| CARVIEW |
Select Language
HTTP/2 200
date: Mon, 29 Dec 2025 23:22:01 GMT
content-type: text/html
nel: {"report_to":"cf-nel","success_fraction":0.0,"max_age":604800}
link: <./_app/immutable/assets/0.ebab8ecf.css>; rel="preload";as="style"; nopush, <./_app/immutable/assets/2.3b549260.css>; rel="preload";as="style"; nopush, <./_app/immutable/entry/start.f0a907b8.js>; rel="modulepreload"; nopush, <./_app/immutable/chunks/scheduler.aa9ca62a.js>; rel="modulepreload"; nopush, <./_app/immutable/chunks/singletons.172d5fce.js>; rel="modulepreload"; nopush, <./_app/immutable/entry/app.81655fee.js>; rel="modulepreload"; nopush, <./_app/immutable/chunks/preload-helper.a4192956.js>; rel="modulepreload"; nopush, <./_app/immutable/chunks/index.7a9edd8a.js>; rel="modulepreload"; nopush, <./_app/immutable/nodes/0.93c04099.js>; rel="modulepreload"; nopush, <./_app/immutable/nodes/2.6f99cb17.js>; rel="modulepreload"; nopush, <./_app/immutable/chunks/2.d9ba8143.js>; rel="modulepreload"; nopush, <./_app/immutable/chunks/stores.69d44ac6.js>; rel="modulepreload"; nopush
x-sveltekit-page: true
vary: accept-encoding
report-to: {"group":"cf-nel","max_age":604800,"endpoints":[{"url":"https://a.nel.cloudflare.com/report/v4?s=BUqUQ%2BCEwoeEIp7SwVmWg98Jdu6h7VVI0o3HyljcPaDA96qzJklg5E%2BHoYVbN2v4darMuNBhKYkhQY4Aruqo8lEbIm4%2F9f%2BYHn%2Fd"}]}
cf-cache-status: DYNAMIC
server: cloudflare
content-encoding: gzip
cf-ray: 9b5d0975c97346ef-BOM
alt-svc: h3=":443"; ma=86400
See more 
Charles Vin
Freelance ML Engineer
Project Spotlight
Paper re-implementation: ClimODE: Climate Forecasting With Physics-informed Neural ODEs, ICLR 2024
- Re-implementation, experimentation and review.
- Creation of a poster to present the article and our supplementary experiments.
- Enhanced key features like distributed training and code readability.
- Employed collaborative tools like Notion, GitHub pre-commit hooks and EditorConfig to foster effective collaboration and maintain codebase cleanliness.
PyTorch Torch Ignite CNN ViT ODE
Neural Network DIY
- Development of a neural network library entirely in Numpy
- Implementation of essential modules (linear layers, 1D convolutions, etc.) for creating, training and evaluating neural networks.
- Performance optimization through advanced use of Numpy for efficient computation
Numpy Mathematics Neural Networks
Speaker Recognition & Sentiment analysis
- Design and implementation of a natural language processing system based on bag-of-words representations for speaker recognition and sentiment analysis.
- Use of textual data pre-processing and machine learning modeling techniques (Naive Bayes, logistic regression, SVMs).
- Management of class balancing and estimation of model generalization performance.
NLP Bag of word Unbalanced learning
Experiences
Filter by roles:
Filtered
-
ML Engineer - National Audiovisual Institute (INA)
- Design and implement a image search engine unlocking access to 250K+ hours of archival video content, surfacing media previously difficult or impossible to find.
- Drive full-stack development across frontend, backend, and search infrastructure using Vue.js, FastAPI, and Elasticsearch.
- Orchestrate large-scale on-premise embedding pipelines with Airflow DAGs and vLLM, producing more than 1 billion image embeddings.
-
Research Internship - Self-supervised Learning on Satellite Image Time Series
- Conducted extensive literature review on state-of-the-art methods in self-supervised learning (SSL) applied to Satellite Image Time Series (SITS).
- Reproduced and benchmarked baseline models to ensure robust performance comparisons.
- Developed and implemented an innovative image retrieval pretext task utilizing a specialized hierarchical loss function to train SSL models on SITS data.
- Actively participated in research lab activities.
-
Research project - Explainable insects classification
- Development of a convolutional neural network for insect classification.
- Use XAI with gradient-based approaches and the LIME and SHAP frameworks.
- Takeover, adaptation and documentation of the project.
- Experiences monitoring and evaluation of different models with WandB.
-
Research Project - INRIA
- Study of the trade-off between observation and action in reinforcement learning (subject details)
- Understanded, independently, a cutting-edge problem in reinforcement learning.
- Demonstrated perseverance and determination in the face of technical challenges.
- Implemented an experimental plan.
Education
-
Master's Degree in Computer Science - Specialisation Data, Machine Learning, and Knowledge (DAC)
Learn moreRelevant courses:
- Image and signal processing
- Mathematics for ML (statistics/probability, Markov Chain, ...)
- Databases: SQL, XML, JSON, distributed databases
- Machine Learning: classification, neural networks, decision trees
- Natural language processing, information retrieval
- Opening courses from Master of Mathematics: statistical learning and convex optimization.
-
Bachelor's degree, Mathematics and Computer Science applied to Cognitive Science
Learn moreGrade: Highest Honours
Relevant courses:
- Decision statistics: practical work in R.
- Probability and measurement theory
- Cognitive science
Relevant academic projects:
- Bayesien Tweet Classifier: "Positive" or "Negative" tweets classifier
- Basic ML algorithm from scratch: KNN, KMean, linear/polynomial regression
My main sports
Running
Climbing
Last 4 weeks
33 km
Distance
166 min
Moving Time
Total Activities
Fetched using Strava API