具身智能入门指南 Embodied-AI-Guide

🧑‍🚀 全世界最好的LLM资料总结（数据处理、模型训练、模型部署、o1 模型、小语言模型、视觉语言模型） | Summary of the world's best LLM resources.

[ICCV'23] Hidden Biases of End-to-End Driving Models

[NeurIPS 2024 Datasets and Benchmarks Track] Closed-Loop E2E-AD Benchmark Enhanced by World Model RL Expert

[NeurIPS 2024] NAVSIM: Data-Driven Non-Reactive Autonomous Vehicle Simulation and Benchmarking

[ICRA 2025] Learning Multiple Probabilistic Decisions from Latent World Model in Autonomous Driving (expert-level performance on Waymax)

Fully open reproduction of DeepSeek-R1

VADv2: End-to-End Vectorized Autonomous Driving via Probabilistic Planning

[NeurIPS'23 Spotlight] Segment Any Point Cloud Sequences by Distilling Vision Foundation Models

🚀 「大模型」3小时从0训练27M参数的视觉多模态VLM！🌏 Train a 27M-parameter VLM from scratch in just 3 hours!

🚀🚀 「大模型」2小时完全从0训练26M的小参数GPT！🌏 Train a 26M-parameter GPT from scratch in just 2h!

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

[NeurIPS 2024]OmniTokenizer: one model and one weight for image-video joint tokenization.

Qwen2.5-VL is the multimodal large language model series developed by Qwen team, Alibaba Cloud.

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

[Survey] Next Token Prediction Towards Multimodal Intelligence: A Comprehensive Survey

[NeurIPS 2024] Behavioral Topology (BeTop), a multi-agent behavior formulation for interactive motion prediction and planning

Code for "Heterogeneous Graph Transformer" (WWW'20), which is based on Deep Graph Library (DGL)

Closed-Loop Supervised Fine-Tuning of Tokenized Traffic Models

Official Github Repo for GEM

VQ-Map[NeurIPS 2024]

A tiny deep learning training framework implemented from scratch in C++ that follows PyTorch's API.

Cosmos is a world model development platform that consists of world foundation models, tokenizers and video processing pipeline to accelerate the development of Physical AI at Robotics & AV labs. C…

[CVPR 2024] A world model for autonomous driving.

A library for advanced large language model reasoning

DeepSeek-V2: A Strong, Economical, and Efficient Mixture-of-Experts Language Model

The official Meta Llama 3 GitHub site

Code for "DrivingWorld: Constructing World Model for Autonomous Driving via Video GPT"