@article{quantifyingmultimodalcapabilitiesformalg, title = {Quantifying Multimodal Capabilities: Formal Generalization Guarantees in Pairwise Metric Learning}, author = {Richeng Zhou and Xuelin Zhang and Liyuan Liu}, year = {2026}, eprint = {2605.01424}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2605.01424}, }