- Rating
- 2
- Confidence
- 3
- Informativeness
- 2
- Presentation
- 2
- Soundness
- 2
Read review
Paper summary
This paper studies repetitive box generation in MLLM-based detectors under long decoding horizons, particularly in densely populated scenes. The authors associate this failure with increasing attention to historical answer tokens and propose Compressed Window Auto-Regression (WinAR). WinAR preserves exact autoregressive context within the current window while compressing completed windows into compact representations, retaining boundary tokens to maintain local structural continuity. Experiments cover RexOmni and LocateAnything, multiple decoding modes, and both bounding-box and polygon outputs. On RSDense, RexOmni-WinAR improves F1 from 32.16 to 39.36 and reduces the duplicate rate from 35.48% to 13.00% relative to the exposure-matched FHAR* baseline. The paper also reports lower training memory consumption and improved non-redundant prediction throughput.
Critical strengths
- On RSDense, WinAR improves RexOmni’s F1 by 7.20 points while reducing the duplicate rate from 35.48% to 13.00% against FHAR* . These results indicate meaningful practical benefits beyond a small improvement in aggregate detection accuracy.
- The approach is applicable across multiple generation settings and offers useful resource savings. The experiments include two detector frameworks, multiple decoding modes, and polygon outputs . The reported reductions in training memory and improvements in non-redundant prediction throughput strengthen the practical contribution.
Critical weaknesses
- Limited methodological novelty and missing controls. The method combines window-wise generation with familiar compression operations, but its distinction from existing history-management approaches is insufficiently established. Comparisons with history truncation, uniform sampling, and simple pooling are needed to isolate the contribution of the learned compressor.
- Insufficient experimental specification. Dataset splits and evaluation descriptions are inconsistent between the main text and appendix. Duplicate-box criteria and cross-window training details also remain unclear, limiting reproducibility and assessment of the reported gains and training fairness.
Questions for authors
- How does WinAR compare with history truncation, uniform sampling, and simple pooling under matched budgets?
5 comments
Following Response to Reviewer 4WqF
W2. Evaluation. The main text in Sec. 4.1 summarizes the setup and the appendix in App. A.3 provides the details. All methods within each comparison use the same protocol, ensuring fair comparisons.
| Protocol | Evaluation rule | Reported results |
|---|---|---|
| COCO-Style | Following RexOmni, retain the first K generated boxes per image per category (K=1000 for DOTA2&SODA) and average P/R/F1 across categories. | Tables 1,4,5(DOTA2&SODA) |
| All-Style | Use the same category-wise evaluation but retain all predictions. This captures the effect of redundant boxes, each of which consumes decoding budget. | Table 9 |
| RSDense-Style | Retain all predictions, perform class-agnostic matching within each image, and average per-image P/R/F1 to reduce sensitivity to category imbalance. | Tables 1,4,5(RSDense) and Table 2 |
W2. Duplicate-box criterion. The abstract and the second paragraph of the Introduction describe the repetition loop as repeatedly decoding identical boxes. quantifies coordinate-identical repeats; we will use “exact-duplicate rate” to avoid ambiguity. We already report as a complementary measure of full over-prediction.
W2. Cross-window training. A window is a contiguous, non-overlapping block of answer tokens. A 3,000-token answer yields ten 300-token training instances. When targeting window 3, the model receives the multimodal prefix and compressed ground-truth windows 1–2, and predicts window 3 with causal teacher forcing. Only its 300 tokens contribute to cross-entropy loss; windows 4–10 are excluded. Sec. 3.2, Fig. 4(a), and App. A.2 provide the procedure and configuration.
We have revised the manuscript. We welcome any follow-up questions and will release the preprocessed dataset splits and training and evaluation code.
Follow-up on our responses and revised manuscript
Dear Reviewer,
Thank you again for your constructive feedback. We have clarified the experimental protocols and comparison fairness, added comparisons with the requested baselines under matched history budgets, and revised the manuscript to improve clarity and consistency.
As the discussion deadline approaches, we would appreciate your feedback on whether our responses address your concerns and whether any questions remain. We would welcome the opportunity to provide further clarification.
Thank you for your time and consideration.
Response to Reviewer 4WqF
W1/Q1. We compare WinAR with the 3 requested baselines using 300-token windows and a matched history budget of 20 tokens per window. Like WinAR, Pooling and Sampling retain 6 original tokens at each end and divide the middle 288 tokens into 8 equal intervals. Pooling averages the embeddings in each interval, while Uniform Sampling selects the right-middle token. History Truncation retains the last 20 tokens of each window. All variants use the same training setting in Table 8.
W2. Data Split. We thank the reviewer for identifying this inconsistency and acknowledge that the split in Sec. 4.1 was described incorrectly. The current descriptions and their implied splits are summarized below:
All models and experiments consistently use the Appendix split, and the fairness is unaffected. The counts in Tables 6–7 are consistent with these splits. The SODA description in Sec. 4.1 is a wording error that we will correct.