@article{clayconditionalvisualsimilaritymodulatio, title = {CLAY: Conditional Visual Similarity Modulation in Vision-Language Embedding Space}, author = {Sohwi Lim and Lee Hyoseok and Jungjoon Park and Tae-Hyun Oh}, year = {2026}, eprint = {2604.11539}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2604.11539}, }