Implementation of the Aurora model for Earth system forecasting

Production-tested AI infrastructure tools for efficient AGI development and community-driven innovation

world modeling challenge for humanoid robots

Hybrid ML + physics model of the Earth's atmosphere

Probabilistic time series modeling in Python

Mamba SSM architecture

Large World Model -- Modeling Text and Video with Millions Context

Unofficial implementation of iTransformer - SOTA Time Series Forecasting using Attention networks, out of Tsinghua / Ant group

Open-source deep-learning framework for building, training, and fine-tuning deep learning models using state-of-the-art Physics-ML methods

A library for scientific machine learning and physics-informed learning

Large-scale Self-supervised Pre-training Across Tasks, Languages, and Modalities

Foundation Architecture for (M)LLMs

[ECCV 2022] This is the official implementation of BEVFormer, a camera-only framework for autonomous driving perception, e.g., 3D object detection and semantic map segmentation.

[CVPR 2023 Best Paper Award] Planning-oriented Autonomous Driving

🤗 PEFT: State-of-the-art Parameter-Efficient Fine-Tuning.

Let us control diffusion models!

百亿参数的中英文双语基座大模型

An Open-Ended Embodied Agent with Large Language Models

A repo for distributed training of language models with Reinforcement Learning via Human Feedback (RLHF)

A modular RL library to fine-tune language models to human preferences

Train transformer language models with reinforcement learning.

Hackable and optimized Transformers building blocks, supporting a composable construction.

Collect awesome best papers from top AI conferences.

The open-source solutions of FourCastNet and GraphCast

清华大学计算机系课程攻略 Guidance for courses in Department of Computer Science and Technology, Tsinghua University