Normalized cuts for scalable clustering and segmentation, enabling efficient detection of structure in high-dimensional data and learned representations.
Normalized Cut with Nyström approximation, handle large-scale graph with O(n) time complexity, O(1) space complexity. Solve million-scale graph in milliseconds.
A centralized framework for agricultural machine learning.
Platform to design molecules, plan synthesis routes, and optimize chemical processes.
First rigorous benchmark for advancing multimodal dataset creation.
Cyberinfrastructure services for automated data labeling, image segmentation, model serving, and edge deployment, usable across any field.
An interpretable neural network that helps scientists discover mathematical and physical laws
MutateEverything predicts the effect of all single and double protein mutations in one forward pass. It is even versatile enough to predict higher-order mutations with minimal computational overhead.
An open source implementation of OpenAI's CLIP