Victor Quétu

According to our database, Victor Quétu authored at least 18 papers between 2023 and 2026.

Collaborative distances:

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

2026

From Weights to Layers: Deep Neural Network Compression for Efficient Inference. (Des Poids aux Couches: Compression de Réseau Neuronal Profond pour une Inférence Efficace).

Victor Quétu

PhD thesis, 2026

Layer Collapse Can be Induced by Unstructured Pruning.

Zhu Liao, Victor Quétu, Van-Tam Nguyen, Enzo Tartaglione

Trans. Mach. Learn. Res., 2026

2025

FOLDER: Accelerating Multi-modal Large Language Models with Enhanced Performance.

Haicheng Wang, Zhemeng Yu, Gabriele Spadaro, Chen Ju, Victor Quétu, Enzo Tartaglione

CoRR, January, 2025

LayerFold: A Python library to reduce the depth of neural networks.

Giommaria Pilo, Nour Hezbri, André Pereira e Ferreira, Victor Quétu, Enzo Tartaglione

SoftwareX, 2025

FOLDER: Accelerating Multi-Modal Large Language Models with Enhanced Performance.

Haicheng Wang, Zhemeng Yu, Gabriele Spadaro, Chen Ju, Victor Quétu, Shuai Xiao, Enzo Tartaglione

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

LaCoOT: Layer Collapse through Optimal Transport.

Victor Quétu, Zhu Liao, Nour Hezbri, Fabio Pizzati, Enzo Tartaglione

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

Till the Layers Collapse: Compressing a Deep Neural Network Through the Lenses of Batch Normalization Layers.

Zhu Liao, Nour Hezbri, Victor Quétu, Van-Tam Nguyen, Enzo Tartaglione

Proceedings of the Thirty-Ninth AAAI Conference on Artificial Intelligence, 2025

2024

LaCoOT: Layer Collapse through Optimal Transport.

Victor Quétu, Nour Hezbri, Enzo Tartaglione

CoRR, 2024

NEPENTHE: Entropy-Based Pruning as a Neural Network Depth's Reducer.

Zhu Liao, Victor Quétu, Van-Tam Nguyen, Enzo Tartaglione

CoRR, 2024

The Simpler The Better: An Entropy-Based Importance Metric to Reduce Neural Networks' Depth.

Victor Quétu, Zhu Liao, Enzo Tartaglione

Proceedings of the Machine Learning and Knowledge Discovery in Databases. Research Track, 2024

Memory-Optimized Once-For-All Network.

Maxime Girard, Victor Quétu, Samuel Tardieu, Van-Tam Nguyen, Enzo Tartaglione

Proceedings of the Computer Vision - ECCV 2024 Workshops, 2024

DSD²: Can We Dodge Sparse Double Descent and Compress the Neural Network Worry-Free?

Victor Quétu, Enzo Tartaglione

Proceedings of the Thirty-Eighth AAAI Conference on Artificial Intelligence, 2024

2023

Disentangling private classes through regularization.

Enzo Tartaglione, Francesca Gennari, Victor Quétu, Marco Grangetto

Neurocomputing, October, 2023

Dodging the Sparse Double Descent.

Victor Quétu, Enzo Tartaglione

CoRR, 2023

The Quest of Finding the Antidote to Sparse Double Descent.

Victor Quétu, Marta Milovanovic

Proceedings of the Machine Learning and Principles and Practice of Knowledge Discovery in Databases, 2023

Dodging the Double Descent in Deep Neural Networks.

Victor Quétu, Enzo Tartaglione

Proceedings of the IEEE International Conference on Image Processing, 2023

Sparse Double Descent in Vision Transformers: Real or Phantom Threat?

Victor Quétu, Marta Milovanovic, Enzo Tartaglione

Proceedings of the Image Analysis and Processing - ICIAP 2023, 2023

Can Unstructured Pruning Reduce the Depth in Deep Neural Networks?

Zhu Liao, Victor Quétu, Van-Tam Nguyen, Enzo Tartaglione

Proceedings of the IEEE/CVF International Conference on Computer Vision, 2023