- Rating
- 3
- Confidence
- 3
- Informativeness
- 2
- Presentation
- 2
- Soundness
- 2
Read review
Paper summary
EgoP²C proposes a planning-perception–combination framework for spatial intelligence tasks. This method trains a combination teacher and a perception teacher separately, and then, through multi-teacher online policy distillation, internalizes the interaction process between the teachers into a single student model with role-specific experts. Experiments on three benchmarks demonstrate that this method consistently improves the performance of the base model while reducing the inference overhead compared to teacher-based systems.
Critical strengths
-
The problem is well-defined, and the method is coherently designed. Separating evidence extraction from answer generation aligns with the characteristics of first-person spatial reasoning tasks; the model architecture and training process are also structured around this division of labor.
-
The performance improvements are practically significant. Compared to a direct-answering baseline trained on the same Q&A data, a performance advantage persists. The student model based on SenseNova achieves improvements of 6.5 and 4.4 percentage points on EgoProx and R3D-SQA, respectively, compared to the direct SFT+GRPO baseline.
Critical weaknesses
-
The impact of weakly supervised perceptual rewards on the final LLM policy requires further clarification. In actual inference, paths that are helpful for arriving at the correct answer are not necessarily the same as paths where the perceived result is correct. Can the authors quantitatively characterize, on a subset of data, whether weak reward optimization improves perceptual accuracy in the intermediate space? Furthermore, how common are cases where the intermediate observation is incorrect but the final answer is correct?
-
I noticed that, across the three datasets, the performance improvement on vsi-bench was significantly smaller than on the other two. Should the authors clarify whether this method exhibits a certain preference for specific datasets, or explain why it achieved only a limited improvement on vsi-bench?
-
The sources and scope of efficiency gains remain unclear. Clearly, the reasoning paths and strategies of student models and teacher models differ; I hope to more clearly identify the specific efficiency gains achieved after distillation. For example, could we decompose the reasoning cost into visual encoding, pre-filling, and decoding, and compare the impact of cache reuse under the same interaction trajectories to clarify the contribution of each design aspect to the efficiency gains?
Questions for authors
See Weakness.
Overall, I have a positive view of the work presented in this paper.
2 comments
Thank you very much for your follow-up. We sincerely appreciate your time and your positive assessment.
Thank you to the author for the rebuttal. I stand by my positive review.