- Rating
- 3
- Confidence
- 2
- Informativeness
- 2
- Presentation
- 3
- Soundness
- 3
Read review
Paper summary
This paper proposes FastOCR, a training-free method that speeds up VLM-based document parsing by cutting the number of visual KV entries attended to at each decoding step. It builds on the observation that a model’s top-attended visual tokens are line-local and drift gradually during decoding, much like a human reader’s gaze. Accordingly, it combines Focal-Guided Pruning, which selects a few focal layers to pick the top-attended image tokens and propagates them to the remaining layers, with Cross-Step Fixation Reuse, which warm-starts each step from the previous one. Because the full KV cache is retained, no visual token is ever permanently lost. On OmniDocBench, FastOCR retains up to 98.3% of the unpruned accuracy on Qwen2.5-VL with only 5% of image tokens attended at pruned layers, outperforming all four baselines and reaching up to 3.4× attention speedup.
Critical strengths
-
The writing is clear and easy to follow.
-
The problem and insight are well-motivated.
-
The method is deployment-friendly.
Critical weaknesses
-
One design of this method is selecting focal layers by image-attention ration. But there is no comparison between this selection method and other simple alternatives, like random selection, last few layers, and etc. I think this ablation can further judge the effectiveness about the selection of the focal layers.
-
Did you analyze what characteristics the selected focal layers? Could the online warmup selection be replaced with offline selection?
-
Could you clarify the experimental setup in Table 1? How did you delete or retain tokens in each baselines? At which stage and layers is each baselines' pruning applied under the matched budget? Some gaps are very large and implementation details are needed to support fair comparison.
Questions for authors
See weaknesses.
Dear Reviewer McEj,
With the discussion period concluding in a few days, we wanted to politely check in and see if our two-part response and the blue-highlighted revised manuscript have resolved your concerns. Following your feedback, we expanded our related work and empirical comparisons with recent training-free LVLM compression methods (
Sec. 2, App. C.3), clarified the Table 1 retention ratios (Sec. 4.1), and added end-to-end wall-clock latency / VRAM analyses (App. D.1, App. K) as well as a full 1,000-questionOCRBenchevaluation (Sec. 4.2, App. F).Please let us know if these revisions address your questions or if we can provide any further clarification!