- Rating
- 1
- Confidence
- 3
- Informativeness
- 1
- Presentation
- 2
- Soundness
- 1
Read review
Paper summary
The paper proposes ST-OPSD, which applies on-policy self-distillation to long-video QA. The student model sees 256 frames sampled across the video, while a frozen teacher initialized from the same model bounding-box-marked keyframes and provides token-level supervision. Experiments show that the approach achieves strong performance across four video understanding benchmarks on 4B and 9B models.
Critical strengths
- It conducts experiments on different scales. The 4B and 9B achieve gain across all four benchmarks, with average increases of 3.26 and 2.39 respectively.
- It analyzes the effectiveness of which view should be presented to the teacher model. It ablades for three different views and find joint spatiotemporal view is the best.
Critical weaknesses
- The main table (Table 2) is unfinished. It has randomly generated values as placeholder, as mentioned in the caption "The 4B and 9B SFT rows contain illustrative placeholder values pending measured evaluation results." This make the experimental results hard to follow and questionable.
- The teacher input is unclear. Section 3.2.2 describes several marked keyframes and crops. Section 4.3 says one keyframe and one crop. Which was used in Table 3? Teacher frame counts, image sizes, and box annotation prompts are also missing.
- Teacher quality is only tested for 9B. The training data is selected using 9B, then also used for 2B and 4B. Teacher accuracy on the training examples is not reported for each model size. This makes the mixed 2B results hard to explain.
Questions for authors
- How does ST-OPSD compare with directly training grounding on the same backbone and evidence annotations? 2, At each model scale, what is teacher accuracy on the training examples? How often is the ordinary view correct while the privileged teacher is wrong?
- Does Table 3 use one keyframe or all annotated keyframes? What are the teacher frame counts and resolutions, and what inputs and prompts did the annotation agent receive?
Response to Reviewer hTfk
Q1
We evaluated AnchorSR SFT-v4, a grounding SFT baseline initialized from Qwen3.5-9B and trained on the same CG-Bench examples and evidence annotations as ST-OPSD. The baseline is trained to predict question-relevant evidence locations. We tested its checkpoint on four video question-answering benchmarks to compare direct grounding supervision with privileged-view self-distillation. ST-OPSD outperforms the grounding SFT baseline on all four benchmarks.
Accuracy is reported as a percentage. Δ denotes ST-OPSD minus Grounding SFT in percentage points.
Q2
At each model scale, we evaluated the same frozen checkpoint under ordinary and privileged views on all 3,200 training examples. The table reports both accuracies and the percentage of all training examples for which the ordinary view produces a correct answer but the privileged teacher does not.
Q3
Table 3 uses all annotated keyframes retained after selection and deduplication by the annotation agent. The temporal view contains 16 frames uniformly sampled within the ground-truth temporal intervals. The spatial view contains the retained annotated keyframes and their corresponding crops, with counts varying across examples. The joint view combines these two components. The maximum pixel count per image is 112,896.
We will correct the singular wording in the manuscript and provide the prompts used by the annotation agent in the revised version.