Research map / Video / Video generation
Pondering the Way: Spatial-perceiving World Action Model for Embodied Navigation
Hong Chen, Daqi Liu, Zehan Zhang, Haiguang Wang, Tianhao Lu, Longfei Yan, Haiyang Sun, Fangzhen Li, Hongwei Xie, Bing Wang, Guang Chen, Hangjun Ye and 1 more
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 |
|---|---|---|---|
| add depth modality (ablation) | CogVideoX joint baseline · RECON | ATE: 2.09 -> 1.70 | Improved |
| add depth modality (ablation) | CogVideoX joint baseline · TartanDrive | ATE: 4.90 -> 4.61 | Improved |
| add depth modality (ablation) | CogVideoX joint baseline · SCAND | RPE: 0.67 -> 0.51 | Improved |
| add depth modality (ablation) | CogVideoX joint baseline · SCAND | ATE: 2.25 -> 2.27 | No clear effect |
| add trajectory-scale regularization (ablation) | CogVideoX joint baseline · TartanDrive | ATE: 4.90 -> 2.63 | Improved |
| add trajectory-scale regularization (ablation) | CogVideoX joint baseline · SCAND | ATE: 2.25 -> 1.63 | Improved |
| add trajectory-scale regularization (ablation) | CogVideoX joint baseline · RECON | ATE: 2.09 -> 2.06 | No clear effect |
| add TSR on top of depth (ablation) | SWAM · RECON | ATE: 1.70 -> 1.01 | Improved |
| add visual-guided action refinement (ablation) | SWAM · TartanDrive | ATE: 1.94 -> 1.55 | Improved |
| add visual-guided action refinement (ablation) | SWAM · TartanDrive | RPE: 0.53 -> 0.68 | Hurt |
| add visual-guided action refinement (ablation) | SWAM · SCAND | ATE: 1.12 -> 1.15 | Hurt |
| replace NWM+NoMaD x16 candidate ranking with joint generation | SWAM · RECON | inference time: 245.98 -> 16.91 | Improved |
Closest papers by meaning
- Image2Sim: Scaling Embodied Navigation via Generative Neural Simulator (NeurIPS 2026 · similarity 0.90)
- DriveDreamer-Policy: A Geometry-Grounded World-Action Model for Unified Generation and Planning (NeurIPS 2026 · similarity 0.89)
- Navigation World Models (CVPR 2025 · similarity 0.89)
- DINO-WM: World Models on Pre-trained Visual Features enable Zero-shot Planning (ICML 2025 · similarity 0.88)
- EA-WM: Event-Aware Generative World Model with Structured Kinematic-to-Visual Action Fields (NeurIPS 2026 · similarity 0.88)
- World–Value–Action Model: Implicit Planning for Vision–Language–Action Systems (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.
