen

Proceedings of the Actes des 32ème Conférence sur le Traitement Automatique des Langues Naturelles, 2025

Accelerated training through iterative gradient propagation along the residual path.

Erwan Fagnou, Paul Caillon, Blaise Delattre, Alexandre Allauzen

Proceedings of the Thirteenth International Conference on Learning Representations, 2025

Linear Attention with Global Context: A Multipole Attention Mechanism for Vision and Physics.

Alex Colagrande, Paul Caillon, Eva Feillet, Alexandre Allauzen

Proceedings of the IEEE/CVF International Conference on Computer Vision, ICCV 2025, 2025

Forward Only Learning for Orthogonal Neural Networks of Any Depth.

Paul Caillon, Alex Colagrande, Erwan Fagnou, Blaise Delattre, Alexandre Allauzen

Proceedings of the ECAI 2025 - 28th European Conference on Artificial Intelligence, 25-30 October 2025, Bologna, Italy, 2025

Bridging the Theoretical Gap in Randomized Smoothing.

Blaise Delattre, Paul Caillon, Quentin Barthélemy, Erwan Fagnou, Alexandre Allauzen

Proceedings of the International Conference on Artificial Intelligence and Statistics, 2025

2024

Chain and Causal Attention for Efficient Entity Tracking.

Erwan Fagnou, Paul Caillon, Blaise Delattre, Alexandre Allauzen

Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing, 2024

2023

Apprentissage profond sans supervision directe pour le traitement automatique des langues. (Weakly Supervised Deep Learning for Natural Language Processing).

Paul Caillon

PhD thesis, 2023

2021

Unsupervised Post-Tuning of Deep Neural Networks.

Christophe Cerisara, Paul Caillon, Guillaume Le Berre

Proceedings of the International Joint Conference on Neural Networks, 2021

Growing Neural Networks Achieve Flatter Minima.

Paul Caillon, Christophe Cerisara

Proceedings of the Artificial Neural Networks and Machine Learning - ICANN 2021, 2021