- Rating
- 3
- Confidence
- 4
- Informativeness
- 2
- Presentation
- 2
- Soundness
- 3
Read review
Paper summary
To address the multi-view spatial reasoning in MLLMs, the paper proposes GeoMLLM, a novel framework that grounds cross-view information exchange in camera geometry. By focusing on correlations of tokens from different views, the paper tackles the ambiguity of cross view correspondence. On the method level, they employ a camera-ray embedding and geometry-aware attention, with a geometry-aware correspondence supervision. The model achieves exceptionally strong results for SPAR-Bench etc, beating flagship VLMs and human performance.
Critical strengths
- The research question is important. People in 3D VLMs and video understanding have been talking about or troubled by this problem. A solution for this will be impactful for the research community.
- The design is generally elegant. The Geometry bias, leveraging epipolar calculations, is a simple and effective way to inject geometric constraints into the model, which is worth recognition in academia.
- Exceptionally strong performance across benchmarks, which demonstrates the value of the method. Impressively, the performance was obtained from 3B/4B small models.
- Analysis of Figure 3 is thoughtful. It demonstrates that the model is still robust under camera perturbations, so predicted cameras are not expected to significantly decrease performance.
Critical weaknesses
- The first point of contribution is overclaiming. The “cross-view” issue has been a long-standing research problem. One example is Qwen3d [1].
- (minor) It is confusing to talk about Qwen2.5 results in intro while in abstract the results are reported with Qwen3. Consistency is needed when authors renew a paper with new experimental results.
[1] Lin, Lucy, et al. "Qwen-3d: A generalist 3d vision-language model for spatial understanding." European Conference on Computer Vision. Cham: Springer Nature Switzerland, 2026.
Questions for authors
- In Line 148, what is the reasoning behind suppressing the attention between two tokens from different views that does not correspond? In my opinion, one token in image0 may find extra information in image1 helpful.
- Could you please clarify Line 210? Why the second term is complementary to the first one? What is the underlying logic of the design of Eq.(2)?
3 comments
Dear Reviewer nWiW,
Thank you again for your thoughtful review and constructive suggestions, which have been very helpful in improving our work.
We are writing to gently follow up on our rebuttal and would be grateful to hear whether our responses have addressed your main concerns.
We would be happy to provide any additional explanations or clarifications if needed.
Should you find our responses satisfactory, we would sincerely appreciate your consideration of updating your overall evaluation.
Thank you very much for your time and continued consideration.
Best regards,
Authors
Dear nWiW,
With just over 24 hours remaining before the discussion deadline, we would greatly appreciate your feedback on our responses. Thank you for your time!
Response to Reviewer nWiW
Thank you for recognizing the importance of our research question, the geometric design, and the strong empirical results. We appreciate your constructive comments and suggestions.
Weakness 1 — Scope of the first contribution
Authors’ Response
Thank you for highlighting this point.
Contribution scope
We agree that cross-view reasoning is a long-standing research problem and that our first contribution could be stated more precisely.
Planned revisions
Comparison with GTA and PRoPE
To place our contribution within the established literature on cross-view reasoning, we additionally compare the full GeoMLLM model with GTA and PRoPE, two existing geometry-aware attention methods.
All methods use Qwen2.5-VL-3B with the same training datasets, evaluation datasets, and experimental environment. The table reports overall benchmark scores, with the full GeoMLLM results taken from manuscript Tables 1–2.
Weakness 2 — Consistency of reported results
Authors’ Response
Thank you for noting this inconsistency.
Consistent primary results
We will consistently foreground the Qwen3-VL-4B results on SPAR-Bench full in the abstract and introduction.
Explicit result attribution
We will explicitly identify the backbone and evaluation split associated with each result throughout the paper.
Question 1 — Motivation for the geometric attention bias
Authors’ Response
Thank you for raising this point.
We will clarify this point around Eqs. (2)–(3).
Question 2 — Complementary terms in the geometric attention bias
Authors’ Response
Thank you for asking us to clarify the design of Eq. (2).
The two terms in Eq. (2) provide complementary geometric signals:
Bijh=η[−λψ(rij)vij+gh(ϕij)Δh(ϕij)],
We will clarify this logic around Eq. (2).