Structural and Disentangled Adaptation of Large Vision Language Models for Multimodal Recommendation.

@inproceedings{wang-2026-structural, author = {Xianzhi Wang and Zhongtao Rao and Shoujin Wang and Timothy Jones and Lina Yao and Peilin Zhou and Xianzhi Wang and Zhongtao Rao and Dading Chong and Lina Yao and Peilin Zhou and Zhiwei Chen and Shoujin Wang and Timothy Jones and Nan Tang}, editor = {Hannah Bast and Alistair Moffat and Falk Scholer and Marc Najork and Min Zhang and Hannah Bast and Marc Najork and Min Zhang}, title = {{Structural and Disentangled Adaptation of Large Vision Language Models for Multimodal Recommendation}}, booktitle = {{Proceedings of the 49th International ACM SIGIR Conference on Research and Development in Information Retrieval, SIGIR 2026, MelbourneVICAustralia, July 20-24, 2026}}, pages = {4074--4079}, publisher = {ACM}, year = {2026}, url = {https://doi.org/10.1145/3805712.3809977}, doi = {https://doi.org/10.1145/3805712.3809977} }