Zhu LIAO

PhD student, Télécom ParisTech

Joined

August 2023

Names

Zhu LIAO (Preferred)

Emails

****@telecom-paris.fr (Confirmed)

Personal Links

Career & Education History

PhD student

Télécom ParisTech (telecom-paristech.fr)

2022 – 2026

MS student

IP Paris (ip-paris.fr)

2020 – 2022

Advisors, Relations & Conflicts

PhD Advisor

2022 – 2026

PhD Advisor

Enzo TARTAGLIONE

2022 – 2026

Expertise

Model compression

2022 – 2026

Publications

Layer Collapse Can be Induced by Unstructured Pruning
Zhu LIAO, Victor Quétu, Van-Tam Nguyen, Enzo Tartaglione
- Accepted by TMLR
- Readers: Everyone
Structured Transformer Circuits Pruning
Zhu LIAO, Van-Tam Nguyen, Enzo Tartaglione
- Submitted to ICLR 2026
- Readers: Everyone
LaCoOT: Layer Collapse through Optimal Transport
Victor Quétu, Zhu LIAO, Nour Hezbri, Fabio Pizzati, Enzo Tartaglione
- International Conference on Computer Vision 2025
- Readers: Everyone
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
- 9th Annual AAAI Conference on Artificial Intelligence (AAAI25)
- Readers: Everyone
Can Unstructured Pruning Reduce the Depth in Deep Neural Networks?
Zhu LIAO, Victor Quétu, Van-Tam Nguyen, Enzo Tartaglione
- International Conference on Computer Vision (ICCV) 2023
- Readers: Everyone
The Simpler The Better: An Entropy-Based Importance Metric to Reduce Neural Networks’ Depth
Victor Quétu, Zhu LIAO, Enzo Tartaglione
- Machine Learning and Knowledge Discovery in Databases. Research Track (ECML PKDD 2024)
- Readers: Everyone
NEPENTHE: Entropy-Based Pruning as a Neural Network Depth's Reducer
Zhu LIAO, Victor Quétu, Van-Tam Nguyen, Enzo Tartaglione
- ICLR 2025 Conference Withdrawn Submission
- Readers: Everyone

Co-Authors