- Rating
- 2
- Confidence
- 2
- Informativeness
- 2
- Presentation
- 3
- Soundness
- 2
Read review
Paper summary
This paper studies expert mixed-precision quantization for multimodal MoE. MDMixQ separates routing statistics by modality, filters confidence, and corrects the estimated importance of experts, then assigns different weight precisions to experts on the text side. The experiments cover three backbone models.
Critical strengths
-
The importance estimator can simply use the routing output, without computing gradients or extracting quantization errors from each expert one by one. The allocation logic is also simple and easy to understand. It maintains good retention while covering multimodal scenarios, making it quite convincing.
-
The calibration experiments distinguish between “text-side routing statistics” and “pure text input,” making comparisons easier. These conclusions about how modality-aware quantization is actually implemented are quite valuable as a reference.
Critical weaknesses
- My main concern is novelty. PreMoE has employed Top-K local softmax and average maximum probability threshold. These are highly consistent with SGFR, but the paper does not discuss the relationship between the two. Modal separation statistics and two-level bit allocation based on sorting have precedents in MODE and METGG as well. As it is currently written, the novelty in the method is not as great as the contribution statement suggests.
- The adaptation part of MODE and MBQ is not clearly explained. Neither does it specify exactly which original components are retained, nor does it clarify how each method is transformed into an expert priority baseline.
Questions for authors
1.What are the differences between the PEU process of SGFR and PreMoE v2? 2. Compared with the modal separation statistics in MODE and the bit allocation based on sorting in METGG, which parts of MDC and DMA are new? 3. How do MODE and MBQ adapt to the shared quantizer and expert weight budget?
4 comments
Q2 — Contributions of MDC and DMA relative to MODE and METGG
We will distinguish the importance signal from the allocation operation:
| Component | Relationship to prior work | Role in MDMixQ |
|---|---|---|
| MDC relative to MODE | Both preserve modality-specific routing statistics | Maintains separate text and non-text accumulators and uses text-side salience for the default allocation; non-text reservation is evaluated separately |
| DMA relative to METGG | Ranking-based precision allocation also appears in prior work | Uses text-anchored salience to assign -bit expert precision under the fixed global budget |
MDC supplies modality-separated calibration statistics, and DMA converts the resulting text-side salience into precision assignments under the budget. We will state these roles explicitly in the revision.
W2 & Q3 — MODE and MBQ adaptations
Within each quantizer setting, the controlled comparisons use the same calibration examples, quantizer configuration, target average expert bits, and evaluation within each backbone. Methods differ in importance estimation and allocation.
| Method | Retained or transferred information | Adaptation to the shared pipeline |
|---|---|---|
| MODE | Modality-decomposed frequencies, key-vision-token filtering, per-expert quantization sensitivity, and ILP allocation | These importance and allocation components are retained, with ILP choices restricted to as in MDMixQ. The original GPTQ stage is replaced by the shared quantizer. |
| MBQ | Calibration sensitivity | Sensitivity is converted into expert-level importance and used to assign expert precision under the shared budget and quantizer. |
MBQ uses calibration sensitivity to construct expert importance for precision allocation. MODE remains a sensitivity-aware, ILP-based baseline in our evaluation. We will state these adaptations explicitly in the revised experimental setup. The additional matched GPTQ comparison on Qwen3-VL preserves MODE's GPTQ stage under the stated calibration and bit-budget constraints: MDMixQ + GPTQ achieves 97.85% Retain versus 96.52% for MODE + GPTQ. Retain and end-to-end calibration/quantization time are reported in the response to Reviewer Whd7.
Thank you for the clarification. The response to W2/Q3 resolved my concern. The response to W1/Q1 confirmed that the novelty is limited. Q2 did not point out any new operations; it merely restated the roles of the components. In summary, the main difference is the design choice of “using text-side saliency for assignment.” I believe my initial score was reasonable, and I will maintain my original main score.
W1 & Q1 — Relationship to PreMoE and multimodal extensions
We thank the reviewer for pointing out that this relationship was insufficiently explained. MDMixQ is follow-up work building on PreMoE v2, extending its Predicted Expert Utility (PEU) approach to multimodal MoE mixed-precision quantization. SGFR adapts PEU's local Top-K softmax, adaptive confidence threshold, and logit transformation. Both approaches aggregate importance over offline calibration data.
Our extensions are modality-decoupled collection and modality-conditioned scoring, text-prioritized allocation of expert-weight precision under a global budget, and the study of asymmetric activation precision within MoE layers. MDMixQ retains the experts and their native routing configuration while assigning heterogeneous weight precision. The NT4/T8 extension additionally provides operator implementation guidance and NPU measurements.
We will explicitly attribute the shared PEU operations to PreMoE and substantially revise the related work, methodology, and contribution statements to explain MDMixQ as a multimodal quantization extension. The ablations quantify the benefit of applying these operations within our multimodal quantization framework.