Compress tool outputs, logs, files, and RAG chunks before they reach the LLM. 60-95% fewer tokens, same answers. Library, proxy, MCP server.

VitaminP: a vision transformer-assisted multimodal integration network for pathology cell segmentation

Highly accurate prediction of single-cell spatial transcriptomics from histology images

Haiku: Linking Spatial Biology and Clinical Histology via Tri-Modal Contrastive Learning

A parameter-efficient mixture-of-experts module for computational pathology - ICLR

AI agents running research on single-GPU nanochat training automatically

Semantica 🧠 — AI-native knowledge graph intelligence framework for semantic retrieval, ontology reasoning, context graphs, and explainable AI systems.

Decoupling common and unique representations for multimodal self-supervised learning

A Co-evolving Agentic AI System for Medical Imaging Analysis

The absolute trainer to light up AI agents.

Biomni: a general-purpose biomedical AI agent

Multimodal prototyping for cancer survival prediction - ICML 2024

Refine high-quality datasets and visual AI models

Feather - Lightweight supervised slide foundation models (ICML 2025)

An index of algorithms for offline reinforcement learning (offline-rl)

High-Resolution Image Synthesis with Latent Diffusion Models

Mapping between FinnGen phenotypes and Pan-UKBB phenotypes

Simple, unified interface to multiple Generative AI providers

Incorporating hierarchical information into MIL for patient phenotype prediction with scRNA-seq data

Scaffold decoration and fragment linking with chemical language models and RL

ScaffoldGVAE: A Variational Autoencoder Based on Multi-View Graph Neural Networks for Scaffold Generation and Scaffold Hopping of Drug Molecules

Toolkit for large-scale whole-slide image processing.

Arc Virtual Cell Atlas

Pathology Language and Image Pre-Training (PLIP) is the first vision and language foundation model for Pathology AI (Nature Medicine). PLIP is a large-scale pre-trained model that can be used to ex…