Research

Replications, reports, and original work across robustness, adaptation, and generative modeling.

This page collects the projects where I used research as a craft: reading closely, reproducing carefully, testing assumptions, and trying to understand what really changes when a method leaves the paper.

Robustness Optimal transport Adaptation 3D detection
2025 / Original work

Sparse Representations Improve Adversarial Robustness of Neural Network Classifiers

Killian Steunou, Théo Druilhe, Sigurd Saue

We revisit linear dimensionality reduction as a defense and compare PCA with Sparse PCA as front-end feature extractors for adversarial robustness.

Preprint GitHub
2024 / Reproduction

Score-Based Generative Neural Networks for Large-Scale Optimal Transport

Original paper by Max Daniels, Tyler Maunu, Paul Hand

I reproduced the hybrid score-based transport approach and studied how regularization and sampling affect the quality of recovered maps.

Original paper Report GitHub
2024 / Adaptation

Test Time Training with Masked Autoencoders

Original paper by Yossi Gandelsman, Yu Sun, Xinlei Chen, Alexei A. Efros

I evaluated TTT-MAE on corruption benchmarks and explored an online variant that retains encoder updates between samples.

Original paper Report GitHub
2023 / Robustness

Are Generative Classifiers More Robust to Adversarial Attacks?

Original paper by Yingzhen Li, John Bradshaw, Yash Sharma

I revisited the robustness claims around generative classifiers and extended the original setup beyond MNIST to a more realistic dataset.

Original paper Report GitHub
2023 / Applied ML

Toxic Gas Characterization

Independent applied project

I studied domain shift caused by humidity changes and combined multi-task learning with adversarial adaptation for more stable gas characterization.

Report GitHub
2023 / Optimization

Convergence of SGD for Training Neural Networks with Sliced Wasserstein Losses

Original paper by Eloi Tanguy

We verified convergence behavior for sliced Wasserstein training on toy distributions and Fashion-MNIST, including a look at Noise Projected SGD.

Original paper Report GitHub
2023 / 3D Vision

An End-to-End Transformer Model for 3D Object Detection

Original paper by Ishan Misra, Rohit Girdhar, Armand Joulin

I reproduced 3DETR on SUN RGB-D and explored how an RGB-enhanced variant compares to the original point-cloud-only pipeline.

Original paper Report