Task-Aware Cloud-End Offloading for Vision-Language Model Serving via Dynamic Modality-Specific Adapter Scheduling.

@inproceedings{wang-2026-taskaware, author = {Zian Wang and Ziyi Wang and Jie Xing and Yaya Wei and Ziyan Zhong and Lanshan Zhang}, editor = {Hakim Hacid and Yoelle Maarek and Francesco Bonchi and Ido Guy and Emine Yilmaz}, title = {{Task-Aware Cloud-End Offloading for Vision-Language Model Serving via Dynamic Modality-Specific Adapter Scheduling}}, booktitle = {{Proceedings of the ACM Web Conference 2026, WWW 2026, Dubai, United Arab Emirates, originally scheduled for April 13-17, 2026, rescheduled for June 29 - July 3, 2026}}, pages = {5021--5030}, publisher = {ACM}, year = {2026}, url = {https://doi.org/10.1145/3774904.3792127}, doi = {https://doi.org/10.1145/3774904.3792127} }