- Rating
- 2
- Confidence
- 3
- Informativeness
- 2
- Presentation
- 2
- Soundness
- 2
Read review
Paper summary
This paper studies whether post-training updates learned by an autoregressive (AR) language model remain useful after that model has been converted into a diffusion language model. A2D applies an AR task vector to the diffusion base model and, when a diffusion-post-trained checkpoint is available, interpolates the AR and diffusion updates. Both operations work directly in weight space and require no further training.
Critical strengths
-
The question is timely and practically motivated. Diffusion models often inherit AR pretrained weights, while useful AR post-trained checkpoints are also available but are seldom reused after conversion. The proposed method is simple and has no additional inference-time computation once the weights are merged.
-
The controlled experiments train matched AR and diffusion models on the same math or code data, making a reasonable case that the AR update itself can survive diffusion conversion. The finding that the two updates are nearly orthogonal in parameter space but induce more aligned representation changes is also interesting.
Critical weaknesses
-
The methodological novelty of A2D-Transfer is limited relative to AR-MAP[1], which already applies an AR post-training task vector to diffusion checkpoints. The broader evaluation is valuable, but the paper should distinguish this empirical extension more clearly from the previously established transfer operation.
-
A2D-Merge is a linear interpolation of two weight updates. Its interesting contribution is the observed compatibility of AR and diffusion updates for the same capability, rather than a new merging algorithm. Comparisons with adding a tuned AR update directly to the post-trained diffusion model across non-anchor benchmarks would better isolate this claim.
Lin, Liang, et al. "AR-MAP: Are Autoregressive Large Language Models Implicit Teachers for Diffusion Large Language Models?." arXiv preprint arXiv:2602.02178 (2026).
Questions for authors
- What precisely does A2D-Transfer establish beyond AR-MAP? A comparison on a shared Dream setting or a more explicit discussion of why the settings cannot be matched would help define the incremental contribution.
- How does A2D-Merge compare across the non-anchor benchmarks with simply adding a tuned AR vector to the already post-trained diffusion checkpoint? The appendix studies this alternative on anchor tasks, but a full side-by-side comparison would show what replacing part of the diffusion update contributes.
3 comments
Rebuttal - part 2
W2/Q2: Direct addition versus A2D-Merge.
We thank the reviewer for this insightful suggestion.
Comparison with direct addition. Following the notation in our manuscript, we refer to the baseline for adding an AR update to the post-trained diffusion model as “+τ_A only”. Based on the reviewer’s suggestion, we extended these ablations to non-anchor benchmarks, including diffusion-only downscaling as a control (denoted as “−τ_D only”). The results are summarized below. Results cover 7 anchor and 21 non-anchor model–benchmark evaluations with complete ablations. Wins indicate strict improvements over the diffusion parent.
| Method | Anchor avg. | Non-anchor avg. | Overall avg. | Wins vs. parent |
|---|---|---|---|---|
| Diffusion parent | 72.3 | 52.2 | 57.3 | — |
| +τ_A only | 75.8 | 55.1 | 60.3 | 19/28 (67.9%) |
| −τ_D only | 74.1 | 52.9 | 58.2 | 20/28 (71.4%) |
| A2D-Merge | 76.8 | 55.3 | 60.7 | 27/28 (96.4%) |
On non-anchor benchmarks, A2D-Merge achieves higher average performance than +τ_A only (55.3 vs. 55.1). More importantly, its gains are substantially more consistent: A2D-Merge improves upon the diffusion parent in 20/21 evaluations (95%), tying it in the remaining one, whereas +τ_A only improves performance in only 14/21 (67%).
Across all 28 evaluations, both +τ_A only and A2D-Merge provide larger average gains over the parent than diffusion-only downscaling (+3.0 and +3.4 vs. +0.9 percentage points), highlighting the importance of incorporating AR updates. Globally, A2D-Merge achieves the highest overall average performance and improves upon the parent in 27/28 evaluations, compared with 19/28 improvements for +τ_A only and 20/28 for downscaling alone.
Notably, the +τ_A only baseline also falls within our framework of AR-to-diffusion post-training merging. It combines the same two updates but adopts a different merging strategy that fixes the diffusion update coefficient at 1. These results support our design choice of jointly rebalancing AR and diffusion updates for more consistent gains. We will include these expanded anchor and non-anchor ablations in the revised manuscript.
Choice of linear interpolation. While A2D uses simple and direct linear interpolation, we have additionally experimented with more advanced model merging techniques including TIES [1] and DARE [2], and the results demonstrate that these methods do not further enhance the performance of A2D, partially supporting the observed compatibility of AR and diffusion updates, and our choice for linear interpolation.
| Model | τ_D / τ_A weights | IFEval | MATH-500 | MBPP+ | Average |
|---|---|---|---|---|---|
| Transfer | |||||
| Dream-7B Base | 0 / 0 | 49.7 | 20.8 | 59.3 | 43.3 |
| TIES | 0 / 0.9 | 55.5 | 36.4 | 61.9 | 51.3 |
| DARE | 0 / 0.8 | 60.3 | 35.4 | 60.6 | 52.1 |
| A2D (transfer) | 0 / 0.9 | 59.2 | 40.2 | 62.7 | 54.0 |
| Merge | |||||
| Dream-7B Instruct | 1 / 0 | 63.0 | 38.4 | 57.1 | 52.8 |
| TIES | 0.8 / 0.2 | 63.6 | 43.8 | 57.9 | 55.1 |
| DARE | 0.1 / 0.9 | 47.3 | 35.8 | 61.6 | 48.2 |
| A2D (merge) | 0.4 / 0.6 | 72.8 | 45.0 | 58.7 | 58.8 |
We hope this effectively addresses the reviewer’s concerns and remain available for any further discussion or clarification.
[1] TIES-Merging: Resolving Interference When Merging Models, Yadav et al., NeurIPS 2023.
[2] Language Models are Super Mario: Absorbing Abilities from Homologous Models as a Free Lunch, Yu et al., ICML 2024.
Gentle Follow-up
Dear Reviewer,
We wanted to follow up on whether our responses have addressed your concerns. We would be happy to address any remaining questions before the discussion period ends.
Thank you again for your valuable feedback and for your time.
Best regards, The Authors
Rebuttal
We thank the reviewer for their valuable feedback and recognition of our method's simplicity, practical motivation, and interesting findings. Below, we address their comments and questions.
W1/Q1: Relationship and comparisons to AR-MAP.
We thank the reviewer for highlighting this connection. We acknowledge and respect AR-MAP’s contribution to transferring AR updates in the DPO setting and explicitly discussed it in the manuscript. A2D-Transfer and AR-MAP both build on Task Arithmetic and share the same task-vector addition operation. Our main contribution, as correctly summarized by the reviewer, lies in systematically establishing and studying the recycling and compatibility of AR post-training updates to enhance diffusion models, rather than introducing a new merging method.
However, the two works address different research questions and differ in their scope. AR-MAP targets the difficulty of estimating likelihoods for diffusion during specifically the DPO stage: its workflow trains an AR donor with DPO and transfers the update as an alternative to diffusion-specific preference training. In contrast, the main motivation for A2D is to leverage the rich ecosystem of existing AR post-training checkpoints to further enhance diffusion models across post-training stages without training. Our extensive evaluations demonstrate the broad applicability of A2D across model scales, diverse post-training paradigms including instruction tuning, reasoning, and RL, and specialized domains such as coding and medical VQA.
Importantly, A2D goes beyond empirical demonstration of transferring by systematically investigating the relationship and complementarity between the two post-training processes. As the reviewer also appreciates, our controlled experiments reveal that the two updates are nearly orthogonal in parameter space yet induce more aligned representation changes. These findings motivate A2D-Merge, which combines independently acquired post-training gains to further improve diffusion-post-trained models, rather than merely replacing diffusion-specific training. This progression from transfer to complementary post-training composition is central to A2D's contribution.
We illustrate the distinctions in the shared Dream model family. AR-MAP trains an AR DPO update and transfers it to Dream-7B-Instruct for preference alignment. In contrast, A2D aims to leverage the broader existing AR post-training ecosystem, directly reusing released checkpoints such as Qwen2.5-7B-Instruct to transfer instruction-tuning capabilities to Dream-7B-Base. Going one step further, A2D-Merge combines this AR update with Dream's own instruction-tuning update, achieving further improvements over both A2D-Transfer and Dream-7B-Instruct.
Following the reviewer’s suggestion, we will add a dedicated section in the revised manuscript to more clearly compare and distinguish A2D from AR-MAP.