-
Stanford University
- Stanford
-
15:30
(UTC -07:00) - https://kdmayer.github.io/
- https://orcid.org/0000-0002-5340-2711
Stars
Master programming by recreating your favorite technologies from scratch.
A concise but complete full-attention transformer with a set of promising experimental features from various papers
Build and share delightful machine learning apps, all in Python. 🌟 Star to support our work!
[CVPR'24 Oral] Official repository of Point Transformer V3 (PTv3)
An extremely fast Python package and project manager, written in Rust.
🌐 Make websites accessible for AI agents. Automate tasks online with ease.
Implementation of the Equiformer, SE3/E3 equivariant attention network that reaches new SOTA, and adopted for use by EquiFold for protein folding
Official code repository of paper Equivariance via Minimal Frame Averaging for More Symmetries and Efficiency.
Equivariant Steerable CNNs Library for Pytorch https://quva-lab.github.io/escnn/
A modular framework for neural networks with Euclidean symmetry
Official Code Repository for the paper C236 "Graph Generation with Diffusion Mixture" (ICML 2024).
PyTorch native quantization and sparsity for training and inference
Neural Network Force Field based on PyTorch
Python utilities to work with the RPLAN dataset
Vector (and Scalar) Quantization, in Pytorch
MiDi: Mixed Graph and 3D Denoising Diffusion for Molecule Generation
🤗 Diffusers: State-of-the-art diffusion models for image, video, and audio generation in PyTorch and FLAX.
[SIGGRAPH 2024] Official PyTorch Implementation of "BrepGen: A B-rep Generative Diffusion Model with Structured Latent Geometry".
The implementation of "HouseDiffusion: Vector Floorplan Generation via a Diffusion Model with Discrete and Continuous Denoising", https://arxiv.org/abs/2211.13287
A collection of resources and papers on Diffusion Models
Differentiable Iso-Surface Extraction Package (DISO)
MeshGPT: Generating Triangle Meshes with Decoder-Only Transformers
[ICLR 2025] From anything to mesh like human artists. Official impl. of "MeshAnything: Artist-Created Mesh Generation with Autoregressive Transformers"