Research map / Vision-language and multimodal / Robot action and navigation
ScenarioControl: Vision-language Controllable Vectorized Latent Scenario Generation
Lili Gao, Yanbo Xu, William Koch, Samuele Ruffino, Luke Rowe, Behdad Chalaki, Dmitriy Rivkin, Julian Ost, Roger Girgis, Mario Bijelic, Felix Heide
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 |
|---|---|---|---|
| Use cross-global control instead of concatenation (ablation) | ScenarioControl (image) · nuPlan | collision rate: 30.18 -> 17.07 | Improved |
| Use cross-global control instead of full cross-attention (ablation) | ScenarioControl (image) · nuPlan | agent AP: 32.00 -> 33.46 | Improved |
| Use full cross-attention instead of cross-global control (collision rate) (ablation) | ScenarioControl (image) · nuPlan | collision rate: 16.07 -> 17.07 | Improved |
| Use attention-based conditioning instead of concatenation (ablation) | ScenarioControl (prompt) · nuPlan | agent control CSC: 0.1340 -> 0.1626 | Improved |
| Use windowed attention instead of cross-global control (ablation) | ScenarioControl (prompt) · nuPlan | agent AP: 23.36 -> 5.55 | Hurt |
| Add collision loss (ablation) | ScenarioControl · nuPlan test subset | collision rate: 19.81 -> 14.07 | Improved |
| Add f_count count prediction (ablation) | ScenarioControl · nuPlan test subset | collision rate / AP: 19.81 -> 18.78 collision; AP 39.55 -> 38.70 | Mixed |
| Use ScenarioControl instead of Scenario Dreamer, nuPlan image | ScenarioControl · nuPlan | agent control CSC: 0.0623 -> 0.2255 | Improved |
| Use ScenarioControl instead of Scenario Dreamer, Waymo | ScenarioControl · Waymo Motion | lane control CSC: 0.2128 -> 0.5179 | Improved |
| Condition on text prompt for agent placement vs TrafficGen | ScenarioControl · Waymo Open Motion | agent AP: 5.5 -> 26.8 | Improved |
Closest papers by meaning
- Scenario Dreamer: Vectorized Latent Diffusion for Generating Driving Simulation Environments (CVPR 2025 · similarity 0.89)
- Generative Scenario Rollouts for End-to-End Autonomous Driving (NeurIPS 2026 · similarity 0.89)
- Generating Multimodal Driving Scenes via Next-Scene Prediction (CVPR 2025 · similarity 0.89)
- FutureSightDrive: Thinking Visually with Spatio-Temporal CoT for Autonomous Driving (NeurIPS 2025 · similarity 0.88)
- SGDrive: Scene-to-Goal Hierarchical World Cognition for Autonomous Driving (CVPR 2026 · similarity 0.88)
- Less Language, More Latents: Annotation-Efficient VLAs for Driving (NeurIPS 2026 · similarity 0.88)
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.
