@article{fireboltvlefficientvisionlanguageunderst, title = {Firebolt-VL: Efficient Vision-Language Understanding with Cross-Modality Modulation}, author = {Quoc-Huy Trinh and Mustapha Abdullahi and Bo Zhao and Debesh Jha}, year = {2026}, eprint = {2604.04579}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2604.04579}, }