- Rating
- 3
- Confidence
- 3
- Informativeness
- 2
- Presentation
- 3
- Soundness
- 2
Read review
Paper summary
GLANCE is a training-free, query-agnostic visual-token compressor for video language models. IUS combines within-group feature-norm ranks with video-wide directional uniqueness to construct candidate pools. PRS then computes similarity penalties against preceding candidates in a fixed utility order in parallel, avoiding the sequential updates of greedy subset construction. The complete system additionally expands the input budget and withdraws visual tokens in later decoder layers: nominal 10% retention corresponds to approximately 12.5% decoder-input retention and 9.4% layer-averaged visual-token retention. Across three backbones and four benchmarks, this configuration preserves 94.2%–97.6% of full-token mean accuracy with approximately 2.2–3.9× speedups in model-side time to first token. Matched selector comparisons, component ablations, and frame-scaling experiments further evaluate the design.
Critical strengths
The low-cost redundancy treatment has direct empirical support. Fixing the candidate order makes PRS amenable to batched execution and well suited to GPU inference. With the same IUS scores, candidate pools, quotas, and depth schedule, Table 3(c) reduces candidate-selection time from 8.37 ms for Greedy to 0.66 ms, with three-task mean accuracy of 60.2 versus 60.0. The paired analysis in Appendix D additionally supports a TTFT reduction on that cohort. The authors appropriately avoid claiming that PRS is more accurate than Greedy. Separating accuracy, module time, and overall latency makes the practical argument convincing.
Broad evaluation demonstrates a useful trade-off for temporal coverage. Results across three backbones, four benchmarks, and multiple compression levels provide stronger evidence than a single-model, single-budget evaluation. In Table 10, 128-frame GLANCE on Qwen3-VL achieves a three-task mean of 63.0 at 981.3 ms TTFT, compared with 62.4 at 1,383.0 ms for the 64-frame full-token model. This illustrates how compression savings can support denser temporal observation. Reporting the accompanying peak-memory increase from 23.6 to 27.4 GiB also makes the trade-off transparent.
Critical weaknesses
Cross-method comparisons do not fully isolate the new selector's contribution. Tables 2 and 14 usefully separate IUS–PRS from input expansion and late withdrawal, but competing methods have not been evaluated under the same schedule. For example, at the 20% setting on Qwen3-VL, the selector alone scores 62.3, matching V-CAST's displayed mean in Table 1, whereas the complete configuration reaches 63.0. The main results therefore support the accuracy–latency trade-off of the complete system, but do not attribute all of that advantage to IUS–PRS. Comparing the strongest baseline with matched input quotas and withdrawal depth would better identify the methodological contribution. This is an addressable evidence gap and does not invalidate the measured benefit of the complete configuration.
The robustness of the smaller main-table accuracy gains is not directly quantified. Appendix D does provide appropriate paired bootstrap analyses, but its accuracy diagnostics concern separate subsets and component comparisons; they are not confidence intervals for the main four-benchmark means or differences from the strongest external baselines. This matters for the approximately 0.4-point advantage on LLaVA-Video at 10% retention and for the task-level regressions observed when adding uniqueness. The current results establish competitive performance, but paired analyses of the full prediction sets would clarify whether the smaller advantages are robust.
Questions for authors
Could at least one strongest baseline be evaluated with the same input quotas and late-withdrawal schedule, reporting accuracy and TTFT against IUS–PRS? This would directly affect my assessment of the selector's incremental contribution.
Could the existing full prediction sets be used to report video-clustered paired intervals for GLANCE versus the strongest baseline, at least at the 10% setting in Table 1? This does not require retraining and would clarify the stability of the smaller gains.
PRS can suppress a candidate because of an earlier candidate that is ultimately discarded. Can the authors quantify how often this occurs and whether it correlates with failures relative to Greedy? This would help establish the limits of the parallel approximation.
4 comments
Response to W2 & Q2 (video-clustered paired intervals)
W2:The robustness of the smaller main-table accuracy gains is not directly quantified. Appendix D does provide appropriate paired bootstrap analyses, but its accuracy diagnostics concern separate subsets and component comparisons; they are not confidence intervals for the main four-benchmark means or differences from the strongest external baselines. This matters for the approximately 0.4-point advantage on LLaVA-Video at 10% retention and for the task-level regressions observed when adding uniqueness. The current results establish competitive performance, but paired analyses of the full prediction sets would clarify whether the smaller advantages are robust.
Q2:Could the existing full prediction sets be used to report video-clustered paired intervals for GLANCE versus the strongest baseline, at least at the 10% setting in Table 1? This does not require retraining and would clarify the stability of the smaller gains.
Thank you for your insightful comments.
To address this, we conducted video-clustered paired analyses at nominal 10% retention, comparing GLANCE with native FlashVID on Qwen3-VL-8B and LLaVA-Video-7B, and with V-CAST on Qwen3.8-27B, without retraining.
We evaluate both methods on Video-MME, LongVideoBench, MLVU, and MVBench.
We report the measured paired accuracy differences and 95% confidence intervals separately for each benchmark, together with the equally weighted four-benchmark mean. Separately for each backbone, the four benchmark comparisons and their mean form one Holm family of five tests. Sorting the unadjusted values in ascending order, we apply the Holm step-down correction:
Table R2. Video-clustered paired comparisons at nominal 10% retention. Each cell reports GLANCE minus the native baseline in accuracy points and an unadjusted 95% confidence interval. The final row reports Holm-adjusted values for the four-benchmark mean. Baselines are native FlashVID for Qwen3-VL-8B and LLaVA-Video-7B, and V-CAST for Qwen3.8-27B.
| Benchmark | Qwen3-VL-8B | LLaVA-Video-7B | Qwen3.8-27B |
|---|---|---|---|
| Video-MME | +2.37 [1.11, 3.63] | +1.56 [0.37, 2.78] | +2.67 [1.22, 4.11] |
| LongVideoBench | +1.57 [0.29, 2.85] | +0.52 [0.26, 0.78] | +0.22 [0.05, 0.40] |
| MLVU | +1.81 [0.51, 3.16] | +0.37 [0.14, 0.59] | −0.41 [−2.01, 1.20] |
| MVBench | −0.08 [−1.25, 1.10] | +0.24 [0.12, 0.36] | +0.34 [0.10, 0.58] |
| Four-benchmark mean | +1.42 [0.79, 2.05] | +0.67 [0.36, 0.98] | +0.70 [0.16, 1.24] |
| Holm for mean | 0.00005 | 0.00015 | 0.03547 |
The four-benchmark mean differences are +1.42 points for Qwen3-VL-8B (95% CI [0.79, 2.05]; Holm ), +0.67 for LLaVA-Video-7B ([0.36, 0.98]; ), and +0.70 for Qwen3.8-27B ([0.16, 1.24]; ). The mean improvements remain statistically significant after Holm correction across all three backbones (adjusted ). The benchmark breakdown also retains task-specific regressions on MVBench for Qwen3-VL-8B and on MLVU for Qwen3.8-27B.
Response to Q3 (Suppression by discarded predecessors)
Q3: PRS can suppress a candidate because of an earlier candidate that is ultimately discarded. Can the authors quantify how often this occurs and whether it correlates with failures relative to Greedy? This would help establish the limits of the parallel approximation.
Thank you for your insightful comments.
To examine the impact of discarded predecessors, we conducted a retained-set recomputation diagnostic and a matched comparison with selected-set Greedy.
Selection diagnostic. We analyzed videos at both 32 and 128 frames using Qwen3-VL-8B under S1 at nominal 10% retention. For each original PRS-selected set , we recomputed redundancy penalties using only preceding candidates retained in , while keeping the candidate order and token budget fixed. This produces a counterfactual selection that excludes suppression by discarded predecessors.
The pooled replacement fraction, , is 6.04% at 32 frames and 6.29% at 128 frames. These values quantify changes in the retained subset induced by removing discarded-predecessor penalties, without implying equivalent losses in useful information or prediction accuracy.
Table R3. Selection changes, accuracy disagreements, and efficiency. The lower value in each latency pair is bold. Accuracy disagreements are evaluated on Video-MME, LongVideoBench, and MLVU at each frame count. Latencies are from the separate matched H100 profiling experiments in the submitted paper (Table 3(c), Table 16, and Appendix C.6).
| Diagnostic | 32 frames | 128 frames |
|---|---|---|
| Retained positions replaced | 6.04% | 6.29% |
| PRS wrong / Greedy correct | 57 | 50 |
| PRS correct / Greedy wrong | 78 | 53 |
| Candidate selection: PRS / Greedy (ms) | 0.66 / 8.37 | 1.07 / 8.87 |
| Complete compression: PRS / Greedy (ms) | 1.68 / 9.32 | 3.50 / 11.42 |
| Model-side TTFT: PRS / Greedy (ms) | 288.75 / 299.77 | 1100.84 / 1107.54 |
Under identical token budgets and the S1 schedule, PRS and selected-set Greedy achieve comparable three-benchmark mean accuracy at 128 frames (65.81% versus 65.79%). Their predictions differ in both directions: Greedy corrects 50 PRS errors, while PRS correctly answers 53 questions missed by Greedy. Thus, the approximation affects individual predictions but has little observed impact on aggregate accuracy.
Meanwhile, PRS reduces candidate-selection latency from 8.87 to 1.07 ms (8.3$\times$) and complete compression latency from 11.42 to 3.50 ms (3.3$\times$) at 128 frames, with a smaller reduction of 6.70 ms in model-side TTFT. These timings come from the submitted paper's matched profiling setup, separate from the benchmark accuracy diagnostic.
Overall, these results indicate that discarded-predecessor suppression changes a limited fraction of retained tokens, while PRS maintains comparable aggregate accuracy to sequential Greedy with substantially lower subset-construction overhead.
Dear Reviewer pbqc,
We hope this message finds you well. We sincerely thank you for the time and effort you have devoted to reviewing our paper.
We have posted our response to your comments, where we did our best to address each of your concerns. As the discussion period is approaching its end, we would be grateful if you could kindly take a look when convenient, and let us know whether our response addresses your concerns or whether anything remains unclear. We would be happy to provide further clarifications promptly within the remaining time.
Thank you very much again for your valuable feedback, which has helped us improve the paper.
Response to W1 & Q1 (Selector contribution under matched schedules)
Thank you for your insightful comments.
To isolate the selector's incremental contribution, we conducted a controlled comparison of IUS–PRS, V-CAST, and FlashVID's before-LLM selector across three shared schedules on Qwen3-VL-8B at a nominal 10% retention budget. Within each schedule, input token counts, withdrawal depth and rule, and visual-token counts at every decoder layer match exactly across all methods for every example, including integer rounding.
Here, FlashVID-selector denotes its before-LLM compression evaluated under these common schedules. Aggregate mean accuracy weights Video-MME, LongVideoBench, MLVU, and MVBench equally.
Table R1. Shared-schedule accuracy and latency. Each cell reports the equally weighted four-benchmark mean accuracy (%) / model-side TTFT (ms).
As shown in Table R1, IUS–PRS consistently achieves the highest four-benchmark mean accuracy and the lowest model-side TTFT under every shared schedule. Under S0—where neither input expansion nor withdrawal is applied—it outperforms V-CAST by +1.79 percentage points and FlashVID-selector by +1.72. Under S1, the corresponding gains are +1.18 and +1.16 points, respectively. Under S2, the gains are +1.09 and +0.89 points, respectively. Together, these controlled comparisons provide direct evidence of an incremental selector contribution under matched input and decoder budgets.