CIM-Embed: Learning Instruction-Conditioned Multimodal Embeddings for Clustering
arXiv:2610.21805v1 Announce Type: new Abstract: Multimodal objects can require different partitions under different instructions, as when products in an e-commerce catalog are grouped by color, material, or both. Retrieval-oriented embeddings may not recover these partitions, while generative clustering often relies on intermediate descriptions or iterative decisions. This paper presents CIM-Embed, a framework for learning instruction-conditioned multimodal embeddings for clustering. Supervised…