Research map / Vision-language and multimodal / Robot action and navigation
TopV-Nav: Unlocking the Top-View Spatial Reasoning Potential of MLLM for Zero-Shot Object Navigation
Linqing Zhong, Chen Gao, Zihan Ding, Yue Liao, Huimin Ma, Shifeng Zhang, Xu Zhou, Si Liu
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 AVPG top-view map reasoning with MLLM to the LLM-only baseline (ablation) | LLM-based baseline · HM3D (ablation subset) | SR: 45.0 -> 49.0 | Improved |
| add AVPG top-view map reasoning with MLLM to the LLM-only baseline (ablation) | LLM-based baseline · HM3D (ablation subset) | SPL: 25.44 -> 28.07 | Improved |
| add Dynamic Map Scaling (ablation) | TopV-Nav with AVPG · HM3D (ablation subset) | SR: 49.0 -> 50.0 | Improved |
| add Dynamic Map Scaling (ablation) | TopV-Nav with AVPG · HM3D (ablation subset) | SPL: 28.07 -> 27.16 | Hurt |
| add Potential Target Driven mechanism (ablation) | TopV-Nav with AVPG and DMS · HM3D (ablation subset) | SR: 50.0 -> 52.0 | Improved |
| add Potential Target Driven mechanism (ablation) | TopV-Nav with AVPG and DMS · HM3D (ablation subset) | SPL: 27.16 -> 28.73 | Improved |
| add text-boxes visual prompt for objects (ablation) | TopV-Nav AVPG · HM3D (ablation subset) | SR: 45.0 -> 52.0 | Improved |
| add coordinate grid visual prompt (ablation) | TopV-Nav AVPG · HM3D (ablation subset) | SR: 46.0 -> 52.0 | Improved |
| add obstacle visual prompt (ablation) | TopV-Nav AVPG · HM3D (ablation subset) | SR: 49.0 -> 52.0 | Improved |
| add history traversed-area visual prompt (ablation) | TopV-Nav AVPG · HM3D (ablation subset) | SR: 51.0 -> 52.0 | Improved |
| add Gaussian probability fusion instead of selecting max-probability point (ablation) | TopV-Nav PTD · HM3D (ablation subset) | SR: 50.0 -> 52.0 | Improved |
| set beta to 0.5 instead of 0.4 or 0.6 in Gaussian fusion (ablation) | TopV-Nav PTD · HM3D (ablation subset) | SR: 52.0 -> 52.0 (beta 0.4 vs 0.5), 51.0 at beta 0.6 | Improved |
Earlier methods this paper compares with
Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 on most 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 0.89)
- NavGPT: Explicit Reasoning in Vision-and-Language Navigation with Large Language Models (AAAI 2024 · similarity 0.88)
- SG-Nav: Online 3D Scene Graph Prompting for LLM-based Zero-shot Object Navigation (NeurIPS 2024 · similarity 0.87)
- MindJourney: Test-Time Scaling with World Models for Spatial Reasoning (NeurIPS 2025 · similarity 0.87)
- RAO-Nav: Probing Omni-Language Models for Zero-shot Semantic Audio-Visual Navigation (NeurIPS 2026 · similarity 0.87)
- ImagineNav: Prompting Vision-Language Models as Embodied Navigator through Scene Imagination (ICLR 2025 · 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.
