Skip to content
View NathanVanier's full-sized avatar

Block or report NathanVanier

Block user

Prevent this user from interacting with your repositories and sending you notifications. Learn more about blocking users.

You must be logged in to block users.

Maximum 250 characters. Please don't include any personal information such as legal names or email addresses. Markdown supported. This note will be visible to only you.
Report abuse

Contact GitHub support about this user’s behavior. Learn more about reporting abuse.

Report abuse
NathanVanier/README.md

Nathan VANIER DE SAINT-AUNAY

M2 Data Science | Deep Learning & Generative Models
Seeking a 6-month internship in Data Science / Machine Learning


Profile

Academic Background

Core Machine Learning & Deep Learning

  • Deep Learning : DNN, RNN, Transformers
  • Machine learning : Linear Regression, Logistic Regression, kNN, k-Means, Hierarchical Clustering, GMM, SVM, Random Forests, XGBoost
  • Optimization for Data Science : GD, AGD, PGD, APGD, SGD, BFGS
  • Reinforcement Learning basics
  • Generative Models basics
  • Natural Language Processing & Sentiment Analysis
  • AI for Sound: Analysis, Processing & Generation

Projects

Generative Modeling — Consistency Model Reproduction

Reproduction (simplified) of the paper:

"How to Build a Consistency Model: Learning Flow Maps via Self-Distillation"

Implemented:

  • Self-distillation training loop
  • Flow-map consistency objective
  • Sampling comparison

Focus areas:

  • Diffusion-based generative modeling
  • Continuous-time formulation
  • Numerical stability considerations
  • Experimental validation

Stack:

  • PyTorch
  • Mathematical modeling
  • Research paper implementation

🔗 Repository: https://github.com/NathanVanier/flow-map-self-distillation


Technical Skills

Languages

Python, SQL, java

Machine Learning

scikit-learn, PyTorch, pandas, numpy

Deep Learning

RNN, Attention, Seq2Seq, Diffusion Models, Consistency Models

Tools

Git, Linux, Jupyter


Objective

Looking for a 6-month internship starting <01/04/2026 date> where I can contribute to:

  • Model development and evaluation
  • Research implementation
  • Generative AI or NLP systems
  • End-to-end ML pipelines

Contact

Pinned Loading

  1. flow-map-self-distillation flow-map-self-distillation Public

    Jupyter Notebook