Research map / Image generation / Fast diffusion sampling
A Diffusion-Model of Joint Interactive Navigation
Matthew Niedoba, Jonathan Wilder Lavington, Yunpeng Liu, Vasileios Lioutas, Justice Sefas, Xiaoxuan Liang, Dylan Green, Setareh Dabiri, Berend Zwartsenberg, Adam Scibior, Frank Wood
Read the paperCheck your idea against 137,217 papers
AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Measured effects reported in the paper
| What was changed | Where | Measured | Effect |
|---|---|---|---|
| Generate the full joint scene with DJINN rather than Scene Transformer (Joint) | Argoverse validation set · Argoverse validation set | minSceneADE_6: 1.019 -> 0.895 | Improved |
| Use DJINN rather than Scene Transformer (Joint) | Argoverse validation set · Argoverse validation set | minADE_6: 0.848 -> 0.871 | Hurt |
| Train on a mixture of observation masks instead of only the predictive task (ablation) | DJINN · INTERACTION validation set | minADE: 0.21 -> 0.26 | Hurt |
| Train on a mixture of observation masks instead of only the predictive task (ablation) | DJINN · INTERACTION validation set | MFD: 2.33 -> 3.11 | Improved |
| Reduce sampling from 50 to 10 diffusion steps (ablation) | DJINN · INTERACTION validation set | minADE: 0.21 -> 0.28 | Hurt |
| Reduce sampling from 50 to 20 diffusion steps (ablation) | DJINN · INTERACTION validation set | minADE: 0.21 -> 0.22 | Hurt |
| Reduce sampling from 50 to 30 diffusion steps (ablation) | DJINN · INTERACTION validation set | minADE: 0.21 -> 0.22 | No clear effect |
| Reduce sampling from 50 to 40 diffusion steps (ablation) | DJINN · INTERACTION validation set | minADE: 0.21 -> 0.21 | No clear effect |
Closest papers by meaning
- Trajeglish: Traffic Modeling as Next-Token Prediction (ICLR 2024 · similarity 0.88)
- BehaviorGPT: Smart Agent Simulation for Autonomous Driving with Next-Patch Prediction (NeurIPS 2024 · similarity 0.88)
- DeMo: Decoupling Motion Forecasting into Directional Intentions and Dynamic States (NeurIPS 2024 · similarity 0.87)
- Flow Matching-Based Autonomous Driving Planning with Advanced Interactive Behavior Modeling (NeurIPS 2025 · similarity 0.87)
- Scenario Dreamer: Vectorized Latent Diffusion for Generating Driving Simulation Environments (CVPR 2025 · similarity 0.87)
- Future-Aware End-to-End Driving: Bidirectional Modeling of Trajectory Planning and Scene Evolution (NeurIPS 2025 · similarity 0.87)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.
