ORB forcefield models from Orbital Materials

The attention heads in the Transformer architecture possess a variety of capabilities. This is a carefully compiled list that summarizes the diverse functions of the attention heads.

ReFT: Representation Finetuning for Language Models

DuckDB-powered Postgres for high performance apps & analytics.

SynDL: A Large-Scale Synthetic Test Collection for Passage Retrieval

Code for reproducting experiments of the PISA paper published at RecSys 2024

An R package implementing the UMAP dimensionality reduction method.

Tutorial on User Profiling with Graph Neural Networks and Related Beyond-Accuracy Perspectives @ UMAP'23

A graph neural network for high-entropy alloys.

(NeurIPS 2022) On Embeddings for Numerical Features in Tabular Deep Learning

papers of universal user representation learning for recommendation

StructuredRAG Benchmarker

Code for paper "W-RAG: Weakly Supervised Dense Retrieval in RAG for Open-domain Question Answering"

RAGLAB: A Modular and Research-Oriented Unified Framework for Retrieval-Augmented Generation

Implementation of the Aurora model for atmospheric forecasting

AI for crystal materials

TxGNN: Zero-shot prediction of therapeutic use with geometric deep learning and clinician centered design

An implementation of the Fermionic Neural Network for ab-initio electronic structure calculations

RefChecker provides automatic checking pipeline and benchmark dataset for detecting fine-grained hallucinations generated by Large Language Models.

Baguetter is a flexible, efficient, and hackable search engine library implemented in Python. It's designed for quickly benchmarking, implementing, and testing new search methods. Baguetter support…

Repository for the figures of "Computing Power and the Governance of AI".

A graph benchmark library for heterophilic and heterogeneous graphs

Serverless Postgres for modern SaaS