mlsanityData to 14 Oct 2026

Proposal-Conditioned Latent Diffusion for Closed-Loop Traffic Scenario Generation

arXiv 2606.27123 ↗First posted 25 Jun 2026cs.RO cs.CVcited by 0

On the map: Diffusion models → Diffusion and flow policies for robotics

Abstract (arXiv)

Closed-loop traffic simulation remains challenging because it must generate interactive multi-agent behaviors that are scene-consistent and controllable throughout rollout. Prior diffusion-based approaches achieve strong realism, but their computational cost can hinder deployment in time-constrained replanning loops for autonomous vehicle planning and simulation. We present a diffusion-based scenario generation framework conditioned on instance-centric scene context and multimodal proposal priors, with optional test-time guidance for shaping safety-critical behaviors. A compact action-latent representation and proposal-based initialization improve sampling efficiency and reduce per-step runtime without retraining. Experiments on the Waymo Open Motion Dataset demonstrate a favorable balance among realism, safety, and controllability across diverse interactive scenarios, while showing that test-time guidance enables systematic trade-offs among competing objectives.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Placed in Diffusion and flow policies for robotics, one of 14 directions in Diffusion models. Builds on 24 of its 32 references that are in the map. First posted on arXiv 25 Jun 2026.

Builds on

24 of 32 references.

Closest ancestors · 4

Same direction, newest first

  1. 2024Optimizing Diffusion Models for Joint Trajectory Prediction and Controllable Generation1 Aug
  2. 2024Intention-aware Denoising Diffusion Model for Trajectory Prediction14 Mar
  3. 2023SAFE-SIM: Safety-Critical Closed-Loop Traffic Simulation with Diffusion-Controllable Adversaries31 Dec
  4. 2022Guided Conditional Diffusion for Controllable Traffic Simulation31 Oct

Other references · 20

  1. 2020Denoising Diffusion Probabilistic Modelscited by 21,076
  2. 2020Denoising Diffusion Implicit Modelscited by 9,781
  3. 2021Diffusion Models Beat GANs on Image Synthesiscited by 8,255
  4. 2022Classifier-Free Diffusion Guidancecited by 5,847
  5. 2022Compositional Visual Generation with Composable Diffusion Modelscited by 624
  6. 2021Large Scale Interactive Motion Forecasting for Autonomous Driving : The Waymo Open Motion Datasetcited by 537
  7. 2023MotionDiffuser: Controllable Multi-Agent Motion Prediction using Diffusioncited by 213
  8. 2021TrafficSim: Learning to Simulate Realistic Multi-Agent Behaviorscited by 193
  9. 2022Stochastic Trajectory Prediction via Motion Indeterminacy Diffusioncited by 185
  10. 2023Waymax: An Accelerated, Data-Driven Simulator for Large-Scale Autonomous Driving Researchcited by 160
  11. 2023GameFormer: Game-theoretic Modeling and Learning of Transformer-based Interactive Prediction and Planning for Autonomous Drivingcited by 141
  12. 2021Generating Useful Accident-Prone Driving Scenarios via a Learned Traffic Priorcited by 139
8 more
  1. 2022TrafficGen: Learning to Generate Diverse and Realistic Traffic Scenarioscited by 106
  2. 2022KING: Generating Safety-Critical Driving Scenarios for Robust Imitation via Kinematics Gradientscited by 96
  3. 2023CAT: Closed-loop Adversarial Training for Safe End-to-End Drivingcited by 54
  4. 2024Versatile Behavior Diffusion for Generalized Traffic Agent Simulationcited by 30
  5. 2024SIMPL: A Simple and Efficient Multi-agent Motion Prediction Baseline for Autonomous Drivingcited by 27
  6. 2023Unsupervised Sampling Promoting for Stochastic Human Trajectory Predictioncited by 17
  7. 2023The 2nd Place Solution for 2023 Waymo Open Sim Agents Challengecited by 6
  8. 2022DeFIX: Detecting and Fixing Failure Scenarios with Reinforcement Learning in Imitation Learning Based Autonomous Drivingcited by 2

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2026One Diffusion Model, Two Roles: Guided Trajectory Planning and Safety-Critical Scenario Generation in Closed-Loop Simulation
  2. 2025Controllable Latent Diffusion for Traffic Simulation
  3. 2025Scenario Dreamer: Vectorized Latent Diffusion for Generating Driving Simulation Environments
  4. 2023Scenario Diffusion: Controllable Driving Scenario Generation With Diffusion
  5. 2025Path Diffuser: Diffusion Model for Data-Driven Traffic Simulator
  6. 2025Rolling Ahead Diffusion for Traffic Scene Simulation
  7. 2023A Diffusion-Model of Joint Interactive Navigation
  8. 2024SceneDiffuser: Efficient and Controllable Driving Simulation Initialization and Rollout