Modality-Gated Deep Adapters: Adding a Modality to a Frozen Embedding Model with Exact Preservation

Excerpt

arXiv:2609.26182v1 Announce Type: new Abstract: Multimodal embedding models are deployed at scale: retrieval indices, benchmark results, and behavioral audits all depend on the base model's exact outputs. Extending such a model to a new modality with existing parameter-efficient methods silently changes those outputs; LoRA-style adaptation rewrites the text path whether or not the weights are merged, invalidating every stored embedding. We propose modality-gated deep adapters: bottleneck adapter