- Rating
- 3(+1)
- Confidence
- 4
- Informativeness
- 2
- Presentation
- 2
- Soundness
- 2
Read review
Paper summary
This paper proposes NEOPrune, a training-free token pruning method for omni-modal large language models (OmniLLMs). It estimates token replaceability through the reconstruction error of layer-wise orthogonal updates. Before the LLM, it combines within-modality reconstruction with encoder attention to select audio and video tokens. Inside the LLM, it progressively prunes video tokens using audio-conditioned reconstruction and text-query attention. Experiments cover four audio-visual benchmarks, primarily using Qwen2.5-Omni, with additional Qwen3-Omni results on AVUT.
Critical strengths
-
The paper is readable and clearly presented. The two-stage framework and reconstruction-based selection criteria are generally easy to follow.
-
The motivation is reasonably clear. Assessing whether several tokens can collectively explain another token provides a sensible approach to identifying redundancy beyond pairwise similarity.
Critical weaknesses
-
The model coverage remains limited. Although Appendix A.8 includes Qwen3-Omni-30B-A3B-Instruct, its evaluation is restricted to AVUT, without corresponding efficiency measurements. The authors should extend this evaluation across the other benchmarks and report latency and memory usage to establish broader applicability.
-
The baseline comparison is insufficiently comprehensive. Although FastV and DyCoke are included, representative methods such as VisionZip [1], VidCom2 [2], HoliTom [3], and OmniSIFT [4] are missing. Comparisons should assess both accuracy and efficiency under clearly specified, comparable budgets.
-
The task coverage is too narrow. The evaluation focuses on audio-visual QA without assessing temporal grounding or caption generation. Experiments on LongVALE [6] and AVSCapBench [7] would help establish whether compression preserves temporal evidence and detailed audio-visual information.
-
The modest accuracy gains come with higher latency, leaving the practical advantage unclear. In Table 2, at 35% retention, NEOPrune achieves 46.50% accuracy versus 45.30% for OmniZip and 45.55% for DASH, gains of only 1.20 and 0.95 percentage points. However, its latency increases to 5.02 s from 4.40 s and 4.56 s, respectively. Its prefill time is also 25.0% and 21.3% higher. This pattern persists in Appendix Table 6: average latency over 30 videos is 20.4% and 22.5% higher than the two baselines. Comparisons at matched accuracy or latency, together with a breakdown of reconstruction overhead, are needed to establish a convincing accuracy–efficiency advantage.
[1] Senqiao Yang, Yukang Chen, Zhuotao Tian, Chengyao Wang, Jingyao Li, Bei Yu, and Jiaya Jia. VisionZip: Longer is Better but Not Necessary in Vision Language Models. CVPR, 2025.
[2] Xuyang Liu, Yiyu Wang, Junpeng Ma, and Linfeng Zhang. Video Compression Commander: Plug-and-Play Inference Acceleration for Video Large Language Models. EMNLP, 2025.
[3] Kele Shao, Keda Tao, Can Qin, Haoxuan You, Yang Sui, and Huan Wang. HoliTom: Holistic Token Merging for Fast Video Large Language Models. NeurIPS, 2025.
[4] Yue Ding, Yiyan Ji, Jungang Li, Xuyang Liu, Xinlong Chen, Junfei Wu, Bozhou Li, Bohan Zeng, Yang Shi, Yushuo Guan, Yuanxing Zhang, Jiaheng Liu, Qiang Liu, Pengfei Wan, and Liang Wang. OmniSIFT: Modality-Asymmetric Token Compression for Efficient Omni-modal Large Language Models. ICML, 2026.
[5] Tiantian Geng, Jinrui Zhang, Qingni Wang, Teng Wang, Jinming Duan, and Feng Zheng. LongVALE: Vision-Audio-Language-Event Benchmark Towards Time-Aware Omni-Modal Perception of Long Videos. CVPR, 2025.
[6] Yanghai Wang, Jiahao Wang, Jiafu Tang, Yuanxing Zhang, Zhe Cao, Hanyan Bian, Zijie Zhang, Weiliang Luo, Zhiyu Pan, Zixuan Dong, Jiaheng Liu, and Zhaoxiang Zhang. AVSCap: Orchestrating Audio-Visual Synergy for Omni-modal Video Captioning. arXiv:2607.12820, 2026.
Questions for authors
Could the authors provide broader model, baseline, and task evaluations, together with efficiency comparisons at matched accuracy, to demonstrate the general applicability and practical advantages of the proposed method?
7 comments
Response to Reviewer vF4B — Part 1 of 4
1. Broader evaluation and efficiency on Qwen3-Omni-30B (W1 & Q)
W1: The evaluation of Qwen3-Omni-30B-A3B-Instruct is restricted to AVUT and lacks corresponding efficiency measurements. Broader benchmark coverage and efficiency results are needed to assess the applicability and practical benefits of NEOPrune on the larger model.
Q: “Could the authors provide broader model, baseline, and task evaluations, together with efficiency comparisons at matched accuracy, to demonstrate the general applicability and practical advantages of the proposed method?”
Response:
We agree that broader model evaluation should include both accuracy and practical inference costs. Using Qwen3-Omni-30B-A3B-Instruct and the same experimental setup as in the paper, we extended the accuracy evaluation beyond AVUT to ShortVid. The AVUT evaluation for Qwen3-Omni used 1,729 QA pairs. Table 1 reports accuracy on both benchmarks at 45% and 35% AV token retention, with newly added VidCom2 results at both ratios and a full-token (100% retention) reference. Table 2 provides inference latency and LLM prefill measurements on AVUT.
Table 1. Accuracy of Qwen3-Omni-30B-A3B on AVUT and ShortVid
| Method | AV token retention (%) | AVUT accuracy (%) | ShortVid accuracy (%) |
|---|---|---|---|
| Full | 100 | 77.3 | 74.9 |
| NEOPrune | 45 | 76.5 | 74.7 |
| NEOPrune | 35 | 75.8 | 74.5 |
| OmniZip | 45 | 75.7 | 74.6 |
| OmniZip | 35 | 74.6 | 73.8 |
| DASH | 45 | 75.2 | 74.7 |
| DASH | 35 | 74.2 | 73.4 |
| VidCom2 | 45 | 76.2 | 74.1 |
| VidCom2 | 35 | 75.4 | 73.6 |
Bold accuracy values indicate the highest observed accuracy among the compression methods at each retention ratio.
The full-token reference achieves 77.3% accuracy on AVUT and 74.9% on ShortVid. At 45% retention, NEOPrune achieves 76.5% and 74.7%, respectively, corresponding to differences of 0.8 and 0.2 percentage points from full-token inference. At 35% retention, it achieves 75.8% and 74.5%, with differences of 1.5 and 0.4 percentage points.
At 35% retention, NEOPrune’s observed accuracy is 1.2, 1.6, and 0.4 percentage points higher than OmniZip, DASH, and VidCom2, respectively, on AVUT. On ShortVid, it is 0.7, 1.1, and 0.9 percentage points higher than OmniZip, DASH, and VidCom2, respectively. At 45% retention, NEOPrune also has higher AVUT accuracy than all three baselines, exceeding VidCom2 by 0.3 percentage points, and matches DASH at 74.7% on ShortVid. These results extend the evidence for the larger model to a second benchmark.
For the efficiency evaluation on AVUT, all methods used the same 60 inputs, and each input was measured three times. Model inference latency and LLM prefill are reported as the mean standard deviation across the three measurements, in seconds and milliseconds, respectively. Table 2 reports results at 45% and 35% retention.
Table 2. Accuracy and inference efficiency on AVUT at 45% and 35% retention
| Method | AV token retention (%) | Accuracy (%) | Model inference latency (s) | LLM prefill (ms) |
|---|---|---|---|---|
| Full | 100 | 77.3 | ||
| NEOPrune | 45 | 76.5 | ||
| NEOPrune | 35 | 75.8 | ||
| OmniZip | 45 | 75.7 | ||
| OmniZip | 35 | 74.6 | ||
| DASH | 45 | 75.2 | ||
| DASH | 35 | 74.2 | ||
| VidCom2 | 45 | 76.2 | ||
| VidCom2 | 35 | 75.4 |
On AVUT, NEOPrune achieves the highest accuracy among the compared compression methods at both retention ratios: 76.5% at 45% retention and 75.8% at 35% retention. Its inference latencies are 1.563 s and 1.475 s, respectively, compared with 1.433–1.464 s and 1.376–1.411 s for the baselines. NEOPrune thus offers higher accuracy at broadly comparable inference latency, with an additional 64–130 ms in these settings. Both configurations also have lower inference latency and LLM prefill time than the full-token reference shown in Table 2.
We will incorporate the additional ShortVid accuracy results, full-token accuracy references for both benchmarks, and AVUT efficiency measurements into the revised manuscript. These additions broaden the accuracy evaluation of Qwen3-Omni-30B-A3B and quantify its inference costs on AVUT.
Response to Reviewer vF4B — Part 2 of 4
2. Baseline comparisons and accuracy–efficiency analysis (W2, W4 & Q)
W2 & W4: Comparisons with representative token compression methods are insufficient, and NEOPrune’s accuracy gains at matched token retention come with higher latency, leaving its practical advantage unclear. Additional baselines under comparable budgets, efficiency comparisons at matched accuracy or latency, and an analysis of the additional cost are needed.
Q: “Could the authors provide broader model, baseline, and task evaluations, together with efficiency comparisons at matched accuracy, to demonstrate the general applicability and practical advantages of the proposed method?”
Response:
We agree with the reviewer that the range of baselines should be expanded and that accuracy should be evaluated together with actual inference latency. We therefore additionally evaluated VidCom2, one of the methods suggested by the reviewer, and compared it with the existing baselines at matched token retention and at similar accuracy or latency.
OmniSIFT [1] requires additional training. As our study focuses on training-free token compression, we restrict our baseline comparisons to training-free methods.
The additional experiments used Qwen2.5-Omni-7B and the same evaluation protocols as in the paper. Table 3 compares NEOPrune, OmniZip, DASH, and VidCom2 on four benchmarks at AV token retention ratios of 45% and 35%, alongside a full-token reference.
Table 3. Accuracy on four benchmarks with the additional baseline
| Method | AV token retention (%) | AVUT (%) | WorldSense (%) | ShortVid (%) | VideoMME (%) |
|---|---|---|---|---|---|
| Full | 100 | 64.5 | 46.8 | 70.5 | 66.0 |
| NEOPrune | 45 | 64.2 | 46.7 | 70.3 | 66.4 |
| NEOPrune | 35 | 63.3 | 46.5 | 69.7 | 66.5 |
| OmniZip | 45 | 63.0 | 45.9 | 69.9 | 66.3 |
| OmniZip | 35 | 61.0 | 45.3 | 69.0 | 66.1 |
| DASH | 45 | 63.5 | 45.9 | 69.9 | 66.4 |
| DASH | 35 | 61.5 | 45.6 | 69.4 | 66.7 |
| VidCom2 | 45 | 63.0 | 46.2 | 68.5 | 66.2 |
| VidCom2 | 35 | 61.6 | 45.7 | 65.8 | 66.3 |
Bold values indicate the highest accuracy among the compression methods at each retention ratio.
NEOPrune achieved higher observed accuracy than VidCom2 on all four benchmarks at both retention ratios. At 45% retention, the gains on AVUT, WorldSense, ShortVid, and VideoMME were 1.2, 0.5, 1.8, and 0.2 percentage points, respectively; at 35%, they were 1.7, 0.8, 3.9, and 0.2 percentage points. These results provide additional evidence of NEOPrune’s ability to preserve accuracy beyond the existing comparisons with OmniZip and DASH.
We thank the reviewer for the constructive feedback and for recognizing the motivation behind our reconstruction-based approach. We appreciate the call for a more rigorous evaluation of NEOPrune’s broader applicability and practical accuracy–efficiency trade-offs. We are currently conducting additional experiments to address these concerns. As an initial update, we plan to share verified results on additional datasets and comparisons with relevant existing methods under clearly specified, comparable budgets as soon as they become available. We will provide further results and analysis as the ongoing experiments are completed. Thank you for your patience and for the suggestions that are helping us strengthen the empirical evaluation.