Research map / Vision-language and multimodal / Robot action and navigation
Chain-of-Search: Parameter-Efficient Reasoning for Zero-Shot Object Navigation
Hanrui Chen, Liqi Yan, Qifan Wang, Jianhui Zhang, Fangli Guan, Pan Li
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 semantic map (ablation) | CoS · HM3D | SR (%): 53.15 -> 55.90 | Improved |
| add cost map (ablation) | CoS · HM3D | SR (%): 54.50 -> 55.90 | Improved |
| add confidence map instead of averaging (ablation) | CoS · HM3D | SR (%): 54.85 -> 55.90 | Improved |
| add RDV VQA confirmation module (ablation) | CoS · HM3D | NE (%): 18.70 -> 10.10 | Improved |
| add RDV VQA confirmation module (ablation) | CoS · HM3D | SPL (%): 29.75 -> 29.06 | Hurt |
| add RDV VQA confirmation module (ablation) | CoS · HM3D | SR (%): 52.35 -> 55.90 | Improved |
| use lightweight PEIA instead of BLIP2 OPT (ablation) | CoS · HM3D | SR (%): 55.25 -> 55.90 | Improved |
| use lightweight PEIA instead of BLIP2 OPT (ablation) | CoS · HM3D | SPL (%): 30.31 -> 29.06 | Hurt |
| add discrete-prompt pre-training of PEIA (ablation) | CoS · HM3D | SR (%): 53.35 -> 55.90 | Improved |
| add fine-tuning stage of PEIA (ablation) | CoS · HM3D | SR (%): 55.60 -> 55.90 | No clear effect |
| CoS vs VLFM on SPL | zero-shot navigation · HM3D | SPL (%): 30.4 -> 29.1 | Hurt |
| CoS vs best zero-shot baselines on MP3D SR | zero-shot navigation · MP3D | SR (%): 41.0 (UniGoal) vs 37.6 (CoS) | Mixed |
Earlier methods this paper compares with
Named baselines from earlier accepted papers in this paper's results tables: better than 2 of 2 on most shared results.
- ImagineNav — ImagineNav: Prompting Vision-Language Models as Embodied Navigator through Scene Imagination (ICLR 2025) · better on 2 of 2 shared results
- VoroNav — VoroNav: Voronoi-based Zero-shot Object Navigation with Large Language Model (ICML 2024) · better on 2 of 2 shared results
Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.
Closest papers by meaning
- BeliefMapNav: 3D Voxel-Based Belief Map for Zero-Shot Object Navigation (NeurIPS 2025 · similarity 0.91)
- FantasyVLN: Unified Multimodal Chain-of-Thought Reasoning for Vision-and-Language Navigation (CVPR 2026 · similarity 0.90)
- Hierarchical Semantic-Augmented Navigation: Optimal Transport and Graph-Driven Reasoning for Vision-Language Navigation (NeurIPS 2025 · similarity 0.90)
- NavGPT: Explicit Reasoning in Vision-and-Language Navigation with Large Language Models (AAAI 2024 · similarity 0.90)
- Enhancing Multi-Robot Semantic Navigation Through Multimodal Chain-of-Thought Score Collaboration (AAAI 2025 · similarity 0.89)
- RAO-Nav: Probing Omni-Language Models for Zero-shot Semantic Audio-Visual Navigation (NeurIPS 2026 · similarity 0.89)
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.
