- Rating
- 2
- Confidence
- 3
- Informativeness
- 1
- Presentation
- 3
- Soundness
- 2
Read review
Paper summary
The paper presents a method for in-contextl learning by training LoRAs and MoE-LoRAs on a text-to-image editing foundation model (Qwen-Image-Edit). The methods accomplished image analogy editing on some varied tasks (from depth estimation to image editing), and show the method generalizes to unseen image-editing tasks. This is done without any guidance from text.
Critical strengths
- The paper was written well and easy to follow. The method itself is quite simple.
- The method does not require text instructions (Although I have reservations about this, in the weaknesses section)
- The evaluation includes held-out styles, which is very important to see generalization, and is something sometimes missed by works. (I still have reservations in the weakness section)
- the performances compare to the baselines seem as well, qualitatively as well.
Critical weaknesses
- My main concern with the paper is its novelty. The task as described in sec 3.1 is essentially Image analogies (Hertzman et al. SigGraph 2001), which was studied extensively, including by using pretrained DiTs and adapting them with various LoRA based architectures (including MoE-LoRAs), but this and other seminal works in the field remain uncited. The paper doesn’t acknowledge any Image analogies works, and simply acknowledges in context learning. In-context learning can be considered a subset of image anaolgies, and even is a new, LLM-centric viewpoint. For example, the same task can be solved by patch-based methods (such as the original Hertzman et al. 2001). Image analogies should be discussed explicitly, and make the distinction to in-context learning based approaches.
- Importantly, this I think is the cause of missing so many highly related work, maybe the most is VisualCloze (Li et al. ICCV 2025), which solve many of the same tasks by adapting a DiT (Flux.1) with LoRAs. They also leverage 3D-RoPE for multi-image conditioning.
- The paper doesn’t acknowledge other DiT based editing works such as RelationAdapter (Gong et al. NeurIPS 2025) which investigate positional encoding for DiT-based editing or LoRWeB (Manor et al. ECCV 2026) which uses a similar mixture of LoRAs on DiTs.
- The paper compares to ICEdit (Zhang et al. NeurIPS 2025), but fails to mention it in the related work section, where it would highly be beneficial to distinguish it from ICEdit’s LoRA-MoE routing in DiTs.
- The authors claim in the last line of the abstract that their results show that one pre-trained DiT can support lots of visual transofmations. As expresses here, this is not the first time this was shown and cannot be claimed as a contribution.
- Of course, this translates to the much needed comparisons to the recent DiT-based analogy methods, rather than relying on the older baselines that currently the paper compares to.
- The proposed method doesn’t use text, and it’s true that recent analogy methods opt for text-based guidance as well, however, I’m not sure how much of a strength it really is. For starters, the used model is a text-to-image model, so there’s no need for additional training for text. This is related to the notion of how much info is present in . Specifically, while it might be difficult to describe all transformations exactly with text, text is usually very useful when given , without . This is especially important since it’s usually very hard to get paired source exemplars in the wild. For example, the third line in Fig1 shows masks and bounding boxes on an object, which can easily be described by text (mask the chicken, get the bounding box of the car). This might even be easier then extracting some bounding box or mask of the original image. Similarly with style transfer, usually the original image doesn’t hold any important information which isn’t shown already in . For example, the anime style applied in the bottom row can be inferred from alone. The added information from is that a hat was added and the mouth was opened for a smile. This also can be easily described in text. Practically speaking, usually in the real world you might even only have access to , and you’d want to “copy” the same edit to your own image, without any access to . Indeed, Tab 6 compares to baselines with text, but it doesn’t really reveal if is in itself necessary or the model just learned to imitatie directly. An experiment with mismatched exemplar pairs can help here, and even ablating what happens when a guiding text is given to Qwen (since it’s already built for it).
- Figure 4 seems weird to me. I went to the relevant tab 12 that shows the automatic text instructions given to the baslines, however they depict a description of the exemplar pair sometimes - instead of the transformation. For example, ‘replace the cupcake with a galaxy theme’ - when the query image is a cake. Applying these instructions might bias against methods that use these automatic prompt. Actually, this figure is very confusing to me, as it seems for example for this cake example only ICEdit actually used for editing. Specifically, it doesn’t look at all like galaxy cupcakes - but just blue cupcakes, yet somehow your and Qwen-Edit applied an unrelated galaxy edit. Did figure 4 actually use the prompts for your method? In any case, this casts doubts on the comparisons.
- While lineart is considered an unseen task, one of the trained tasks is edge detection. This means, in my opinion, it’s not really an unseen tasks as the 2 tasks are too similar. Additionally, since the training data also includes some stylization tasks, without the dataset being public here in this submission it’s hard to see if the evaluated data truly captures enough variety and if the unseen tasks are really unseen.
- I’d like to make the wording in the abstact a bit more nuanced. In the abstract L36 the authors frame in a sentence the framework as using just pretrained models. Only next it says it’s LoRAs instantiated from them. This can be misleading, and make it seem like it’s a zero shot method.
- A lot of the evaluation is heavily dependant on synthetic images, generated with Qwen. Then, the used model is Qwen as well. This introduces a bias risk where maybe the model is collapsed towards these results and no learning was actually really done.
- Similarly, this approach was trained and then tested on labels generated via ControlNetAux, but is compared to completely different methods trained on other datasets. This also introduces an evaluation bias towards the distribution of ControlNetAux.
- The B.2 appendix says tab 8 will include task sampling probabilities, noise-level distribution, etc. but it doesn’t?
Questions for authors
- You have tasks in the dataset such as pose estimation or segmentation but you do not report any metrics on them. Why?
- Table 10 says ‘category and fold selection’ yet the word fold appears once in the entire manuscript - what fold do you mean here? I'd also appreciate answers regarding my concerns in the weakness section.