BIGKnight

ZORO

Zeroth-Order Regularized Optimization (ZORO): Approximately Sparse Gradients and Adaptive Sampling

BAdam

MathBlackBox

Adjoint-MAML

Repository of Meta-Learning with Adjoint Methods

LLaVA-NeXT

efficient-kan

An efficient pure-PyTorch implementation of Kolmogorov-Arnold Network (KAN).

jaxkan

JAX implementation of Kolmogorov Arnold Networks (KANs).

FourierKAN

pykan

Kolmogorov Arnold Networks

llama3

The official Meta Llama 3 GitHub site

scaling_on_scales

When do we not need larger vision models?

CaMeLS

Codebase for Context-aware Meta-learned Loss Scaling (CaMeLS). https://arxiv.org/abs/2305.15076.

evolutionary-model-merge

Official repository of Evolutionary Optimization of Model Merging Recipes

Understanding-Training-free-Diffusion-Guidance

lmms-eval

Accelerating the development of large multimodal models (LMMs) with lmms-eval

LMMS

Language Modelling Makes Sense - WSD (and more) with Contextual Embeddings

Conservative_PINNs

We propose a conservative physics-informed neural network (cPINN) on decompose domains for nonlinear conservation laws. The conservation property of cPINN is obtained by enforcing the flux continuity in the strong form along the sub-domain interfaces.

python-tsp-simulated-annealing

Visualisation of Simulated Annealing algorithm to solve TSP

prompt-to-prompt

mamba

Mamba SSM architecture

NeuralPDE.jl

Physics-Informed Neural Networks (PINN) Solvers of (Partial) Differential Equations for Scientific Machine Learning (SciML) accelerated simulation

Bi-level-PINN

inexact_dfo_bilevel_learning

Inexact Derivative-Free Optimization for Bilevel Learning

PINNacle

Codebase for PINNacle: A Comprehensive Benchmark of Physics-Informed Neural Networks for Solving PDEs.

partial-differential-equations

Notes and examples on how to solve partial differential equations with numerical methods, using Python.

PhiFlow

A differentiable PDE solving framework for machine learning

mle_score_ode

Official code for "Maximum Likelihood Training for Score-Based Diffusion ODEs by High-Order Denoising Score Matching" (ICML 2022)

denoising-diffusion-pytorch

Implementation of Denoising Diffusion Probabilistic Model in Pytorch

Otter

🦦 Otter, a multi-modal model based on OpenFlamingo (open-sourced version of DeepMind's Flamingo), trained on MIMIC-IT and showcasing improved instruction-following and in-context learning ability.

variance_reduced_neural_networks

Implementation of SVRG and SAGA optimization algorithms for deep learning topics.