Alexandre Milesi

Alexandre Milesi is a deep learning algorithms engineer at NVIDIA. He holds a master’s in machine learning from the UTC, France, and a master’s in robotics and multi-agent systems from Sorbonne University, France. Before joining NVIDIA, Alexandre was an affiliate researcher at Berkeley Lab, solving electrical grid problems using deep reinforcement learning. At NVIDIA, his work is focused on DL algorithms for drug discovery and computer vision, including equivariant graph neural networks.

Posts by Alexandre Milesi

Llama 3.2 Full-Stack Optimizations Unlock High Performance on NVIDIA GPUs

Meta recently released its Llama 3.2 series of vision language models (VLMs), which come in 11B parameter and 90B parameter variants. These models are... 6 MIN READ

Simulation / Modeling / Design Aug 24, 2021

Accelerating SE(3)-Transformers Training Using an NVIDIA Open-Source Model Implementation

SE(3)-Transformers are versatile graph neural networks unveiled at NeurIPS 2020. NVIDIA just released an open-source optimized implementation that uses 43x less... 8 MIN READ