Victor Quétu

22 papers A* 2B 1Journal 14Unranked 5
YearRankTypeTitle / Venue / Authors
2026 J jnl
Layer Collapse Can be Induced by Unstructured Pruning.
Trans. Mach. Learn. Res.
Zhu Liao, Victor Quétu, Van-Tam Nguyen, Enzo Tartaglione
2025 J jnl
FOLDER: Accelerating Multi-modal Large Language Models with Enhanced Performance.
CoRR
Haicheng Wang, Zhemeng Yu, Gabriele Spadaro, Chen Ju, Victor Quétu, Enzo Tartaglione
2025 J jnl
LayerFold: A Python library to reduce the depth of neural networks.
SoftwareX
Giommaria Pilo, Nour Hezbri, André Pereira e Ferreira, Victor Quétu, Enzo Tartaglione
2025 A* conf
Till the Layers Collapse: Compressing a Deep Neural Network Through the Lenses of Batch Normalization Layers.
AAAI
Zhu Liao, Nour Hezbri, Victor Quétu, Van-Tam Nguyen, Enzo Tartaglione
2024 A* conf
DSD²: Can We Dodge Sparse Double Descent and Compress the Neural Network Worry-Free?
AAAI
Victor Quétu, Enzo Tartaglione
2024 J jnl
LaCoOT: Layer Collapse through Optimal Transport.
CoRR
Victor Quétu, Nour Hezbri, Enzo Tartaglione
2024 — conf
Memory-Optimized Once-For-All Network.
ECCV Workshops (11)
Maxime Girard, Victor Quétu, Samuel Tardieu, Van-Tam Nguyen, Enzo Tartaglione
2024 J jnl
Memory-Optimized Once-For-All Network.
CoRR
Maxime Girard, Victor Quétu, Samuel Tardieu, Van-Tam Nguyen, Enzo Tartaglione
2024 J jnl
NEPENTHE: Entropy-Based Pruning as a Neural Network Depth's Reducer.
CoRR
Zhu Liao, Victor Quétu, Van-Tam Nguyen, Enzo Tartaglione
2024 J jnl
The Simpler The Better: An Entropy-Based Importance Metric To Reduce Neural Networks' Depth.
CoRR
Victor Quétu, Zhu Liao, Enzo Tartaglione
2024 — conf
The Simpler The Better: An Entropy-Based Importance Metric to Reduce Neural Networks' Depth.
ECML/PKDD (6)
Victor Quétu, Zhu Liao, Enzo Tartaglione
2024 J jnl
Till the Layers Collapse: Compressing a Deep Neural Network through the Lenses of Batch Normalization Layers.
CoRR
Zhu Liao, Nour Hezbri, Victor Quétu, Van-Tam Nguyen, Enzo Tartaglione
2023 — conf
Can Unstructured Pruning Reduce the Depth in Deep Neural Networks?
ICCV (Workshops)
Zhu Liao, Victor Quétu, Van-Tam Nguyen, Enzo Tartaglione
2023 J jnl
Can Unstructured Pruning Reduce the Depth in Deep Neural Networks?
CoRR
Zhu Liao, Victor Quétu, Van-Tam Nguyen, Enzo Tartaglione
2023 J jnl
Disentangling private classes through regularization.
Neurocomputing
Enzo Tartaglione, Francesca Gennari, Victor Quétu, Marco Grangetto
2023 B conf
Dodging the Double Descent in Deep Neural Networks.
ICIP
Victor Quétu, Enzo Tartaglione
2023 J jnl
Dodging the Double Descent in Deep Neural Networks.
CoRR
Victor Quétu, Enzo Tartaglione
2023 J jnl
Dodging the Sparse Double Descent.
CoRR
Victor Quétu, Enzo Tartaglione
2023 — conf
Sparse Double Descent in Vision Transformers: Real or Phantom Threat?
ICIAP (2)
Victor Quétu, Marta Milovanovic, Enzo Tartaglione
2023 J jnl
Sparse Double Descent in Vision Transformers: real or phantom threat?
CoRR
Victor Quétu, Marta Milovanovic, Enzo Tartaglione
2023 — conf
The Quest of Finding the Antidote to Sparse Double Descent.
PKDD/ECML Workshops (4)
Victor Quétu, Marta Milovanovic
2023 J jnl
The Quest of Finding the Antidote to Sparse Double Descent.
CoRR
Victor Quétu, Marta Milovanovic