- Rating
- 3(+1)
- Confidence
- 3
- Informativeness
- 2
- Presentation
- 2
- Soundness
- 2(+1)
Read review
Paper summary
This paper proposes QCPruner, a training-free visual token pruning method that integrates query-conditioned utility into a facility-location coverage objective. The method combines hidden-state similarity and query–key alignment to guide token selection, and demonstrates strong performance retention across four MLLM backbones under aggressive compression.
Critical strengths
-
The paper addresses a practical problem and achieves strong performance across multiple MLLMs and benchmarks, particularly under aggressive token compression.
-
The experimental evaluation is fairly comprehensive, including component ablations, controlled selector comparisons, pruning-layer analysis, and computational cost measurements.
Critical weaknesses
-
The QCPruner-Early comparison in Table 3 does not isolate the effect of pruning depth, since this variant also changes the selection objective and removes query conditioning. I would like to see a comparison using the same visual-only coverage objective at different pruning layers.
-
The necessity of bilateral utility weighting is not sufficiently justified. Table 4 shows that representative-only weighting already achieves nearly identical performance on Qwen2.5-VL, while the theoretical guarantee is inherited from standard facility-location optimization.
-
Table 5 measures the effect of removing high-utility tokens on output KL divergence, but does not directly validate whether QCPruner preserves query-relevant visual evidence.
-
The paper lacks controlled experiments on relational questions, negation, prompt paraphrases, and multilingual queries, where unigram extraction may miss important semantic information.
-
The accuracy–efficiency trade-off needs further evaluation. In Table 3, QCPruner requires 11.1 TFLOPs and 127.5 ms of prefill compared with DivPrune's 5.0 TFLOPs and 41.8 ms; accuracy–latency curves across different budgets and backbones would be more informative.
Questions for authors
pls see weakness