Training a rail ego path detector (Laurent, 2024) using the DINOv3 backbone (Siméoni et al., 2025)

Experiments with TEP-Net (Laurent 2024, arxiv.org/abs/2403.13094), with the goal of improving performance through architectural enhancements.

Combining Grouped-Query Attention (https://arxiv.org/abs/2305.13245) with Deformable Attention (https://arxiv.org/abs/2201.00520) in PyTorch.

Grouped Query Attention implementation in PyTorch

A pytorch implementation of Multi Query Attention

Short programs for practicing CUDA

Experiments with the aim of improving the computational efficiency of SOTA object tracking algorithms.

Replacing the reset method in BBF (Schwarzer et al., 2023) with ReDo (Sokar et al., 2023), in order to investigate whether that improves performance on the Atari 100k benchmark.

Replicating the DQN agent from the 2015 Nature paper by Mnih et. al.

My solutions to the exercises in "Deep Reinforcement Learning" by Aske Plaat (arxiv.org/abs/2201.02135v5).

A curated list of computer science (mostly RL) books and papers I've read. This repository serves as a personal reference and resource for others interested in similar readings.

Some practice x86-64 Linux Assembly programs I wrote while learning x86-64.