Research map / Probabilistic and scientific modeling / Causal discovery
Layout-Based Causal Inference for Object Navigation
Read the paperCheck your idea against 108,967 papers
AI-extracted summary. Written by AI from the paper's title only (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 |
|---|---|---|---|
| Apply L-sTDE to VTNet | VTNet · AI2THOR | SR (%): 70.10 -> 75.25; +5.15 | Helped |
| Apply L-sTDE to VTNet | VTNet · AI2THOR | SPL (%): 39.60 -> 41.69; +2.09 | Helped |
| Apply L-sTDE to VTNet | VTNet · AI2THOR | DTS (m): 0.52 -> 0.47; 0.05↑ | Helped |
| Apply L-sTDE to HOZ | HOZ · RoboTHOR | SR (%): 32.27 -> 42.13; +9.86 | Helped |
| Apply L-sTDE to HOZ | HOZ · RoboTHOR | SPL (%): 20.48 -> 24.54; +4.06 | Helped |
| Apply L-sTDE to HOZ | HOZ · RoboTHOR | DTS (m): 1.85 -> 1.67; 0.18↑ | Helped |
| Apply L-sTDE to SemExp | SemExp · Gibson | SR (%): 65.35 -> 66.96; +1.61 | Helped |
| Apply L-sTDE to SemExp | SemExp · Gibson | SPL (%): 33.52 -> 34.33; +0.81 | Helped |
| Apply L-sTDE to SemExp | SemExp · Gibson | DTS (m): 1.56 -> 1.53; 0.03↑ | Helped |
| Add posterior layout expectation wt (ablation) | ORG · AI2THOR validation | SR (%): 66.48 -> 71.40 | Helped |
| Add sTDE debiasing based on layout gap (ablation) | ORG + wt · AI2THOR validation | SR (%): 71.40 -> 74.95 | Helped |
| Replace sTDE with full TDE (ablation) | ORG + wt · AI2THOR validation | SR (%): 71.40 -> 69.24 | Hurt |
Closest papers by meaning
- Vision-and-Language Navigation via Causal Learning (CVPR 2024 · similarity 0.85)
- Reasoning in Visual Navigation of End-to-end Trained Agents: A Dynamical Systems Approach (CVPR 2025 · similarity 0.85)
- CausalSpatial: A Benchmark for Object-Centric Causal Spatial Reasoning (NeurIPS 2026 · similarity 0.84)
- Aux-Think: Exploring Reasoning Strategies for Data-Efficient Vision-Language Navigation (NeurIPS 2025 · similarity 0.84)
- Imagine Before Go: Self-Supervised Generative Map for Object Goal Navigation (CVPR 2024 · similarity 0.84)
- Trajectory Diffusion for ObjectGoal Navigation (NeurIPS 2024 · similarity 0.84)
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.