- Rating
- 2
- Confidence
- 3
- Informativeness
- 2
- Presentation
- 3
- Soundness
- 2
Read review
Paper summary
This paper proposes CoSpace for combining spatial representations in MLLMs. The shared VGGT features are organized into semantically dense tokens, geometrically multi-scale summaries, and a temporal summary. CoSpace adopts a question-conditional router to select the feature library, an allocator to weight the features according to the question and visual summaries, and independent cross-attention branches to refine a shared geometry-enhanced visual representation. Experiments on MMSI-Bench and ViewSpatial show improvements, but SITE and CV-Bench show a decline compared to the original backbone.
Critical strengths
-
The well-controlled comparison supports the architectural contributions. Standard settings control CoSpace and related baselines across multiple factors such as training data, backbone, frame count, etc. This is important because spatial instruction tuning alone can yield significant improvements, making comparisons with an untuned backbone insufficient.
-
Component analysis examines several different aspects of the mechanism. Retraining ablation is supplemented with fixed checkpoint routing and feature library interventions. The paper also clearly distinguishes between residual suppression and weight renormalization and mentions that these interventions may introduce composition-distribution mismatch.
-
Effective inference-time scaling. A checkpoint trained with fixed frames benefits from additional inference frames without retraining, which provides an interesting point of the framework.
Critical weaknesses
-
Insufficient isolation of bank organization from multiscale branching and supervised routing. All three banks largely transform the same VGGT features in a heuristic way, and the routing patterns are led by manually specified masks. Furthermore, Equation (3) uses a shared visual token rather than a question representation as the cross-attention query, thus question adaptation relies primarily on feature library selection and weighting. Current experiments more clearly demonstrate the effectiveness of the overall configuration, rather than specific components.
-
The feature bank specialization validation is insufficient. While the semantic, geometric, and temporal feature libraries are all constructed using shared VGGT feature transforms, their expected functional divisions have not been directly validated. The routing pattern is guided by a predefined task mask, while removing the ablation only proves the branch's usefulness, not the proposed semantic-geometric-temporal interpretation. Even without strict decoupling, comparison with general branches matching the parameter count and token budget is necessary to support this core architectural contribution.
-
Performance improvements are modest. Improvements over GeoThinker are approximately 0.9 points in the matched regime and 0.8 points in the scaled 32-frame comparison. In Table 3 (cross-benchmark performance), the proposed method also underperforms GeoThinker and the base model on several benchmarks.
Questions for authors
-
Can you provide the comparisons between CoSpace and direct multiscale banks without semantic-geometric-temporal organization?
-
Beyond routing patterns encouraged by predefined masks, what evidence shows that each bank correctly captures its intended semantic, geometric, or temporal information?