Research map / Vision-language and multimodal / Robot action and navigation
A Dataset for Interactive Vision-Language Navigation with Unknown Command Feasibility
Andrea Burns, Deniz Arsan, Sanjna Agrawal, Ranjitha Kumar, Kate Saenko, Bryan A. Plummer
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 |
|---|---|---|---|
| concatenate demonstration steps instead of averaging (ablation) | CLIP screen-image feasibility MLP · MoTIF feasibility | F1: 44.7 -> 58.2 | Improved |
| add app screen image CLIP features to view hierarchy CLIP features (concat) (ablation) | feasibility MLP · MoTIF feasibility | F1: 50.9 -> 61.1 | Improved |
| replace FastText with CLIP for view hierarchy (concat) (ablation) | feasibility MLP · MoTIF feasibility | F1: 43.6 -> 50.9 | Improved |
| use Screen2Vec instead of CLIP for view hierarchy (concat) (ablation) | feasibility MLP · MoTIF feasibility | F1: 50.9 -> 33.7 | Hurt |
| use averaged icon features instead of CLIP screen image (ablation) | feasibility MLP · MoTIF feasibility (averaged) | F1: 44.7 -> 0.4 | Hurt |
| add view hierarchy to CLIP screen image with LSTM aggregation (ablation) | feasibility MLP · MoTIF feasibility (LSTM) | F1: 42.8 -> 40.9 | Hurt |
| add RicoSCA data to MoTIF training (ablation) | Seq2Seq · MoTIF complete Action+Ground (app seen) | accuracy: 15.9 -> 22.5 | Improved |
| add RicoSCA data to MoTIF training (ablation) | MOCA · MoTIF complete Action+Ground (app seen) | accuracy: 12.3 -> 20.7 | Improved |
| add high-level goal to low-level instruction at test time (ablation) | Seq2Seq · MoTIF complete Action+Ground (app seen) | accuracy: 18.0 -> 22.5 | Improved |
| give only high-level goal at test time instead of low-level instruction (ablation) | Seq2Act · MoTIF complete Action+Ground (app seen) | accuracy: 32.4 -> 7.6 | Hurt |
| give only high-level goal instead of both inputs (ablation) | MOCA · MoTIF complete Action+Ground (app seen) | accuracy: 20.7 -> 8.4 | Hurt |
| test on unseen apps instead of seen apps | Seq2Seq · MoTIF complete Action+Ground | accuracy: 22.5 -> 17.7 | Hurt |
Closest papers by meaning
- AwareVLN: Reasoning with Self-awareness for Vision-Language Navigation (CVPR 2026 · similarity 0.90)
- Scaling, Benchmarking, and Reasoning of Vision-Language Agents for Mobile GUI Navigation (ICML 2026 · similarity 0.89)
- STRIDER: Navigation via Instruction-Aligned Structural Decision Space Optimization (NeurIPS 2025 · similarity 0.88)
- Towards Long-Horizon Vision-Language Navigation: Platform, Benchmark and Method (CVPR 2025 · similarity 0.88)
- NavGPT: Explicit Reasoning in Vision-and-Language Navigation with Large Language Models (AAAI 2024 · similarity 0.88)
- General Scene Adaptation for Vision-and-Language Navigation (ICLR 2025 · 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.
