- Rating
- 2
- Confidence
- 4
- Informativeness
- 1
- Presentation
- 2
- Soundness
- 2
Read review
Paper summary
This paper proposes URUQI, a framework for learning spatial cognition in VLMs from visual experience. It introduces a data-generation pipeline that produces motif-driven camera trajectories in simulated 3D scenes and derives supervision for self-motion tracking, persistent object mapping, and operations over spatial state. Trained on URUQI-600k, the InternVL3-8B–based URUQ-8B achieves state-of-the-art performance on the proposed URUQI benchmark and improves over its backbone on VSI-Bench, MMSI-Bench, and MindCube-tiny.
Critical strengths
- Scalable data-generation pipeline. This work introduces a scalable pipeline that generates motif-driven camera trajectories in simulated 3D scenes and uses privileged camera poses, object identities, and visibility annotations to derive supervision for self-motion tracking, persistent object mapping, and operations over spatial state.
Critical weaknesses
-
Insufficient evidence supporting the main contribution. The paper presents the joint organization of self-motion tracking, persistent object mapping, and spatial-state operations within visual experience as its main contribution. In practice, however, this idea is implemented primarily through data construction, while model training relies on a standard answer-token prediction objective. the paper does not sufficiently establish what the proposed organization of supervision contributes beyond existing spatial QA data-generation approaches. Furthermore, the lack of direct comparisons with existing data pipelines (such as Holi-Spatial (ICML 2026)) makes it difficult to assess the distinctiveness of the proposed method.
-
Modest transfer gains and incomplete comparisons. The improvements on external spatial reasoning benchmarks are relatively modest. Compared with SenseNova-SI-1.5, URUQI-SI-Mix-8B achieves overall score gains of 0.55, 2.70, and 0.57 on VSI-Bench, MMSI-Bench, and MindCube-tiny, respectively. Moreover, its training data include 100k examples randomly sampled from SenseNova-SI-8M, making it difficult to isolate the contribution of URUQI supervision. Comparisons with recent spatial reasoning approaches, including 3DThinker (CVPR 2026), GeoThinker (ICML 2026), and Holi-Spatial (ICML 2026), would further clarify the method’s relative effectiveness.
Questions for authors
Please see the weaknesses above.
3 comments
Response to Reviewer x9K6 (Part 2)
W2. External Transfer and Comparisons with Recent Spatial approaches
"The improvements on external spatial reasoning benchmarks are relatively modest." "Its training data include 100k examples randomly sampled from SenseNova-SI-8M, making it difficult to isolate the contribution of URUQI supervision." "Comparisons with recent spatial reasoning approaches, including 3DThinker, GeoThinker, and Holi-Spatial, would further clarify the method's relative effectiveness."
Thank you for suggesting these comparisons. Our newly added SenseNova-100k-only ablation demonstrates substantial additional gains from URUQI supervision, and we further compare our results with the suggested recent methods.
URUQI provides substantial transferable gains beyond conventional spatial QA supervision. With the same InternVL3-8B initialization and SenseNova-100k subset, adding URUQI improves all three external benchmarks (+4.13/+9.80/+9.05) and URUQI accuracy (+30.49) (as shown in Table R2 below).
| Training Data | URUQI | VSI-Bench | MMSI-Bench | MindCube-tiny |
|---|---|---|---|---|
| SenseNova-100k only (New) | 17.86 | 53.43 | 30.00 | 46.95 |
| URUQI + SenseNova-100k | 48.35 | 57.56 | 39.80 | 56.00 |
| Gain | +30.49 | +4.13 | +9.80 | +9.05 |
These gains show that visual-experience supervision provides additional spatial learning beyond exposure to task-aligned QA data alone. Moreover, URUQI-Syn-8B independently improves all three external benchmarks (+5.12/+5.30/+7.71) using only simulated visual experiences, without their training data (Table 2).
We have added the SenseNova-100k-only ablation to Table 2(b) and discussed its comparison with URUQI-Mix-8B in Section 4.3.
(2) Our transfer gains are competitive with recent spatial reasoning methods. We compare the reported results of Holi-Spatial, GeoThinker, and 3DThinker on MMSI-Bench, which has no official training set (as shown in Table R3 below).
| Method | Backbone | Main Approach | MMSI Base → Trained | Gain |
|---|---|---|---|---|
| Holi-Spatial | Qwen3-VL-8B | Video-derived 3D spatial QA | 31.10 → 32.60 | +1.50 |
| GeoThinker | Qwen3-VL-8B | Active geometric feature integration | 28.80 → 30.90 | +2.10 |
| GeoThinker | Qwen2.5-VL-7B | Active geometric feature integration | 26.80 → 31.70 | +4.90 |
| 3DThinker | Qwen2.5-VL-7B | 3D latent alignment and outcome optimization | 26.90 → 43.30 | +16.40 |
| URUQI-Syn-8B | InternVL3-8B | Interleaved visual-experience supervision | 27.80 → 33.10 | +5.30 |
| URUQI-Mix-8B | InternVL3-8B | Visual experiences + spatial QA | 27.80 → 39.80 | +12.00 |
We further evaluate the released HoliSpatial-2M-QA-Qwen3-VL-8B to directly examine the spatial capabilities learned from different supervision approaches. Table R4 below compares Holi-Spatial with our newly trained URUQI-only model based on the Qwen3-VL-8B backbone.
| Model | URUQI | VSI-Bench | MMSI-Bench | MindCube-tiny |
|---|---|---|---|---|
| Holi-Spatial (Qwen3-VL-8B) | 17.58 | 46.84 | 32.60 | 54.38 |
| URUQI-Only (Qwen3-VL-8B) | 54.76 | 54.56 | 34.70 | 44.38 |
The comparison reflects different training coverage. Holi-Spatial benefits from extensive spatial QA supervision, while our Qwen3-VL-8B uses only synthetic visual experiences and achieves substantially better coherent spatial understanding (Table R4). Due to limited time, we have not trained a Qwen3-VL-8B Mix variant. Notably, our InternVL3-8B results demonstrate that adding task-aligned spatial QA data can further improve MindCube performance.
(3) More importantly, improvements on spatial QA benchmarks do not necessarily imply coherent spatial understanding. SenseNova-SI-1.5 achieves 92.00% on MindCube-tiny but only 17.02% on URUQI, whereas GPT-6 Astra reaches 50.08% without URUQI-specific training (Table 1). This contrast reveals a capability gap that conventional spatial QA benchmarks do not adequately capture.
Our training addresses this gap while further improving existing spatial QA performance. URUQI raises SenseNova-SI-1.5's accuracy from 17.02% to 50.41% (+33.39), alongside improvements on all three external benchmarks. Thus, URUQI not only reveals this previously underexplored gap, but also enables models to develop coherent spatial understanding alongside their existing spatial QA capabilities.
Dear Reviewer x9K6,
As the discussion period is coming to an end, we would greatly appreciate your feedback on whether our clarifications have addressed your main concerns.
Thank you again for your time and consideration.
Best regards,
Submission 7770 Authors
Response to Reviewer x9K6
Thank you for your valuable feedback and for recognizing the scalability of our data-generation pipeline. We clarify our key contributions and provide additional experimental evidence and comparisons below.
W1. Contribution of Interleaved Spatial Supervision and Benchmark
Thank you for raising these questions. We would like to clarify that URUQI contributes both an evaluation of coherent spatial understanding and an interleaved supervision approach designed to develop this capability.
(1) URUQI benchmark evaluates coherent spatial understanding beyond conventional spatial QA performance. Existing spatial benchmarks primarily evaluate whether models answer spatial questions correctly. In contrast, URUQI uses temporally connected queries within continuous visual experiences to assess whether models can track their own motion, maintain previously observed object locations, and update spatial relationships as the observer moves. This distinction reveals a substantial capability gap that previous spatial benchmarks fail to capture. SenseNova-SI-1.5 achieves 92.00% on MindCube-tiny but only 17.02% on URUQI, whereas GPT-6 Astra reaches 50.08% without URUQI-specific training (Table 1). These results show that strong performance on existing spatial QA benchmarks does not necessarily imply coherent spatial understanding across observations.
(2) Our training contribution lies in how spatial supervision is organized within continuous visual experiences. Existing pipelines, such as Holi-Spatial, provide rich geometric and relational supervision through spatial QA. URUQI interleaves temporally grounded QA within a shared context. This organization allows successive questions to build on the same observation history, linking observer motion to changes in object locations and spatial relations. Our same-QA single-turn comparison isolates the benefit of this episodic organization, with interleaved training outperforming independent single-turn training across all four benchmarks (Table R1).
To further address the suggested comparison with Holi-Spatial, we also evaluate its officially released 2M-QA checkpoint on URUQI and external benchmarks (please see Table R4 below).
We have incorporated these ablations and the single-turn comparison into Section 4.4 and Table 3 of the revised manuscript.