The code of our work "Golden Noise for Diffusion Models: A Learning Framework".

Revisit Mixture Models for Multi-Agent Simulation: Experimental Study within a Unified Framework

collection of diffusion model papers categorized by their subareas

A collection of resources and papers on Diffusion Models

Official code for "DPM-Solver: A Fast ODE Solver for Diffusion Probabilistic Model Sampling in Around 10 Steps" (Neurips 2022 Oral)

[ICLR 2025 Oral] The official implementation of "Diffusion-Based Planning for Autonomous Driving with Flexible Guidance"

Diffusion model papers, survey, and taxonomy

A PyTorch library for implementing flow matching algorithms, featuring continuous and discrete flow matching implementations. It includes practical examples for both text and image modalities.

[Information Fusion 2025] A Survey on Occupancy Perception for Autonomous Driving: The Information Fusion Perspective

GPD-1: Generative Pre-training for Driving

Closed-Loop Supervised Fine-Tuning of Tokenized Traffic Models

Bridging Large Vision-Language Models and End-to-End Autonomous Driving

VBD: Versatile Behavior Diffusion for Generalized Traffic Agent Simulation

Multimodal Whole Slide Foundation Model for Pathology

An open source implementation of CLIP.

Truncated Diffusion Model for Real-Time End-to-End Autonomous Driving

PyTriton is a Flask/FastAPI-like interface that simplifies Triton's deployment in Python environments.

ZIM: Zero-Shot Image Matting for Anything

Benchmark for studying the imitation gap when training autonomous driving policies from human demonstrations

Flickr-Faces-HQ Dataset (FFHQ)

DualAD: Dual-Layer Planning for Reasoning in Autonomous Driving

Introduce Multiscope Conception to Sequential Descision Learning

Controllable Hair Editing (ECCV 2022)

A large-scale face dataset for hair segmentation, hair recognition, and GANs for hair generation and editing.

[CoRL 2024] The official code for paper "Promptable Closed-loop Traffic Simulation"

[NeurIPS 2024] DrivingDojo Dataset: Advancing Interactive and Knowledge-Enriched Driving World Model

[CoRL 2024 Oral] FREA: Feasibility-Guided Generation of Safety-Critical Scenarios with Reasonable Adversariality

[NeurIPS 2024] DeMo: Decoupling Motion Forecasting into Directional Intentions and Dynamic States