Lists (1)
Stars
[NeurIPS 2025] How Many Tokens Do 3D Point Cloud Transformer Architectures Really Need?
Loss Functions in the Era of Semantic Segmentation: A Survey and Outlook
FastAPI framework, high performance, easy to learn, fast to code, ready for production
[WIP] Resources for AI engineers. Also contains supporting materials for the book AI Engineering (Chip Huyen, 2025)
Replace 'hub' with 'ingest' in any GitHub URL to get a prompt-friendly extract of a codebase
This is an official implementation for "Swin Transformer: Hierarchical Vision Transformer using Shifted Windows".
Free, simple, fast interactive diagrams for any GitHub repository
This repository is mainly dedicated for listing the recent research advancements in the application of Self-Supervised-Learning in medical images computing field
Graph Attention Networks (https://arxiv.org/abs/1710.10903)
Representation learning on large graphs using stochastic graph convolutions.
PyTorch code for Vision Transformers training with the Self-Supervised learning method DINO
A novel machine learning pipeline to analyse spatial transcriptomics data
SpaGCN: Integrating gene expression, spatial location and histology to identify spatial domains and spatially variable genes by graph convolutional network
Collection of publicly available spatial transcriptomes
High-Resolution Spatial Transcriptomics Using Histology Images with HisToSGE (Pathology Image Large Model, Transformers)
A curated repository designed to serve as a comprehensive guide for researchers interested in the intersection of Transformer models and genomics. This repository compiles key academic papers that …
🧑🏫 60+ Implementations/tutorials of deep learning papers with side-by-side notes 📝; including transformers (original, xl, switch, feedback, vit, ...), optimizers (adam, adabelief, sophia, ...), ga…
The official project website of "Omni-Dimensional Dynamic Convolution" (ODConv for short, spotlight in ICLR 2022).
Benchmarking clustering, alignment, and integration methods for spatial transcriptomics
Official Implementation of "ADOPT: Modified Adam Can Converge with Any β2 with the Optimal Rate"
Bayesian model for clustering and enhancing the resolution of spatial gene expression experiments.