Apprentissage automatique · GitHub

zea: A Toolbox for Cognitive Ultrasound Imaging

A differentiable PDE solving framework for machine learning

• Tight integration with PyTorch, Jax and TensorFlow for straightforward neural network training with fully differentiable simulations that can run on the GPU.
• Built-in PDE operations with focus on fluid phenomena, allowing for concise formulation of simulations.

[NeurIPS2026] Flexible scientific foundation models trained with synthetic online data generation

Awesome papers on Language-Model-as-a-Service (LMaaS)

Python Audio Analysis Library: Feature Extraction, Classification, Segmentation and Applications

Plug and Play Language Model implementation. Allows to steer topic and attributes of GPT-2 models.

A model-agnostic visual debugging tool for machine learning

A Python package for Bayesian forecasting with object-oriented design and probabilistic models under the hood.

The official implementation of Self-Play Fine-Tuning (SPIN)

An ML Platform for storing, analyzing, and visualizing your data all in the browser.

🏔️ ALPS: Visual State Encoders for World Models

• 🎯 State. The lowest aggregate LIBERO state-probe error among ViT-B encoders, matching the 3.5x larger V-JEPA 2-L.
• 💬 Language. A native text tower: image-text retrieval within 2 points of the best image-text encoders.

Repo for the Deep Reinforcement Learning Nanodegree program

Setup and customize deep learning environment in seconds.