demon2036's Stars
deepchem/deepchem
Democratizing Deep-Learning for Drug Discovery, Quantum Chemistry, Materials Science and Biology
karpathy/LLM101n
LLM101n: Let's build a Storyteller
cuda-mode/lectures
Material for cuda-mode lectures
Stunkymonkey/nautilus-open-any-terminal
CUHK-AIM-Group/U-KAN
[ArXiv' 24] U-KAN Makes Strong Backbone for Medical Image Segmentation and Generation
stes/dino-1
PyTorch code for Vision Transformers training with the Self-Supervised learning method DINO
brianfitzgerald/jax-mmdit
Implementation of Diffusion Transformers and Rectified Flow in Jax
poloclub/robust-principles
Robust Principles: Architectural Design Principles for Adversarially Robust CNNs
affjljoo3581/deit3-jax
Jax/Flax implementation of DeiT and DeiT-III (ViT)
3b1b/manim
Animation engine for explanatory math videos
ayaka14732/tpu-starter
Everything you want to know about Google Cloud TPU
CG80499/KAN-GPT-2
Training small GPT-2 style models using Kolmogorov-Arnold networks.
snoop2head/KAN-ViT
ViT with Kolmogorov–Arnold Networks (KAN) trained on ImageNet1K in Jax/Flax.
GistNoesis/FourierKAN
google-research/vmoe
Ekoda/SoftMoE
Soft Mixture of Experts Vision Transformer, addressing MoE limitations as highlighted by Puigcerver et al., 2023.
BobMcDear/attorch
A subset of PyTorch's neural network modules, written in Python using OpenAI's Triton.
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 )
wzekai99/DM-Improves-AT
Code for the paper "Better Diffusion Models Further Improve Adversarial Training" (ICML 2023)
volmodaoist/DIP-HW
数字图像处理作业,代码开源
anlcnydn/bilateral
Bilateral Filter implementation both in Python and C++
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。
volmodaoist/TaoistTorchKit
TaoistTorchKit for ML/DL development
BladeTransformerLLC/gauzilla
Gauzilla: a 3D Gaussian Splatting renderer written in Rust for WebAssembly with lock-free multithreading
guikunchen/3DGS_NOTES
Code Notes (in Chinese) for 3D Gaussian Splatting
graphdeco-inria/diff-gaussian-rasterization
graphdeco-inria/gaussian-splatting
Original reference implementation of "3D Gaussian Splatting for Real-Time Radiance Field Rendering"
DeMoriarty/custom_matmul_kernels
Customized matrix multiplication kernels
srush/mamba-scans
Blog post
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