AddASecond
Follow
Stars
Collect some World Models for Autonomous Driving (and Robotic, etc.) papers.
Wan: Open and Advanced Large-Scale Video Generative Models
Official Code for Epona: Autoregressive Diffusion World Model for Autonomous Driving (ICCV 2025)
[NeurIPS 2025 spotlight] Official implementation for "FutureSightDrive: Thinking Visually with Spatio-Temporal CoT for Autonomous Driving"
Industry-level video foundation model for unified Text-to-Video (T2V) and Image-to-Video (I2V) generation.
[NeurIPS 2025] LangSplatV2: High-dimensional 3D Language Gaussian Splatting with 450+ FPS
A curated list of awesome HD map construction methods
[Information Fusion 2025] A Survey on Occupancy Perception for Autonomous Driving: The Information Fusion Perspective
The simplest, fastest repository for training/finetuning small-sized VLMs.
🚀🚀 「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!
[ICCV 2025] HERMES: A Unified Self-Driving World Model for Simultaneous 3D Scene Understanding and Generation
[CVPR2025] PyTorch-based reimplementation of CrossFlow, as proposed in 'Flowing from Words to Pixels: A Noise-Free Framework for Cross-Modality Evolution'
a comprehensive and critical synthesis of the emerging role of GenAI across the full autonomous driving stack
[🔥updating ...] AI 自动量化交易机器人(完全本地部署) AI-powered Quantitative Investment Research Platform. 📃 online docs: https://ufund-me.github.io/Qbot ✨ :news: qbot-mini: https://github.com/Charmve/iQuant
A 3DGS framework for omni urban scene reconstruction and simulation.
State-of-the-art, simple, fast unbounded / large-scale NeRFs.
text and image to video generation: CogVideoX (2024) and CogVideo (ICLR 2023)
A simple code base for Gaussian Splatting research
Open-source evaluation toolkit of large multi-modality models (LMMs), support 220+ LMMs, 80+ benchmarks
An integration of Segment Anything Model, Molmo, and, Whisper to segment objects using voice and natural language.
主要记录大语言大模型（LLMs） 算法（应用）工程师相关的知识及面试题
using PARL reinforement learning framework with torch to implement SeqGAN(Chinese Poem generation)
A generative world for general-purpose robotics & embodied AI learning.