- Rating
- 2
- Confidence
- 2
- Informativeness
- 1
- Presentation
- 2
- Soundness
- 3
Read review
Paper summary
This paper proposes VOLT, a training-free method for video token compression. It reserves a minimum number of tokens per frame, then allocates the remaining budget across frames through greedy orthogonal-residual selection motivated by a log-determinant objective. Discarded tokens are assigned to their cosine-nearest retained tokens within the same frame and aggregated before the compressed sequence is passed to the frozen LLM. The paper evaluates the method on five video understanding benchmarks and three video MLLM backbones.
Critical strengths
-
VOLT preserves strong accuracy under aggressive token compression. On LLaVA-OneVision at 10% retention (Table 1), it exceeds the uncompressed model on EgoSchema (61.2 vs. 60.4), LongVideoBench (57.1 vs. 56.4), and MLVU (64.4 vs. 64.0), while retaining 100.4% of the uncompressed five-benchmark average. Preserving this level of accuracy with approximately one tenth of the visual tokens is a useful result.
-
The reported improvements extend across different backbones. At 10% retention on LLaVA-Video (Table 2), VOLT improves over the manuscript’s FlashVID baseline on LongVideoBench from 54.9 to 55.5 and on MLVU from 67.7 to 68.4, while retaining 96.0% of the uncompressed average accuracy. On Qwen2.5-VL at the same retention ratio (Table 3), it improves MVBench from 64.2 to 64.8 and LongVideoBench from 53.7 to 54.2 over the reported FlashVID baseline. These are incremental but consistent gains across the evaluated model families.
-
I did not find major technical problems with the core method. The pipeline appears sound and operates without retraining the backbone. The evaluation covers five video understanding benchmarks, three video MLLM backbones, and several retention ratios.
Critical weaknesses
-
Limited novelty and outdated baseline model makes the missing performance comparisons important. I view this primarily as a performance-centered paper. The comparison should therefore include established, closely related methods with competitive published results. In particular:
- UniComp (CVPR 2026) reports a mean of 60.775 over LongVideoBench, EgoSchema, MLVU, and VideoMME on OneVision-7B with 32 frames at 25% retention, compared with 60.425 for VOLT on these four benchmarks. UniComp is higher on three of the four benchmarks. VOLT’s shared-four average is higher at 10% and 15%, so this is an omitted competitive comparison rather than evidence of general inferiority.
- MMG-Vid (AAAI 2026) reports LongVideoBench scores of 58.8/58.6/57.7/56.3 at 25/20/15/10% retention on LLaVA-Video-7B with 64 frames. VOLT Table 2 reports 57.8/57.5/56.0/55.5. Both report an uncompressed LongVideoBench score of 58.9. VOLT is higher on the other three shared benchmarks and their mean, but MMG-Vid remains a relevant missing quantitative comparison, especially since it is already discussed in Section 2.
I understand that these paper might have their own reimplementation of the compared methods. But considering the proximity of the topic, I think they should also be included in the main comparison. Or explained why they are excluded in the comparison.
-
I believe there is a factual error in Table 2 for the VisionZip entry. Its numbers are identical across the 25% and 15% retention settings. For such are large drop in the token count, it’s highly unlikely that the numbers would stay the same. Please check the presented numbers carefully.
-
The writing and presentation could be significantly improved.
-
Citation formatting needs systematic correction. Narrative author–year citations are repeatedly appended where parenthetical citations are needed. For example, Section 3.2, p4, line 200, reads “…token features Taskar (2013)” and later “…feature directions Boyd & Vandenberghe (2004).” The same pattern appears in the opening sentence of Section 1: “Recent video MLLMs Li et al. (2024a); Zhang et al. (2024b); … encode …”. These supporting citations should be placed in parentheses or integrated grammatically into the sentence.
-
The DPP reference has incorrect author and publication metadata. The bibliography on p11 lists “Alex Kulesza Ben Taskar” as one name and gives “stat, 1050:10, 2013.” The canonical journal reference is Alex Kulesza and Ben Taskar, Determinantal Point Processes for Machine Learning, Foundations and Trends in Machine Learning 5(2–3):123–286, 2012. The corresponding citation should name both authors. If the authors intend the 2013 arXiv revision, they should identify that version consistently.
-
Figure 2 should include the reservation stage. Its global-selection loop starts with an empty set, while Section 3.2 first reserves tokens independently per frame and initializes the global basis from their union. Adding this stage would make the actual sequence of operations more clear.
-
Table 6 does not sufficiently define its fusion variants. The distinction between “Within-frame avg.” and “Within-frame nbhd.” is unclear because Section 3.3 already averages tokens assigned to cosine-nearest representatives. “Cross-frame top-k” also lacks a specified . Please define or explain what’s be compared here.
-
The diagnostic figures need clearer definitions. For example, figure 1(b,c) does not specify the feature projection, the conditioning and normalization of “log-det gain,” or the variables and statistic behind the displayed correlation.
-
Questions for authors
- Can the authors provide matched comparisons with UniComp and MMG-Vid, including the evaluation settings and actual retained-token counts? Or explain the exclusion.
- Can the authors check the number presented in Table 2 for VisionZip?