- Rating
- 4
- Confidence
- 2
- Informativeness
- 2
- Presentation
- 3
- Soundness
- 3
Read review
Paper summary
Existing VLMs and spatial reasoning benchmarks mostly focus on observed scenes, while predicting future spatial states is still underexplored. This paper proposes SpatialMind, a metric-scale VLM for spatial reasoning and future prediction. Given a video prefix, it predicts distances, motion directions, and spatial relations in both observed and unseen future frames. A metric depth adapter anchors reasoning to real-world scale. A progressive state chain then has the model work out the current state and the observed motion before predicting the future. The authors also build a data engine on Waymo and Ego-Exo4D, which produces the SpatialMind-30K dataset and the SpatialMind-2K benchmark. SpatialMind clearly beats existing VLMs on this benchmark and shows competitive zero-shot results on VSI-Bench, OSI-Bench, and VLM4D.
Critical strengths
- The paper is clearly written and easy to follow. The three-level view is well motivated, and the figures make the data pipeline and the model easy to understand.
- Each step of the method is explained clearly and the logic is easy to follow. The data engine is also carefully built.
- The experiments are thorough, with a wide range of baselines, ablations of both components, and extra diagnostic analyses. The worked examples in the appendix make the method very easy to understand.
Critical weaknesses
- Most of the gain comes from the new data. Fine-tuning Qwen3-VL-8B on SpatialMind-30K alone raises the score from 20.20 to 45.70, while the two new modules add only about 7 more points (to 52.65).
- The future-prediction claim is only tested on the authors' own benchmark, but the paper did not evaluate on the most related future-prediction benchmarks like STRIDE-QA and SCP-Bench.
- On VSI-Bench, the base model Qwen3-VL-8B is not listed. The Qwen3-VL Technical Report [1] reports 59.4 for Qwen3-VL-8B-Instruct, and SenseNova-SI [2] reports 57.9, but SpatialMind only gets 46.4.
- Some highly related work is not cited, such as ST-VLM [3], which builds a very similar data pipeline for kinematic QA. Spatial-MLLM [4] is used as a baseline in Table 2 but never cited.
- Several implementation details are missing, including the values of , , , , the LoRA and training settings, the MRA tolerance settings.
References: [1] Shuai Bai, Yuxuan Cai, Ruizhe Chen, Keqin Chen, Xionghui Chen, Zesen Cheng, et al. Qwen3-VL Technical Report. arXiv:2511.21631, 2025. [2] Scaling Spatial Intelligence with Multimodal Foundation Models (SenseNova-SI). arXiv:2511.13719, 2025. [3] Dohwan Ko, Sihyeon Kim, Yumin Suh, Vijay Kumar B.G, Minseo Yoon, Manmohan Chandraker, Hyunwoo J. Kim. ST-VLM: Kinematic Instruction Tuning for Spatio-Temporal Reasoning in Vision-Language Models. arXiv:2503.19355, 2025. [4] Diankun Wu, Fangfu Liu, Yi-Hsin Hung, Yueqi Duan. Spatial-MLLM: Boosting MLLM Capabilities in Visual-based Spatial Intelligence. NeurIPS 2025.
Questions for authors
- Please report zero-shot Qwen3-VL-8B on VSI-Bench under your protocol and explain the gap to the published 57.9 to 59.4.
- If possible, please evaluate on STRIDE-QA and SCP-Bench. If this is not feasible, please explain why.
- Please provide the hyperparameters listed above.
- Please cite and discuss closely related work such as ST-VLM and Spatial-MLLM.
6 comments
Response to Reviewer FBbM [2/5]
Evaluation on External Future Prediction Benchmarks
The future-prediction claim is only tested on the authors' own benchmark, but the paper did not evaluate on the most related future-prediction benchmarks like STRIDE-QA and SCP-Bench.
If possible, please evaluate on STRIDE-QA and SCP-Bench.
We extend our evaluation to STRIDE-QA [1] and SCP-Bench [2] in a zero-shot setting, following their original input and scoring protocols. First, STRIDE-QA evaluates future localization in urban driving, requiring models to predict a target agent's distance and direction relative to the ego vehicle at different future horizons. As shown in Table 1, SpatialMind achieves consistent improvements over our baseline, Qwen3-VL-8B, across the three prediction horizons, with notable gains at 1 and 2 seconds compared with the other methods.
Table 1. STRIDE-QA: Future localization success rate (%, ↑).
| Model | LSR @ 1 s | LSR @ 2 s | LSR @ 3 s |
|---|---|---|---|
| InternVL2.5-8B | 1.4 | 1.7 | 1.7 |
| Cosmos-Reason1-7B | 3.2 | 2.0 | 1.5 |
| Qwen3-VL-8B | 2.7 | 1.7 | 2.7 |
| SpatialMind | 9.3 | 8.8 | 6.8 |
We further evaluate on SCP-Bench, which examines spatial reasoning about unobserved past and future states from partially observed videos. As shown in Table 2, SpatialMind achieves consistent improvements over Qwen3-VL-8B and Spatial-MLLM, with competitive performance compared to the larger Qwen3-VL-30B across overall, relation, and relative-distance metrics, indicating improved spatial reasoning about unobserved states.
Table 2. SCP-Bench: Accuracy (%, ↑).
| Model | Overall | Relation | Relative distance |
|---|---|---|---|
| Spatial-MLLM | 39.76 | 38.33 | 49.73 |
| Qwen3-VL-8B | 47.52 | 42.33 | 49.47 |
| Qwen3-VL-30B | 54.16 | 46.22 | 56.65 |
| SpatialMind | 54.96 | 50.80 | 59.57 |
Overall, these zero-shot evaluations support the generalization of SpatialMind's spatial prediction capabilities beyond our benchmark. We have added the zero-shot evaluation results on STRIDE-QA and SCP-Bench, together with the evaluation settings, in Appendix O.
Response to Reviewer FBbM [3/5]
VSI-Bench Evaluation and Input Settings
On VSI-Bench, the base model Qwen3-VL-8B is not listed. The Qwen3-VL Technical Report [3] reports 59.4 for Qwen3-VL-8B-Instruct, and SenseNova-SI [4] reports 57.9, but SpatialMind only gets 46.4.
Please report zero-shot Qwen3-VL-8B on VSI-Bench under your protocol and explain the gap to the published 57.9 to 59.4.
We thank the reviewer for highlighting the need to clarify the evaluation settings and include the base model. Our original VSI-Bench evaluation uses 8 input frames, while SenseNova-SI [4] uses 32 frames. To comprehensively analyze performance, we evaluate Qwen3-VL-8B and SpatialMind on VSI-Bench in a zero-shot setting with both 8 and 32 input frames.
As shown in the table, SpatialMind achieves comparable performance to the baseline under both settings. Furthermore, increasing the input to 32 frames substantially improves the performance of both models, bringing their scores close to the published 57.9–59.4% [3, 4] and suggesting that input frame count contributes substantially to the reported score gap.
Table 3. VSI-Bench performance under different input frame settings (%, ↑).
| Input frames | Qwen3-VL-8B-Instruct | SpatialMind |
|---|---|---|
| 8 frames | 49.35 | 46.40 |
| 32 frames | 57.29 | 58.63 |
We are not surprised that SpatialMind achieves comparable performance to the baseline on VSI-Bench, because SpatialMind-30K does not include training examples for room-layout reasoning. VSI-Bench is built from room-scanning videos and evaluates spatial layouts and relationships across viewpoints, while SpatialMind-30K, as introduced in Sec. 3, focuses on dynamic scenes and future spatial prediction.
Despite this domain gap, SpatialMind maintains comparable performance on VSI-Bench while achieving notable improvements in dynamic scene reasoning (OSI-Bench, VLM4D) and future spatial prediction (STRIDE-QA, SCP-Bench), suggesting improved predictive spatial reasoning capabilities while preserving general spatial understanding. We include the VSI-Bench results under 8- and 32-frame inputs and the corresponding discussion in Appendix P.
Response to Reviewer FBbM [1/5]
We sincerely appreciate your valuable time and efforts in reviewing this paper. We thank the thoughtful feedback you provided, which significantly improved the quality of this paper. For the potential concerns you bring up, we would like to answer/address them here.
Contributions of Dataset and Method
Thank you for highlighting the substantial contribution of SpatialMind-30K. This improvement aligns with the domain gap between existing spatial reasoning datasets and tasks requiring future spatial prediction. As shown in Table 1 of the main paper, most existing models achieve scores below 20% on SpatialMind-2K, reflecting the importance of task-specific supervision for adapting general-purpose VLMs to predictive spatial reasoning. This observation also motivates our development of the data engine and benchmark to support future spatial prediction. Building on this, the metric adapter and progressive state chain further improve performance from 45.70% to 52.65% (+6.95 pp), supporting their additional contributions beyond supervised fine-tuning alone.