snap-stanford

Biomni: a general-purpose biomedical AI agent

Stanford Network Analysis Platform (SNAP) is a general purpose network analysis and graph mining library.

Benchmark datasets, data loaders, and evaluators for graph machine learning

Platform for designing and evaluating Graph Neural Networks (GNN)

Strategies for Pre-training Graph Neural Networks

🦍 Memorilla: Latent Semantic Memory for LLMs

Python library assists deep learning on graphs

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

UCE is a zero-shot foundation model for single-cell gene expression data

(NeurIPS D&B 2024) STaRK: Benchmarking LLM Retrieval on Textual and Relational Knowledge Bases

CS224W Course Notes

SNAP Python code, SWIG related files

Multi-Hop Logical Reasoning in Knowledge Graphs

Automated Hypothesis Testing with Agentic Sequential Falsifications

[ICLR 2022 spotlight]GreaseLM: Graph REASoning Enhanced Language Models for Question Answering

Distance Encoding for GNN Design

Graph Information Bottleneck (GIB) for learning minimal sufficient structural and feature information using GNNs

BioDiscoveryAgent is an LLM-based AI agent for closed-loop design of genetic perturbation experiments

Discovering novel cell types across heterogenous single-cell experiments

[ICLR 2021] Concept Learners for Few-Shot Learning

[ICLR 2022] Open-World Semi-Supervised Learning

Uncertainty Quantification over Graph with Conformalized Graph Neural Networks (NeurIPS 2023)

Relational Graph Transformer

(ICLR 2026) Optimas: Optimizing Compound AI Systems

KGWAS: novel genetics discovery enabled by massive functional genomics knowledge graph