Research map / Vision-language and multimodal / Robot action and navigation
ProFocus: Proactive Perception and Focused Reasoning in Vision-and-Language Navigation
Wei Xue, Mingcheng Li, Xuecheng Wu, Jingqun Tang, Dingkang Yang, Lihua Zhang
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 proactive perception (ablation) | ProFocus (DS3+GLM) · R2R val unseen | SPL: 30.0 -> 41.2 | Improved |
| add proactive perception (ablation) | ProFocus (Q3+Q3VL) · R2R val unseen | SPL: 34.4 -> 39.8 | Improved |
| add proactive perception (ablation) | ProFocus (Q3+Q3VL) · REVERIE val unseen | OSR: 34.0 -> 51.67 | Improved |
| add BD-MCTS focused reasoning (ablation) | ProFocus (DS3+GLM) · R2R val unseen | OSR: 54.2 -> 63.0 | Improved |
| add BD-MCTS focused reasoning (ablation) | ProFocus (DS3+GLM) · REVERIE val unseen | OSR: 42.67 -> 57.14 | Improved |
| add BD-MCTS focused reasoning (ablation) | ProFocus (Q3+Q3VL) · REVERIE val unseen | SPL: 27.37 -> 24.83 | Hurt |
| add BD-MCTS focused reasoning (ablation) | ProFocus (DS3+GLM) · R2R val unseen | SR: 46.9 -> 50.0 | Improved |
| ProFocus vs MapGPT with same backbone | ProFocus (DS3+GLM) · REVERIE val unseen | SR: 37.1 -> 36.9 | No clear effect |
| ProFocus vs NavGPT with Qwen3-Max | ProFocus (Q3+Q3VL) · REVERIE val unseen | SR: 18.0 -> 40.0 | Improved |
| ProFocus vs MapGPT on long trajectories | ProFocus (Q3+Q3VL) · R2R 30 longest episodes | SR: 40.0 -> 50.0 | Improved |
Closest papers by meaning
- Aux-Think: Exploring Reasoning Strategies for Data-Efficient Vision-Language Navigation (NeurIPS 2025 · similarity 0.88)
- NavGPT: Explicit Reasoning in Vision-and-Language Navigation with Large Language Models (AAAI 2024 · similarity 0.88)
- Run, Ruminate, and Regulate: A Dual-process Thinking System for Vision-and-Language Navigation (AAAI 2026 · similarity 0.87)
- FantasyVLN: Unified Multimodal Chain-of-Thought Reasoning for Vision-and-Language Navigation (CVPR 2026 · similarity 0.87)
- BeliefMapNav: 3D Voxel-Based Belief Map for Zero-Shot Object Navigation (NeurIPS 2025 · similarity 0.87)
- RAO-Nav: Probing Omni-Language Models for Zero-shot Semantic Audio-Visual Navigation (NeurIPS 2026 · similarity 0.87)
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.
