Use DINOv3’s powerful, self-supervised visual features + YOLOv12’s blazing-fast detection, all in one repo. Whether you have only a few hundred labeled images or a medium-sized dataset, DINOV3-YOLO…

State is a machine learning model that predicts cellular perturbation response across diverse contexts

pytorch dataloaders for single-cell perturbation data

GEARS is a geometric deep learning model that predicts outcomes of novel multi-gene perturbations

Hierarchical Reasoning Model Official Release

High quality visualization for volumetric image data

A PyTorch library for implementing flow matching algorithms, featuring continuous and discrete flow matching implementations. It includes practical examples for both text and image modalities.

Pytorch Implementation (unofficial) of the paper "Mean Flows for One-step Generative Modeling" by Geng et al.

Omnipose: a high-precision solution for morphology-independent cell segmentation

A generative world for general-purpose robotics & embodied AI learning.

SANA: Efficient High-Resolution Image Synthesis with Linear Diffusion Transformer

Sharing both practical insights and theoretical knowledge about LLM evaluation that we gathered while managing the Open LLM Leaderboard and designing lighteval!

A reading list on LLM based Synthetic Data Generation 🔥

PHATE (Potential of Heat-diffusion for Affinity-based Transition Embedding) is a tool for visualizing high dimensional data.

scPortrait is a scalable toolkit to generate single-cell representations from raw microscopy images

Differential expression analysis for single-cell RNA-seq data.

A curated list of awesome resources for FLUX, the state-of-the-art text-to-image model by Black Forest Labs.

Sparsify transformers with SAEs and transcoders

The repository provides code for running inference with the Meta Segment Anything Model 2 (SAM 2), links for downloading the trained model checkpoints, and example notebooks that show how to use th…

Transformer-based cell tracking for live-cell microscopy

Vector (and Scalar) Quantization, in Pytorch

Multiscale earth mover's distance methods for tree and manifold structured data

Creating beautiful plots of data maps

DreamSim: Learning New Dimensions of Human Visual Similarity using Synthetic Data (NeurIPS 2023 Spotlight) / / / / When Does Perceptual Alignment Benefit Vision Representations? (NeurIPS 2024)

Official code for "FeatUp: A Model-Agnostic Frameworkfor Features at Any Resolution" ICLR 2024

Accurate and efficient spot detection for microscopy data

Pre-trained models, data, code & materials from the paper "ImageNet-trained CNNs are biased towards texture; increasing shape bias improves accuracy and robustness" (ICLR 2019 Oral)

LPIPS metric. pip install lpips