- Rating
- 1
- Confidence
- 4
- Informativeness
- 1
- Presentation
- 2
- Soundness
- 1
Read review
Paper summary
This paper proposes StreamPrune, a training-free and query-free token pruning module for streaming video MLLMs. TTS keeps a token only when its cosine distance to the last kept token at the same position exceeds τ. CAC then packs the kept tokens across frames into 196-token blocks. With ReKV-7B at 1 FPS, the paper reports a 92.6% token reduction, 6.18× higher throughput and an average accuracy drop of 0.8 points over six benchmarks at τ=0.70. The authors claim that it outperforms existing pruning methods on StreamingBench and StreamBench.
Critical strengths
- The method is causal, query-free and training-free, which fits the streaming setting. It can be added to ReKV without changing any model weights, so it is easy to deploy.
- At τ=0.50, the KV-cache growth drops from 37.7 to 10.6 GB/h, while the average accuracy is the same as the unpruned model. This memory saving is the main practical benefit.
Critical weaknesses
- All three abstract numbers use τ=0.70, but StreamBench accuracy at this τ is 5.3 points below unpruned ReKV in Table 4a. In addition, three Avg values in Tables 7 and 8 differ from their sub-task means while other rows match. ReKV should be 64.4 and 46.7, not 63.0 and 45.7, and StreamPrune should be 45.1, not 45.4. These three errors all favor StreamPrune. Both problems are the main reason for my soundness score.
- The core change of TTS over RLT brings little gain. In Table 4a, prev is the rule of RLT, and ref differs from it by only −0.6 to +1.4 points for τ≤0.70. The ref rule clearly leads only at τ≥0.80, where both rules are below 60. This limits the novelty of the paper.
Questions for authors
- Table 2a has no pruning baseline, and Tables 2 and 3b only compare methods at τ≤0.60. Can RLT and TimeChat-Online be added as baselines on both benchmarks, and can all methods be compared at τ=0.70?
- CAC adds 1.5 points in Table 4b. Do the baselines in Table 2b also use CAC and the same token budget?
- Which τ is used in Tables 7 and 8, and why is unpruned ReKV 70.3 on StreamingBench in Table 3a but 69.1 elsewhere?
- What causes the drops of about 10 points on STU and HLD in Tables 7 and 8?
- Although the introduction uses denser frame sampling as the motivation, all experiments use 1 FPS. It would be better to compare StreamPrune at 2 to 4 FPS with unpruned ReKV at 1 FPS under matched throughput.