Highlights
- Pro
Stars
Official reference implementation of dynamics contrastive learning (DCL).
This package contains the original 2012 AlexNet code.
The Python version of the least dependent component analysis and mutual information methods proposed by A. Kraskov, H. Stögbauer, and P. Grassberger, Phys. Rev. E 69 (6) 066138, 2004.
Multifactor Sequential Disentanglement via Structured Koopman Autoencoders
Pretrained deep learning models for Jax/Flax: StyleGAN2, GPT2, VGG, ResNet, etc.
C++ API for the disting NT Eurorack module
This is the repository for the distill web framework
Sound2Synth: Interpreting Sound via FM Synthesizer Parameters Estimation
Multi-sensor data collection gathered to expand research on anomaly detection, fault diagnosis, and predictive maintenance, mainly using non-invasive methods such as thermal observation or vibratio…
Learnable latent embeddings for joint behavioral and neural analysis - Official implementation of CEBRA
A framework for neural network control of dynamical systems over graphs.
A Python package for probabilistic state space modeling with JAX
Official implementation of the paper "GRAPES: Learning to Sample Graphs for Scalable Graph Neural Networks".
Discovers high dimensional models from 1D data using deep delay autoencoders
Associated code to ECAI Workshop ML meets DE 2024 paper - https://proceedings.mlr.press/v255/monsel24a.html
mebitek / performer
Forked from westlicht/performerPER|FORMER Eurorack Sequencer
Digital Audio Workstation with Python; VST instruments/effects, parameter automation, FAUST, JAX, Warp Markers, and JUCE processors
Command line C++ and Python VSTi Host library with MFCC, FFT, RMS and audio extraction and .wav writing.
A project testing and comparing various algorithms for creating isosurfaces.
A procedurally generated planet created in Godot, based on Sebastian Lague's procedural planet for Unity
Finetune Qwen3, Llama 4, TTS, DeepSeek-R1 & Gemma 3 LLMs 2x faster with 70% less memory! 🦥
20+ high-performance LLMs with recipes to pretrain, finetune and deploy at scale.
Kraskov mutual information estimation based on approximate nearest neighbours
A library for efficient similarity search and clustering of dense vectors.