@article{tcmservemodalityawareschedulingformultim, title = {TCM-Serve: Modality-aware Scheduling for Multimodal Large Language Model Inference}, author = {Konstantinos Papaioannou and Thaleia Dimitra Doudali}, year = {2026}, eprint = {2603.26498}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2603.26498}, }