- Rating
- 3(+1)
- Confidence
- 4
- Informativeness
- 2
- Presentation
- 2
- Soundness
- 2
Read review
Paper summary
- This article proposes View-AID, which first generates auxiliary images based on multi-view images, and then converts the spatial relationships into text reasoning for training multi-modal models.
- After supervised fine-tuning, add reinforcement learning based on answer confidence. The final model only requires the original image and question, and does not need to generate auxiliary images.
Critical strengths
- Use auxiliary diagrams to organize cross-view spatial relationships, and then construct text supervision. The idea is intuitive and consistent with the characteristics of the task.
- The auxiliary graph is only used for offline data construction, does not increase the image generation overhead during inference, and the deployment method is relatively simple.
- Improvements are achieved on multiple spatial reasoning test sets, which also complement the 8B base and out-of-distribution task experiments, and are not limited to a single model or test set.
Critical weaknesses
- The independent contributions of auxiliary graphs have not been sufficiently separated. Compared with the original base, the improvement is great, but it lacks a strict comparison of directly generating text CoT under the same teachers, samples and training budget.
- The spatial accuracy of the auxiliary plots lacks validation. The generated diagrams may contain incorrect layouts, and it is difficult to rule out incorrect spatial relationships or to write explanations based on the answers based on the format and answer support checks alone.
- Confidence is not equal to the quality of reasoning. CGPO uses the probability of the final answer, but it has not been shown to improve the correctness of intermediate inferences, and direct evaluation of confidence calibration is lacking.
- Data construction details are incomplete. The specific version of the teacher model, training sample size, screening criteria and retention ratio are insufficiently explained, which affects reproduction and judgment of revenue sources.
Questions for authors
- Using the same teacher and training samples to directly generate answer-guided text CoT, how far is there compared with the auxiliary diagram solution?
- How accurate are the object correspondences, positions, and perspective relationships in the auxiliary images? Will error auxiliary maps be retained and affect training?
- Does CGPO actually improve confidence calibration and inference correctness? Can calibration metrics and inference process evaluation be provided?
- Can you add data size, teacher version, filter retention rate, and scenario-level deduplication description of training and test data?
3 comments
Thank you for the author's reply; it resolved my doubts, and I will improve my score.
Thanks for your paticipating in our work!
We are delighted that our additional experiments have addressed your concerns and deeply appreciate your willingness to raise the score. Thank you once again for your valuable time and constructive feedback, which have significantly strengthened our paper.
W1 — The independent contribution of auxiliary images is not sufficiently isolated. We respectfully clarify that a visual generator alone cannot synthesize textual CoT rationales; in our pipeline, rationales are generated by the lightweight Qwen3-VL-8B conditioned on synthesized auxiliary views. To rigorously evaluate the Reviewer's suggestion and highlight our advantages in parameter efficiency and reasoning performance, we distilled a Text-CoT baseline directly from a 4× larger teacher—Qwen3-VL-32B—without auxiliary views:
Despite using a much smaller 8B VLM teacher, View-AID-SFT substantially outperforms 32B-distilled Text-CoT, boosting Overall accuracy from 45.6% to 59.6% (+14.0 pts). Notably, scaling the text-only teacher to 32B fails to resolve complex mental transformations—
Text-CoTimproves marginally on Rot. (34.1% to 38.0%) and degrades on MSR (23.7% to 18.8%). In contrast, View-AID-SFT (8B teacher) more than doubles Rot. accuracy (77.5%, +39.5 pts overText-CoT) and surges to 86.0% on Amo. (+28.7 pts), driving MindCube All to 83.6% and MMSI All to 35.5%. This proves explicit view synthesis overcomes spatial bottlenecks that scaling a text-only teacher cannot solve.W2 — The spatial accuracy of the auxiliary images is unvalidated. Ensuring visual validity motivates our
Valid(z, y)filtering module (Algorithm 1), where Qwen3-VL-8B automatically prunes low-quality or irrelevant auxiliary images to ensure reliable AID-CoT data while preserving scalability. To quantify the trade-off between automation and per-sample accuracy, we manually audited 100 randomly sampled training instances against their original and auxiliary views across two binary criteria:Logical Consistency checks for self-contradiction, while Factual Grounding verifies whether spatial claims (object presence, position, heading, motion) align with original views. AID-CoT attains 99% logical consistency and 89% factual grounding. Inspecting the 11 ungrounded cases reveals two error sources:
Thus, residual errors rarely stem from auxiliary image defects (only 2%), but rather from the base VLM's (Qwen3-VL-8B) inherent limits in multi-frame correspondence and coordinate transformation. Overall, our pipeline achieves a favorable trade-off between scalability and supervision quality. We will include this analysis in the revision.
W3 — Confidence is not equal to reasoning quality. To quantify probability calibration, we measure True Confidence—the mean probability assigned to the ground-truth token on correct predictions. We compared
Qwen3-VLandView-AIDon 100 paired samples randomly selected from MMSI-Bench and MindCube:Alongside substantial gains in accuracy (+39.0 pts) and CoT fidelity (+26.0 pts in Logical Consistency; +37.0 pts in Factual Grounding), CGPO training boosts True Confidence by +15.3 pts (25.0% to 40.3%), confirming improvements in both reasoning quality and confidence calibration.
W4 — Data construction details are incomplete. Our pipeline's "teacher" comprises two components: Flux2-klein-4B for auxiliary view generation and Qwen3-VL-8B for conditional verification and rationale curation. Matching ViewFusion's scale, our training set contains ~18k SFT and ~15k RL samples. In the curation workflow (Figure 1), Qwen3-VL-8B acts as the filtering and routing module: out of 18,570 SFT questions, 9,135 pass verification to construct AID-CoT rationales. We will fully open-source our code, data, and models.