A General Framework for Multimodal LLM-Based Multimedia Understanding in Large-Scale Recommendation Systems.

@inproceedings{zhu-2026-general, author = {Yiming Zhu and Xu Liu and Birger Larsen and Zheng Wu and Junfeng Pan and Zhihui Xie and Ziyun Xu and Birger Larsen and Zheng Wu and Linhong Zhu and Xiaolu Zhang and Joena Zhang and Maarten de Rijke and Chenheli Hua and Xingmei Wang and Sirius Chen and Zhewei Wei and Petra Galusc\'{a}kov\'{a} and Qichao Que and Chenheli Hua and Xingmei Wang and Sirius Chen and Zhewei Wei and Silvester Yao and Petra Galusc\'{a}kov\'{a} and Qichao Que and Wentao Shi and Junfeng Pan and Zhihui Xie and Linhong Zhu and Xiaolu Zhang}, 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 = {{A General Framework for Multimodal LLM-Based Multimedia Understanding in Large-Scale Recommendation Systems}}, booktitle = {{Proceedings of the 49th International ACM SIGIR Conference on Research and Development in Information Retrieval, SIGIR 2026, MelbourneVICAustralia, July 20-24, 2026}}, pages = {5108--5112}, publisher = {ACM}, year = {2026}, url = {https://doi.org/10.1145/3805712.3808431}, doi = {https://doi.org/10.1145/3805712.3808431} }