A generative world for general-purpose robotics & embodied AI learning.

Official Implementation of Driv3R

GPD-1: Generative Pre-training for Driving

Stag-1: Towards Realistic 4D Driving Simulation with Video Generation Model

[ECCV 2024] 3D World Model for Autonomous Driving

[ECCV 2024] Scene as Gaussians for Vision-Based 3D Semantic Occupancy Prediction

Doe-1: Closed-Loop Autonomous Driving with Large World Model

[arXiv'24] Align3R: Aligned Monocular Depth Estimation for Dynamic Videos

Closed-Loop Supervised Fine-Tuning of Tokenized Traffic Models

NOVA: Autoregressive Video Generation without Vector Quantization

Real-time dense scene reconstruction with SLAM3R

GaussianAD: Gaussian-Centric End-to-End Autonomous Driving

Large Driving Models

Large Reasoning Models

Educational framework exploring ergonomic, lightweight multi-agent orchestration. Managed by OpenAI Solution team.

O1 Replication Journey: A Strategic Progress Report – Part I

my large scale models learning log(我的大模型学习记录,包括langchain之类的放在一起)

该仓库主要记录 大模型（LLMs） 算法工程师相关的面试题

[ICLR 2023] ReAct: Synergizing Reasoning and Acting in Language Models

[ECCV 2024] Asynchronous Large Language Model Enhanced Planner for Autonomous Driving

An Easy-to-use, Scalable and High-performance RLHF Framework (70B+ PPO Full Tuning & Iterative DPO & LoRA & RingAttention & RFT)

A 3DGS framework for omni urban scene reconstruction and simulation.

GLM-4 series: Open Multilingual Multimodal Chat LMs | 开源多语言多模态对话模型

[Embodied-AI-Survey-2024] Paper list and projects for Embodied AI

Official implementation of the Law of Vision Representation in MLLMs