Lune

CVPR Findings2026

MDG: Masked Denoising Generation for Multi-Agent Behavior Modeling in Traffic Environments

Zhiyu Huang, Zewei Zhou, Tianhui Cai, Yun Zhang, Jiaqi Ma

Abstract

Modeling realistic and interactive multi-agent behavior is critical to autonomous driving and traffic simulation. However, existing diffusion and autoregressive approaches are limited by iterative sampling, sequential decoding, or taskspecific designs, which hinder efficiency and reuse. We propose Masked Denoising Generation (MDG), a unified generative framework that reformulates multi-agent behavior modeling as the reconstruction of independently noised spatiotemporal tensors. Instead of relying on diffusion time steps or discrete tokenization, MDG applies continuous, per-agent and per-timestep noise masks that enable localized denoising and controllable trajectory generation in a single or few forward passes. This mask-driven formulation generalizes across open-loop prediction, closed-loop simulation, motion planning, and conditional generation within one model. Trained on large-scale real-world driving datasets, MDG achieves competitive closed-loop performance on the Waymo Sim Agents and nuPlan Planning benchmarks, while providing efficient, consistent, and controllable multi-agent trajectory generation. These results position MDG as a simple yet versatile paradigm for multiagent behavior modeling.

Ask Lune

Know this paper in minutes, not an afternoon.

Lune can read every page of it and the top-tier papers that cite it, and gives you its claims, its evidence and its limits, each one cited to the paper it comes from. No skimming, no AI slop.

Questions to start from

Lune can draw on

the full paper · related work

Get the answer

Free to start. No credit card required.

Lineage

  • Directly Denoising Diffusion Models cites Denoising Diffusion Probabilistic Models
  • Simple and Effective Masked Diffusion Language Models cites Denoising Diffusion Probabilistic Models
Builds onCited byLeft to right by year; the more cited, the higher.

Builds on31

  1. Denoising Diffusion Probabilistic ModelsJonathan Ho, Ajay Jain, Pieter AbbeelNeurIPS 2020 · 35,902 citations
  2. Directly Denoising Diffusion ModelsDan Zhang, Jingjing Wang, Feng LuoICML 2024 · 11,724 citations
  3. MLP-Mixer: An all-MLP Architecture for VisionIlya O. Tolstikhin, Neil Houlsby, Alexander Kolesnikov, Lucas Beyer et al.NeurIPS 2021 · 3,862 citations
  4. Simple and Effective Masked Diffusion Language ModelsSubham S. Sahoo, Marianne Arriola, Yair Schiff, Aaron Gokaslan et al.NeurIPS 2024 · 929 citations
  5. Large Scale Interactive Motion Forecasting for Autonomous Driving : The Waymo Open Motion DatasetScott Ettinger, Shuyang Cheng, Benjamin Caine, Chenxi Liu et al.ICCV 2021 · 817 citations

Related papers

  1. Decoupled Diffusion Sparks Adaptive Scene GenerationYunsong Zhou, Naisheng Ye, William Ljungbergh, Tianyu Li et al.ICCV 2025 · 2 citations
  2. A Diffusion-Model of Joint Interactive NavigationMatthew Niedoba, Jonathan Wilder Lavington, Yunpeng Liu, Vasileios Lioutas et al.NeurIPS 2023 · 27 citations
  3. SceneDiffuser: Efficient and Controllable Driving Simulation Initialization and RolloutChiyu Max Jiang, Yijing Bai, Andre Cornman, Christopher Davis et al.NeurIPS 2024 · 76 citations
  4. BehaviorGPT: Smart Agent Simulation for Autonomous Driving with Next-Patch PredictionZikang Zhou, Haibo Hu, Xinhong Chen, Jianping Wang et al.NeurIPS 2024 · 73 citations
  5. PlannerRFT: Reinforcing Diffusion Planners through Closed-Loop and Sample-Efficient Fine-TuningHongchen Li, Tianyu Li, Jiazhi Yang, Mingyang Shang et al.CVPR 2026 · 13 citations
Dusk over the sea between two cliffs drawn in fine vertical lines