- Rating
- 3
- Confidence
- 3
- Informativeness
- 2
- Presentation
- 3
- Soundness
- 2
Read review
Paper summary
This paper studies whether spatial reasoning improvements of VLMs can be translated into better navigation capability. Based on experiments, it finds out that the spatially specialized VLMs perform worse than their base models when inserted into existing navigation systems and spatial supervision becomes useful when it is connected to the navigation goal. To this end, it proposes a spatial-nav-100K dataset and use it for two-stage fine-tuning and distillation. As illustrated in the results, the final distilled model Spatial-Nav achieves strong performance compared to existing methods.
Critical strengths
The idea of connecting spatial reasoning question with navigation capability is interesting and based on the extensive experiments and analysis, the authors do show fine-tuning on spatial reasoning question can improve model's capability on navigation. Based on the results, although the proposed model does not achieve state-of-the-art performance, it does show comparable capability and as a illustration of the effectiveness of the paper's idea.
Critical weaknesses
- My major concern stems from the distillation process. While the author mentions the two-stage finetuning improve the spatial intelligence of the model but leave the link from spatial evidence to decisions implicit, I think when you distill the model with a focus on the link from spatial to action, you will inevitably damage the spatial reasoning capability compared to the previous fine-tuned model. Could the author provides the results of teacher model on spatial-nav-100K and the results of distilled model on spatial reasoning benchmarks such as HM3D and VSI-Bench.
- I'm curious about the exact meaning, evaluation and samples for ability types proposed such as visibility, topology and affordance. Could the author elaborate more on this part and also give more details about these samples inside their proposed benchmark.
Questions for authors
Similar as weaknesses.
2 comments
W2. Meaning, evaluation, and examples of the ability types
Meaning. The specific meanings of the five abilities are as follows.
| Ability | Definition | Example annotation |
|---|---|---|
| Visibility | Whether the target or a relevant landmark can be visually confirmed | "The TV cannot be confirmed because a closed door blocks the view." |
| Topology | Whether a visible transition connects regions | "The staircase leads to a visible landing and doorway; connectivity beyond the doorway is unknown." |
| Affordance | Whether a visible local region appears usable for movement or interaction | "The central floor strip appears traversable, but it is unclear whether there is enough clearance for the robot to pass through." |
| Relation | Observable relative position among objects, the goal, and candidate regions | "The refrigerator is near the doorway to the right of the staircase." |
| Geometry | Visible shape, scale, and coarse distance cues | "The target appears closer and large enough to consider stopping." |
Each record states the ability, a claim, the visible evidence, its navigation relevance, and an evidence limit, and contains no action label (as structure in Appendix A.3):
{
"ability": ["<ability a>", "<ability b>", ...],
"spatial_reasoning": {
"<ability a>": {
"claim": "...",
"visual_evidence": "...",
"navigation_relevance": "...",
"evidence_limit": "..."
},
...
}
}
Distribution. Of the 112,886 total records, 48,288 carry at least one spatial ability tag, and a record may carry several.
| Spatial ability | Shared foundation | Exploration | Approach | Total |
|---|---|---|---|---|
| Visibility | 11,145 | — | 9,780 | 20,925 |
| Geometry | 8,522 | — | 8,191 | 16,713 |
| Relation | 5,976 | 7,444 | 3,450 | 16,870 |
| Topology | 5,060 | 7,142 | — | 12,202 |
| Affordance | 4,145 | 8,221 | — | 12,366 |
| Tag occurrences | 34,848 | 22,807 | 21,421 | 79,076 |
| Ability-tagged records | 16,000 | 22,508 | 9,780 | 48,288 |
The shared foundation covers all five abilities. Exploration uses the abilities that inform where to go next, and Approach uses those that inform whether the target is confirmed and close enough to stop.
Evaluation. We evaluate the abilities at three levels.
- Annotation quality. An automatic audit of annotations checks output schema and evidence fields, action-label separation, and privileged-information boundaries; 99.93% pass and the rest are removed. A manual review of 500 random annotation-image pairs found 97.8% semantic correctness, 98.8% visual grounding, 98.4% ability-label appropriateness, and 98.2% conservative uncertainty handling, 98.3% on average.
- Ability acquisition. For each ability, we compare the model's spatial response on a held-out observation with the held-out GPT-5.4 annotation and report the mean embedding cosine similarity (Figure 6(b), Supplementary Table 11). These annotations are not used for training.
- Effect on navigation. Main Table 3 trains one model per ability and measures SR / SPL on HM3D-v0.2. Affordance and Topology help Exploration most (+5.2 and +2.8 SR), and Visibility and Geometry help Approach most (+3.1 and +3.0 SPL).
Examples. We added an image-annotation example for each ability to Supplementary Appendix A.3 (Figure 7). More examples are in the anonymous repository, which links the dataset.
Response to Reviewer zYwV
Conclusion
Thank you for the review. We evaluated each phase expert on six spatial benchmarks after Spatial-NPD. Overall, distillation indeed shifts the model's focus toward translating spatial understanding into actions, but the resulting degradation in its general spatial capabilities remains relatively modest.
In addition, we have also provided more details of the proposed Spatial-Nav-100K dataset and released the anonymized code repository and dataset.
W1. Does action-oriented distillation damage spatial reasoning?
Teacher on Spatial-Nav-100K. Supplementary Table 6 reports the teacher on the Spatial-Nav-100K development split. Action accuracy is 83.03% without a prior (Student), 88.02% with the aligned spatial prior (Teacher).
Distilled model on HM3D. HM3D is a navigation benchmark, so we report the navigation metric SR / SPL here. Relative to training without Spatial-NPD, the distilled model improves SR / SPL by +2.9 / +2.5 on HM3D-v0.2, +2.6 / +1.3 on HM3D-v0.1, and +0.8 / +1.3 on MP3D (Main Table 7a).
Distilled model on spatial benchmarks. Supplementary Table 10 reports the phase experts before distillation. The table below adds the same experts after distillation by Spatial-NPD (accuracy in %, before → after).
Across each branch, distillation reduces accuracy on four benchmarks while improving it on VSI-Bench and OmniSpatial. Eleven of the twelve score changes are within 3.0 points. The only notable exception is the Exploration expert on Q-Spatial++, a metric distance-estimation benchmark, where the number of correct answers drops from 70 to 62 out of 101. This observation is consistent with the trade-off you raised: distillation toward movement-oriented decisions may come at the expense of accuracy on explicit metric distance estimation.
We therefore maintain that Spatial-NPD improves the utilization of spatial evidence for navigation, while preserving most general spatial capabilities with only modest degradation. We will include the post-distillation results in Supplementary Table 10 and explicitly acknowledge this trade-off in the limitations.