Pinned Repositories
Differentiable-Frechet-Mean
[ICML 2020] Differentiating through the Fréchet Mean (https://arxiv.org/abs/2003.00335).
Neural-Manifold-Ordinary-Differential-Equations
[NeurIPS 2020] Neural Manifold Ordinary Differential Equations (https://arxiv.org/abs/2006.10254)
Awesome-Diffusion-Models
A collection of resources and papers on Diffusion Models
CS294_homework
My solutions to Berkeley's CS294 (Deep Reinforcement Learning) Homework
GAN-Q-Learning
Unofficial Implementation of GAN Q Learning https://arxiv.org/abs/1805.04874
Reflected-Diffusion
[ICML 2023] Reflected Diffusion Models (https://arxiv.org/abs/2304.04740)
RL-Halite
A reinforcement learning agent for the game halite.io
Scaling-Riemannian-Diffusion
[NeurIPS 2023] Scaling Riemannian Diffusion Models
Score-Entropy-Discrete-Diffusion
[ICML 2024 Best Paper] Discrete Diffusion Modeling by Estimating the Ratios of the Data Distribution (https://arxiv.org/abs/2310.16834)
TopologicalDeepLearning
A collection of Topology Methods in Deep Learning
louaaron's Repositories
louaaron/Score-Entropy-Discrete-Diffusion
[ICML 2024 Best Paper] Discrete Diffusion Modeling by Estimating the Ratios of the Data Distribution (https://arxiv.org/abs/2310.16834)
louaaron/Reflected-Diffusion
[ICML 2023] Reflected Diffusion Models (https://arxiv.org/abs/2304.04740)
louaaron/GAN-Q-Learning
Unofficial Implementation of GAN Q Learning https://arxiv.org/abs/1805.04874
louaaron/CS294_homework
My solutions to Berkeley's CS294 (Deep Reinforcement Learning) Homework
louaaron/TopologicalDeepLearning
A collection of Topology Methods in Deep Learning
louaaron/Scaling-Riemannian-Diffusion
[NeurIPS 2023] Scaling Riemannian Diffusion Models
louaaron/Awesome-Diffusion-Models
A collection of resources and papers on Diffusion Models
louaaron/RL-Halite
A reinforcement learning agent for the game halite.io
louaaron/CoupSimulation
A simulation of the playing card game coup
louaaron/darts
Differentiable architecture search for convolutional and recurrent networks
louaaron/DCGAN-Image-Generation
louaaron/deq
[NeurIPS'19] Deep Equilibrium Models
louaaron/website_old
My personal website
louaaron/dopamine
Dopamine is a research framework for fast prototyping of reinforcement learning algorithms.
louaaron/driver-classif
louaaron/edm
Elucidating the Design Space of Diffusion-Based Generative Models (EDM)
louaaron/expm
Differentiable and numerically stable implementation of expm
louaaron/hgcn
Hyperbolic Graph Convolutional Networks in PyTorch.
louaaron/HyperbolicTiling_Learning
Official implementation (learning part) for paper: Numerically Accurate Hyperbolic Embeddings Using Tiling-Based Models
louaaron/imagenet-simple-labels
Simpler human-readable labels for ImageNet 🏷
louaaron/pearl
Prototypes for Every Applicable RL algorithm
louaaron/pytorch
Tensors and Dynamic neural networks in Python with strong GPU acceleration
louaaron/sgd_tail_index
The codebase for the paper "A Tail-Index Analysis of Stochastic Gradient Noise in Deep Neural Networks"
louaaron/tensorforce
TensorForce: A TensorFlow library for applied reinforcement learning
louaaron/TopologyLayer
A Topology Layer for Machine Learning : Persistent Homology + Features for PyTorch
louaaron/torchdiffeq
Differentiable ODE solvers with full GPU support and O(1)-memory backpropagation.