Research map / Vision-language and multimodal / Robot action and navigation
Generative Language-Grounded Policy in Vision-and-Language Navigation with Bayes' Rule
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 |
|---|---|---|---|
| Use the generative instead of discriminative policy | VLN policy · R2R validation-unseen | SR: 0.380 -> 0.434 | Helped |
| Use the generative instead of discriminative policy | VLN policy · R2R validation-unseen | SPL: 0.335 -> 0.371 | Helped |
| Add augmented training data (ablation) | Generative Policy · R2R validation-unseen | SR: 0.434 -> 0.476 | Helped |
| Add augmented training data (ablation) | Discriminative Policy · R2R validation-unseen | SR: 0.380 -> 0.431 | Helped |
| Combine the augmented generative and discriminative policies (ablation) | R2R navigation policy · R2R validation-unseen | SR: 0.476 -> 0.489 | Helped |
| Add FAST backtracking to the combined policy (ablation) | Generative+Discriminative Policy · R2R validation-unseen | SR: 0.489 -> 0.518 | Helped |
| Add FAST backtracking to the combined policy (ablation) | Generative+Discriminative Policy · R2R validation-unseen | SPL: 0.437 -> 0.439 | No clear effect |
| Use generative rather than discriminative parameterization | VLN policy · R4R validation-unseen | CLS: 0.446 -> 0.479 | Helped |
| Train the generative policy with fidelity-oriented rather than supervised learning (ablation) | Generative Policy · R4R validation-unseen | SDTW: 0.121 -> 0.162 | Helped |
| Use the generative instead of discriminative policy | VLN policy without augmentation · R4R validation-unseen | CLS: 0.385 -> 0.471 | Helped |
Closest papers by meaning
- A New Path: Scaling Vision-and-Language Navigation With Synthetic Instructions and Imitation Learning (CVPR 2023 · similarity 0.91)
- General Scene Adaptation for Vision-and-Language Navigation (ICLR 2025 · similarity 0.90)
- Human-Aware Vision-and-Language Navigation: Bridging Simulation to Reality with Dynamic Human Interactions (NeurIPS 2024 · similarity 0.89)
- Vision-Language Navigation with Energy-Based Policy (NeurIPS 2024 · similarity 0.88)
- World–Value–Action Model: Implicit Planning for Vision–Language–Action Systems (NeurIPS 2026 · similarity 0.88)
- Bridging Environments and Language with Rendering Functions and Vision-Language Models (ICML 2024 · 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.