#
Starred repositories
Physics-Guided All-Atom Diffusion Model for Accurate Protein-Ligand Complex Prediction
PINDER: The Protein INteraction Dataset and Evaluation Resource
The Family of Diffusion Protein Language Models (DPLM)
OmniSVG is the first family of end-to-end multimodal SVG generators that leverage pre-trained Vision-Language Models (VLMs), capable of generating complex and detailed SVGs, from simple icons to in…
Sidechain conditioning and modeling for full-atom protein sequence design
Compressing protein structures effectively with torsion angles
Proteina is a new large-scale flow-based protein backbone generator that utilizes hierarchical fold class labels for conditioning and relies on a tailored scalable transformer architecture.
[CVPR 2025] Code for Deformable Radial Kernel Splatting
A lightweight, powerful framework for multi-agent workflows
A trainable PyTorch reproduction of AlphaFold 3.
Open-Sora: Democratizing Efficient Video Production for All
SpargeAttention: A training-free sparse attention that can accelerate any model inference.
FlashMLA: Efficient MLA decoding kernels
SchNetPack - Deep Neural Networks for Atomistic Systems
Official implementation of Continuous 3D Perception Model with Persistent State
[NeurIPS 2024] Direct3D: Scalable Image-to-3D Generation via 3D Latent Diffusion Transformer
This is a simple demonstration of more advanced, agentic patterns built on top of the Realtime API.
Diffusion Powers Video Tokenizer for Comprehension and Generation (CVPR 2025)
Unofficial implementation of Titans, SOTA memory for transformers, in Pytorch
[NeurIPS 2024] SCube: Instant Large-Scale Scene Reconstruction using VoxSplats
A PyTorch native platform for training generative AI models
New repo collection for NVIDIA Cosmos: https://github.com/nvidia-cosmos
Implementation for SE(3) diffusion model with application to protein backbone generation
Comprehensive benchmarking of protein-ligand structure prediction methods. (ICML 2024 AI4Science)
A generative world for general-purpose robotics & embodied AI learning.