- Rating
- 1
- Confidence
- 2
- Informativeness
- 1
- Presentation
- 2
- Soundness
- 2
Read review
Paper summary
This paper propose DepGraph-U, a training-free inference-efficiency framework for unified multimodal models. The authors argue that unified models may execute unnecessary computation for outputs that are not requested or consumed, and propose dependency-aware execution mechanisms to skip such computation. The main implementation and evaluation are centered on the Show-o2 architecture
Critical strengths
- The farmwork accelerates the efficiency while can preserve the performance
- The experiments and internal ablations are extensive.
Critical weaknesses
-
Limited novelty: The high-level motivation of training-free, task-aware acceleration for unified multimodal models has already been explored by Flash-Unified [1]. In fact, DepGraph-U builds on several FlashU mechanisms, including FFN pruning, dynamic layer selection, visual-token pruning, and diffusion-head caching. The primary additional contribution is therefore execution-level dependency analysis that removes computation remaining unnecessary after an acceleration policy has already been selected. While this distinction is valid, some proposed mechanisms, such as checking a valid cache before executing its unused producers or bypassing an unused vocabulary projection, appear relatively straightforward from a systems perspective.
-
Limited architectural generalization: Although the dependency-analysis principle is presented as general, the concrete mechanisms are strongly tailored to Show-o2 [2]. CADD relies on Show-o2's Head-A/Head-B caching structure, VocabBypass targets a vocabulary projection that other architectures may already avoid, and Exact-DLS is specifically designed around the selected dynamic layer-selection and pruning policy. Thus, applying the framework to another unified architecture requires a new architecture-specific dependency audit and potentially different execution rewrites.
-
Limited additional benefit on newer/different unified architectures. the new generation of unified model does not need this framwork. For exampl,in BAGEL[2], several targeted inefficiencies already do not exist: vocabulary projection is already avoided for image calls, native KV is available, and the architecture does not share the same two-part diffusion-head structure. Consequently, the applicable new generation rewrite alone provides almost no additional acceleration in the reported native BAGEL control. This makes it unclear whether DepGraph-U is a broadly applicable acceleration technique or primarily a systematic methodology for finding architecture-specific
-
Paper presentation and clarity. The paper is poorly presented and, in its current form, does not meet the presentation standards expected of a top-tier conference such as ICLR. For example, the motivation for the proposed approach is not clearly articulated.
[1] J. Ke, etal, Flash-unified: A training-free and task-aware acceleration framework for native unified models,CVPR, Findings, 2026.
[2] J. Xie, Z. Yang, and M. Z. Shou, “Show-o2: Improved Native Unified Multimodal Models,” NeurIPS 2025
[3] Ch. Deng, et. Al, ‘Emerging properties in unified multimodal pretraining’, 2025, arxiv.
Questions for authors
Please see the weaknesses.
4 comments
Response to Reviewer 7x6t (2/4): W2, architectural generalization
W2. Limited architectural generalization
We agree that each rewrite has to be instantiated per architecture, and Sec. 5 says so. But the three patterns are less tied to Show-o2's structure than the main text made them look. Taking your three examples in turn:
- CADD does not need the Head-A/Head-B split. The pattern is to test the guard of a cached or predicted state before running the producers that this state replaces. OmniGen2 (a separate MLLM and diffusion transformer) has no Head-A/B. There the same pattern skips the context refiners on TaylorSeer-predicted steps, which gives 1.12× on full GenEval and DPG-Bench with matching paired outputs (Table A13).
- VocabBypass is not always already there. BAGEL does avoid the projection, and we credit no gain for it. Lumina-DiMOO does not: with its shared vocabulary, text logits are computed on every image call. Restricting the head to the image-token slice gives 1.06× with identical outputs, with or without ML-Cache (Table A12).
- Exact-DLS is specific to policies that re-select layers during decoding. We agree, and we do not claim more. Stable-Graph KV covers static pruning (FFN and visual tokens) and does not depend on DLS.
In the table, "Lines" is the number of inserted lines of rewrite code, and the BAGEL number is from the 12-prompt control of Appendix I.4.
| Model (accelerator) | Pattern that applied | Lines | GenEval / DPG | Paired outputs |
|---|---|---|---|---|
| OmniGen2 (TaylorSeer) | CADD (refiners on predicted steps) | 17 | 1.116× / 1.117× | match |
| Lumina-DiMOO (ML-Cache) | VocabBypass (image-token slice) | 13 | 1.062× / 1.061× | match |
| BAGEL (none) | skip an unconsumed CFG prefill | 33 | 1.0001× | 36/36 identical |
So a new architecture does need its own audit. The audit follows the same four steps each time (Appendix A.1), and the resulting rewrite was 13–33 inserted lines per model. These results appeared only in Appendix I.5, and we will move them into the main text.
Response to Reviewer 7x6t (3/4): W3, newer architectures
W3. Limited additional benefit on newer or different architectures
BAGEL is the boundary case of the paper, and we included it for that reason. On your question of whether DepGraph-U is a broadly applicable acceleration technique or a methodology for finding architecture-specific inefficiencies: it is the second, with three rewrite patterns that recur across models. Its gain on a model equals the unconsumed work that model executes, and the audit reports that amount before any engineering is done. Of the four models we audited, three execute a measurable amount of such work. All gains below preserve the outputs.
| Model (release) | Unconsumed work found by the audit | Gain |
|---|---|---|
| Show-o2 (June 2025) + FlashU | producers before 14 of 34 hits; unused text logits | 1.61–1.77× |
| OmniGen2 (June 2025) + TaylorSeer | context refiners on predicted steps | 1.12× |
| Lumina-DiMOO (Oct. 2025) | text-vocabulary slice on image calls | 1.06× |
| BAGEL (May 2025) | one duplicate CFG prompt prefill | 1.0001× |
We do not think "the new generation does not need this" follows, for two reasons.
First, release date does not predict it. BAGEL (May 2025) appeared before Show-o2 (June 2025), and both OmniGen2 and Lumina-DiMOO appeared after BAGEL and still execute unconsumed work.
Second, the waste tends to come back when a caching or prediction accelerator is added to a model. In both cases we studied (FlashU's head cache on Show-o2 and TaylorSeer on OmniGen2), producers keep running ahead of a state that replaces them. Such accelerators are a common way to speed up diffusion-based generation, so we expect the pattern to recur.
Finally, because every rewrite preserves outputs, applying the audit carries no quality risk even when the gain is small. On BAGEL the outcome is 1.0001× with 36/36 pixel-identical images, not a degraded model. We will state this scope in the abstract and introduction.
Response to Reviewer 7x6t (4/4): W4, presentation
W4. Paper presentation and clarity
We take this seriously and will restructure the paper. The motivation can be stated in three sentences, and the revised introduction will open with them.
A unified model shares one inference path between understanding and generation, so a request can execute operators whose outputs it never reads. In FlashU-accelerated Show-o2, an image request spends 38–44% of its time this way: on 14 of 34 denoising calls the trunk is run and its result discarded because a cached head output is used instead, and every trunk call computes logits over the text vocabulary although only pixels are requested. DepGraph-U finds such operators with an output- and state-dependency audit and removes them behind guards, which makes the system 1.61–1.77× faster without changing a single output pixel.
Concretely, we will (1) open the introduction with this example and a table that separates FlashU's factor from ours; (2) lead the abstract with the fixed-policy result and present 2.88–3.21× as its composition with FlashU; (3) move the transfer results and Table A8 into the main text; (4) replace the qualifications repeated through Sec. 4 with one limitations paragraph; and (5) add the applicability guidance for the understanding policies.
We hope this clarifies the contribution and its scope.
Response to Reviewer 7x6t (1/4): W1, novelty
Thank you for the review. We respond to the four weaknesses in order.
W1. Limited novelty
We agree with your description of what the paper adds: an execution-level dependency analysis that removes computation which is still unnecessary after an acceleration policy has been chosen. FlashU and DepGraph-U answer different questions.
We also agree that the two generation rewrites are simple to state. That is not the same as being known, or easy to get right, for three reasons.
The simplicity also has a practical side: the rewrites change no weights and no outputs, so they can be added to an existing accelerator without any quality risk. We will add a comparison with FlashU to Sec. 2 and lead the abstract with the fixed-policy factor.