Starred repositories
LiteRT, successor to TensorFlow Lite. is Google's On-device framework for high-performance ML & GenAI deployment on edge platforms, via efficient conversion, runtime, and optimization
[ICLR 2026] DiffVax: Optimization-Free Image Immunization Against Diffusion-Based Editing
Extremely fast Query Engine for DataFrames, written in Rust
[ICLR 2024] Official implementation of " 🦙 Time-LLM: Time Series Forecasting by Reprogramming Large Language Models"
Unified Schema-Based Information Extraction
Generalist and Lightweight Model for Named Entity Recognition (Extract any entity types from texts)
Improves interoperability between systems (i.e. devices, platforms, apps, databases) by exchanging data based on their semantics
a protocol to poll social-media users unobtrusively and inexpensively using multimodal Large Language Models (LLMs)
Cute dependency injection (DI) framework for Python with agreeable API and everything you need
TimesFM (Time Series Foundation Model) is a pretrained time-series foundation model developed by Google Research for time-series forecasting.
PyTorch Lightning + Hydra. A very user-friendly template for ML experimentation. ⚡🔥⚡
Decoupled Weight Decay Regularization (ICLR 2019)
A LaTeX class for producing presentations and slides
Prioritizing Copy Number Variants (CNV) using Phenotype and Gene Functional Similarity
mOWL: Machine Learning library with Ontologies
The official repository for the gem5 computer-system architecture simulator.
🚀 The Fastest Chunker in the West 🇺🇸 Upto 1TB/s "semantic" chunking, quick and easy!
The repository for the paper "Graph Neural Networks Improve Quantized Transformers by Incorporating Global Structural Relationships".
Collection of common code that's shared among different research projects in FAIR computer vision team.
A fast type checker and language server for Python
This is an official implementation of "ModernTCN: A Modern Pure Convolution Structure for General Time Series Analysis" (ICLR 2024 Spotlight), https://openreview.net/forum?id=vpJMJerXHU