RAP: 3D Rasterization Augmented End-to-End Planning

Generative World Explorer

[NeurIPS 2024] A Generalizable World Model for Autonomous Driving

[ECCV 2024] DriveDreamer: Towards Real-world-driven World Models for Autonomous Driving

A Curated List of Awesome Works in World Modeling, Aiming to Serve as a One-stop Resource for Researchers, Practitioners, and Enthusiasts Interested in World Modeling.

Native Multimodal Models are World Learners

[arXiv 2025] Generative View Stitching

[NeurIPS 2025] The official repository of "Sekai: A Video Dataset towards World Exploration"

Code release for Ming-UniVision: Joint Image Understanding and Geneation with a Continuous Unified Tokenizer

Codebase of GRPO: Implementations and Resources of GRPO and Its Variants

MMGraphRAG is a multi-modal knowledge graph-based framework designed to enhance complex reasoning tasks, such as multi-modal document question-answering. It integrates text and image data into a fi…

Voyager is an interactive RGBD video generation model conditioned on camera input, and supports real-time 3D reconstruction.

Dexbotic: Open-Source Vision-Language-Action Toolbox

The best ChatGPT that $100 can buy.

dLLM: Simple Diffusion Language Modeling

rCM: SOTA Diffusion Distillation & Few-Step Video Generation

MDPO: Overcoming the Training-Inference Divide of Masked Diffusion Language Models

Thinking with Videos from Open-Source Priors. We reproduce chain-of-frames visual reasoning by fine-tuning open-source video models. Give it a star 🌟 if you find it useful.

DiffuCoder: Understanding and Improving Masked Diffusion Models for Code Generation

Fully open reproduction of DeepSeek-R1

A Python tool that automatically cleans, completes, and standardizes BibTeX entries using LLMs and web search.

LongLive: Real-time Interactive Long Video Generation

[NeurIPS 2025] SURDS: Benchmarking Spatial Understanding and Reasoning in Driving Scenarios with Vision Language Models

ReCogDrive: A Reinforced Cognitive Framework for End-to-End Autonomous Driving

DiffusionNFT: Online Diffusion Reinforcement with Forward Process

Closed-Loop Supervised Fine-Tuning of Tokenized Traffic Models. CVPR Oral 2025.

BranchGRPO: Stable and Efficient GRPO with Structured Branching in Diffusion Models

SDAR (Synergy of Diffusion and AutoRegression), a large diffusion language model（1.7B, 4B, 8B, 30B）

Diffusion on syntax trees for program synthesis