Asset Details
Do you wish to reserve the book?
Attention re-alignment in multimodal large language models via intermediate-layer guidance
Hey, we have placed the reservation for you!
By the way, why not check out events that you can attend while you pick your title.
Oops! Something went wrong.
Looks like we were not able to place the reservation. Kindly try again later.
Are you sure you want to remove the book from the shelf?
Attention re-alignment in multimodal large language models via intermediate-layer guidance
Do you wish to request the book?
Attention re-alignment in multimodal large language models via intermediate-layer guidance
Please be aware that the book you have requested cannot be checked out. If you would like to checkout this book, you can reserve another copy
We have requested the book for you!
Your request is successful and it will be processed during the Library working hours. Please check the status of your request in My Requests.
Oops! Something went wrong.
Looks like we were not able to place your request. Kindly try again later.
Journal Article
Attention re-alignment in multimodal large language models via intermediate-layer guidance
2026
Overview
Multimodal large language models (MLLMs) have achieved impressive performance in understanding and describing visual content, setting new state-of-the-art results on a variety of visual question answering (VQA) benchmarks. However, during decoding, these models often fail to attend to fine-grained visual details in the input image. Our analysis of intermediate attention layers reveals that MLLMs are not inherently incapable of perceiving target objects; rather, attention to visual details becomes diluted in deeper layers due to the dominance of language priors. To address this limitation, we propose a plug-and-play attention re-alignment module (ARA) that enhances suppressed visual grounding. ARA conducts a layer-wise analysis of the relative attention distribution of image-centric attention heads. It incorporates a confidence-aware layer selection mechanism based on attention peak and entropy, enabling the dynamic aggregation of attention maps from the most informative layers. These aggregated maps are subsequently leveraged to guide the generation of semantic masks, enabling the model to emphasize salient visual regions while suppressing irrelevant or noisy content. ARA can be seamlessly integrated into existing MLLMs and demonstrates consistent improvements across multiple VQA benchmarks, validating its effectiveness in enhancing visual detail sensitivity.
Publisher
Nature Publishing Group UK,Nature Publishing Group,Nature Portfolio
Subject
