- Rating
- 2
- Confidence
- 3
- Informativeness
- 3(+1)
- Presentation
- 3
- Soundness
- 3(+1)
Read review
Paper summary
This paper proposes RoRA, a training-free visual token pruning framework for multimodal large language models. RoRA divides retained tokens into three complementary roles: semantic core, context, and fine-grained detail. It combines attention debiasing with an object-oriented prior, constructs Attention-Anchored Regions (AARs) to guide regional allocation, and applies similarity-based redundancy filtering. Experiments across LLaVA and Qwen-VL models demonstrate competitive accuracy and low selection overhead.
Critical strengths
S1. Intuitive and practical framework. The role-oriented formulation provides a clear perspective on visual token selection. The training-free design requires no additional model training or object detector.
S2. Broad experimental coverage. The evaluation spans four MLLM backbones and multiple pruning ratios. Notably, RoRA improves over D2 Pruner by 5.4 and 5.3 percentage points in normalized average performance on Qwen3-VL at 75% and 90% pruning, respectively.RoRA reports approximately 0.7 ms of selection overhead and a 24.6% reduction in inference time on LLaVA-1.5 under the reported prefill-dominated setting.
Critical weaknesses
W1. Limited methodological novelty. The main components largely combine existing techniques, including attention debiasing, heuristic importance scoring, and similarity-based filtering. The proposed semantic roles are implemented through predefined budgets and scoring rules, while AARs are constructed from local neighborhoods around attention anchors rather than explicit semantic regions.
W2. Weak evidence for the independent contributions of the proposed components. The ablations indicate that most improvements originate from core protection. Adding AAR-guided context improves normalized RefCOCO performance by only 0.59 and 0.11 percentage points at the two evaluated budgets, while standard detail repair improves the TextVQA/VizWiz average by only 0.19 points.
W3. Insufficient validation of spatial assumptions and fine-grained preservation. For dynamic-resolution models, AARs are constructed using an inferred two-dimensional grid from flattened tokens, which may not faithfully preserve the original spatial topology. Furthermore, dedicated OCR-intensive benchmarks such as OCRBench, ChartQA, and DocVQA are absent despite the emphasis on preserving fine-grained textual evidence.
Questions for authors
Q1. What distinguishes AAR-guided allocation from existing attention-based spatial coverage heuristics beyond the predefined role budgets and regional score adjustments?
Q2. How does the inferred grid preserve true spatial neighborhoods for dynamic-resolution inputs? Can the authors evaluate OCRBench, ChartQA, or DocVQA to verify the preservation of textual and numerical details?
Q3. Given the small incremental gains from AAR and detail repair, can the authors provide stronger component-wise evidence, particularly on Qwen-VL models under aggressive pruning? Can the object prior be evaluated without benchmark-specific hyperparameter selection?
5 comments
Official Comment by Authors (Part 2/3)
Response to Weakness 2 / Question 3: Component Contributions
As discussed in our response to Weakness 1, existing methods already retain performance close to the unpruned reference on some benchmarks and budget settings, leaving relatively little pruning-induced loss to recover. Further improvements require more precise preservation of task-relevant visual evidence. Such evidence may involve only a few tokens, yet affect the final answer to an individual question.
Therefore, although the observed positive increments in our ablations are modest, they represent further improvements over an already strong baseline. RoRA uses AAR-guided context selection and detail recovery to preserve potentially overlooked evidence and further reduce information loss from pruning.
We conducted a controlled comparison on Qwen3-VL at 75% pruning, fixing the inputs, token budget, and shared configuration across tasks. We compared full RoRA against a variant with the object prior, AAR bonuses, and detail components jointly disabled:
| Task | Full RoRA | Jointly Disabled | Difference (pp) |
|---|---|---|---|
| BLINK counting | 60.83 | 60.00 | +0.83 |
| IllusionVQA | 50.57 | 50.57 | 0.00 |
| VisRes orientation | 27.51 | 28.11 | −0.60 |
| CV-Bench | 82.87 | 82.56 | +0.30 |
| POPE | 85.60 | 85.52 | +0.08 |
Scores are percentages, and differences are calculated from unrounded values.
These ablations show modest positive gains across most benchmarks, while also demonstrating that the contributions of individual components vary across tasks. We position these results as supplementary evidence that complements our existing core findings.
Official Comment by Authors (Part 3/3)
Response to Weakness 3 / Question 2: Spatial Assumptions and OCR Evaluation
We clarify that AARs are constructed dynamically from input-dependent attention anchors. They provide approximate regional guidance for token selection, rather than strict object boundaries or hard retention constraints. The anchors change with the input; however, the grid inferred from the flattened token sequence remains a spatial approximation and does not guarantee exact correspondence to the true neighborhoods of dynamic-resolution inputs.
In some qualitative examples, we observed that D²Pruner retained tokens from cluttered backgrounds, while RoRA preserved textual evidence needed to answer the question. Changes to a small number of critical tokens can affect the final answer, motivating our emphasis on fine-grained evidence preservation.
To further evaluate OCR performance, we conducted additional experiments on the complete OCRBench and ChartQA test sets and the DocVQA validation set using Qwen3-VL-8B-Instruct. We used one shared pruning configuration per pruning ratio across all three benchmarks, with identical inputs and evaluation protocols across methods within each benchmark.
| Method | Pruning | OCRBench (out of 1000) | ChartQA (%) | DocVQA (ANLS × 100) |
|---|---|---|---|---|
| Unpruned | 0% | 879 | 82.84 | 95.42 |
| D²Pruner | 75% | 574 | 50.80 | 74.50 |
| RoRA | 75% | 626 | 53.88 | 79.02 |
| D²Pruner | 90% | 355 | 25.92 | 44.71 |
| RoRA | 90% | 357 | 27.68 | 49.81 |
RoRA achieves higher scores than D²Pruner in these comparisons, providing additional evidence of its effectiveness in text recognition, chart understanding, and document question answering.
Official Comment by Authors (Part 1/3)
We sincerely thank the reviewer for the thorough evaluation and constructive feedback. We deeply appreciate your valuable suggestions, which have helped us significantly improve the completeness of our work.
Response to Weakness 1 / Question 1: Methodological Novelty and AAR-Guided Allocation
RoRA’s main contribution is to coordinate the remaining visual-token budget based on the core evidence already retained. Although role budgets are predefined, AAR locations and coverage depend on attention anchors conditioned on the current image and text, rather than a fixed spatial partition.
AAR provides a lightweight approximation of existing evidence coverage: context selection favors complementary information outside these regions, while detail selection favors fine-grained evidence inside them. Similarity filtering further reduces redundancy. The same coverage representation therefore induces different selection preferences for different roles, making subsequent allocation depend on what evidence has already been preserved. This distinguishes the framework from uniform importance ranking or spatial coverage.
In some general-understanding settings, strong baselines already retain performance close to the unpruned reference. Further reducing pruning loss requires preserving localized, task-relevant evidence. Our qualitative examples illustrate the value of retaining information such as jersey numbers and document dates under the same token budget. Improving evidence preservation for individual questions remains valuable even when the aggregate score improvement is modest.