Posts by Collection

Portfolio item number 1

Short description of portfolio item number 1

Portfolio item number 2

Short description of portfolio item number 2

SeeABLE: Soft Discrepancies and Bounded Contrastive Learning for Exposing Deepfakes

Published in ICCV 2023, 2023

Contrastive learning framework for robust deepfake detection and generalization to unseen synthetic media.

Recommended citation: Nicolas Larue, Ngoc-Son Vu, Vitomir Štruc, Peter Peer, Vassilis Christophides. SeeABLE: Soft Discrepancies and Bounded Contrastive Learning for Exposing Deepfakes. ICCV 2023. https://openaccess.thecvf.com/content/ICCV2023/html/Larue_SeeABLE_Soft_Discrepancies_and_Bounded_Contrastive_Learning_for_Exposing_Deepfakes_ICCV_2023_paper.html

QN-Mixer: A Quasi-Newton MLP-Mixer Model for Sparse-View CT Reconstruction

Published in CVPR 2024, 2024

Efficient neural architecture for sparse-view CT reconstruction, inspired by Quasi-Newton optimization.

Recommended citation: Ishak Ayad, Nicolas Larue, Maï K. Nguyen. QN-Mixer: A Quasi-Newton MLP-Mixer Model for Sparse-View CT Reconstruction. CVPR 2024. https://towzeur.github.io/QN-Mixer/

SSD: Neural Collapse Inspired Contrastive Continual Learning

Published in BMVC 2024, 2024

Contrastive continual learning method inspired by neural collapse.

Recommended citation: Nicolas Larue, et al. SSD: Neural Collapse Inspired Contrastive Continual Learning. BMVC 2024. https://bmva-archive.org.uk/bmvc/2024/papers/Paper_579/paper.pdf

Talk 1 on Relevant Topic in Your Field

Published: March 01, 2012

This is a description of your talk, which is a markdown files that can be all markdown-ified like any other post. Yay markdown!

Tutorial 1 on Relevant Topic in Your Field

Published: March 01, 2013

More information here

Talk 2 on Relevant Topic in Your Field

Published: February 01, 2014

More information here

Conference Proceeding talk 3 on Relevant Topic in Your Field

Published: March 01, 2014

This is a description of your conference proceedings talk, note the different field in type. You can put anything in this field.

Teaching Assistant

Teaching Assistant, CY Cergy Paris University / ENSEA, 2021

I taught and supervised 251 hours of engineering-level courses at ENSEA / CY Cergy Paris University, within the French Grande Ecole engineering system. ENSEA is a selective graduate engineering school specializing in electronics, computer science, signal processing, embedded systems, and artificial intelligence. Its engineering curriculum is master’s-equivalent and trains students for technical roles across software, AI, hardware, telecommunications, and systems engineering.

My teaching covered machine learning, deep learning, software engineering, algorithms, systems, and hardware-oriented signal processing. Most of my work was in practical sessions, labs, and projects, where students had to implement, debug, and reason about technical systems rather than only learn theory.

I helped students bridge the gap between mathematical concepts, code, and working systems - from algorithmic reasoning and software design to deep learning experiments, systems programming, and FPGA/DSP-oriented signal processing. This experience strengthened my ability to explain complex technical ideas clearly, diagnose implementation issues quickly, and communicate across different levels of abstraction.

Teaching focus

• Machine Learning and AI: Deep Learning, Artificial Intelligence, Big Data.
• Software and algorithms: Algorithms, Software Engineering, Transversal Software Project.
• Systems: Systems and Networks, Systems-on-Chip.
• Hardware-aware computing: Hardware for Signal Processing, FPGA/DSP-oriented practical work.

Selected responsibilities

• Supervised engineering students during lab sessions and technical projects.
• Helped students debug code, understand algorithms, and reason about implementation trade-offs.
• Supported practical deep learning and AI coursework, including model implementation and experiment analysis.
• Guided students through hardware/software interfaces in signal-processing and systems courses.
• Explained complex technical concepts in a way that connected theory, implementation, and engineering constraints.

Courses taught

Summary

Across these courses, I worked with engineering students on practical AI, software, and systems problems. This teaching experience strengthened my ability to explain technical ideas clearly, diagnose implementation issues quickly, and communicate across different levels of abstraction - from low-level systems and hardware constraints to high-level machine learning concepts.