demon2036

demon2036's Stars

• deepchem/deepchem

  Democratizing Deep-Learning for Drug Discovery, Quantum Chemistry, Materials Science and Biology

  Language:Python5.3k1.6k

• karpathy/LLM101n

  LLM101n: Let's build a Storyteller

  12.5k540

• cuda-mode/lectures

  Material for cuda-mode lectures

  Language:Jupyter Notebook1.5k138

• Stunkymonkey/nautilus-open-any-terminal

  Language:Python51250

• CUHK-AIM-Group/U-KAN

  [ArXiv' 24] U-KAN Makes Strong Backbone for Medical Image Segmentation and Generation

  Language:Python12314

• stes/dino-1

  PyTorch code for Vision Transformers training with the Self-Supervised learning method DINO

  1

• brianfitzgerald/jax-mmdit

  Implementation of Diffusion Transformers and Rectified Flow in Jax

  Language:Python11

• poloclub/robust-principles

  Robust Principles: Architectural Design Principles for Adversarially Robust CNNs

  Language:Python163

• affjljoo3581/deit3-jax

  Jax/Flax implementation of DeiT and DeiT-III (ViT)

  Language:Shell112

• 3b1b/manim

  Animation engine for explanatory math videos

  Language:Python60.2k5.7k

• ayaka14732/tpu-starter

  Everything you want to know about Google Cloud TPU

  Language:Python47227

• CG80499/KAN-GPT-2

  Training small GPT-2 style models using Kolmogorov-Arnold networks.

  Language:Python864

• snoop2head/KAN-ViT

  ViT with Kolmogorov–Arnold Networks (KAN) trained on ImageNet1K in Jax/Flax.

  Language:Python2

• GistNoesis/FourierKAN

  Language:Python63750

• google-research/vmoe

  Language:Jupyter Notebook52947

• Ekoda/SoftMoE

  Soft Mixture of Experts Vision Transformer, addressing MoE limitations as highlighted by Puigcerver et al., 2023.

  Language:Python9

• BobMcDear/attorch

  A subset of PyTorch's neural network modules, written in Python using OpenAI's Triton.

  Language:Python41117

• opendilab/PPOxFamily

  PPO x Family DRL Tutorial Course（决策智能入门级公开课：8节课帮你盘清算法理论，理顺代码逻辑，玩转决策AI应用实践 ）

  Language:Python1.8k164

• wzekai99/DM-Improves-AT

  Code for the paper "Better Diffusion Models Further Improve Adversarial Training" (ICML 2023)

  Language:Python11515

• volmodaoist/DIP-HW

  数字图像处理作业，代码开源

  Language:Python2

• anlcnydn/bilateral

  Bilateral Filter implementation both in Python and C++

  Language:C++7230

• Kedreamix/MAE-for-CIFAR

  MAE for CIFAR，由于可用资源有限，我们仅在 cifar10 上测试模型。我们主要想重现这样的结果：使用 MAE 预训练 ViT 可以比直接使用标签进行监督学习训练获得更好的结果。这应该是自我监督学习比监督学习更有效的数据的证据。

  Language:Jupyter Notebook474

• volmodaoist/TaoistTorchKit

  TaoistTorchKit for ML/DL development

  Language:Python1

• BladeTransformerLLC/gauzilla

  Gauzilla: a 3D Gaussian Splatting renderer written in Rust for WebAssembly with lock-free multithreading

  Language:Rust25121

• guikunchen/3DGS_NOTES

  Code Notes (in Chinese) for 3D Gaussian Splatting

  Language:C++10413

• graphdeco-inria/diff-gaussian-rasterization

  Language:Cuda727222

• graphdeco-inria/gaussian-splatting

  Original reference implementation of "3D Gaussian Splatting for Real-Time Radiance Field Rendering"

  Language:Python12.4k1.5k

• DeMoriarty/custom_matmul_kernels

  Customized matrix multiplication kernels

  Language:Jupyter Notebook526

• srush/mamba-scans

  Blog post

  16

• mihirp1998/AlignProp

  AlignProp uses direct reward backpropogation for the alignment of large-scale text-to-image diffusion models. Our method is 25x more sample and compute efficient than reinforcement learning methods (PPO) for finetuning Stable Diffusion

  Language:Python2027