SWE-Bench Pro: Can AI Agents Solve Long-Horizon Software Engineering Tasks?

A model-driven approach to building AI agents in just a few lines of code.

20+ high-performance LLMs with recipes to pretrain, finetune and deploy at scale.

🐍 Python SDK for Hide (Headless IDE)

🤗 Transformers: State-of-the-art Machine Learning for Pytorch, TensorFlow, and JAX.

Odisha in ML GitHub page website.

RobustBench: a standardized adversarial robustness benchmark [NeurIPS'21 Benchmarks and Datasets Track]

Code paper Uncertainty Reduction for Uncertainty Reduction for Model Adaptation in Semantic Segmentation at CVPR 2021

HYPAOBT - HYperParameter-Aware Optimizer Benchmarking Protocol

DeepOBS: A Deep Learning Optimizer Benchmark Suite

Sacred is a tool to help you configure, organize, log and reproduce experiments developed at IDSIA.

Code for <Confidence Regularized Self-Training> in ICCV19 (Oral)

A Keras-like framework and utilities for PyTorch

A state-of-the-art semi-supervised method for image recognition