Prefix Retention Optimization

Closing the Indexing-Decoding Gap in Multimodal Generative Retrieval via Prefix Retention Optimization

arXiv:2606.09241v1 Announce Type: new Abstract: Multimodal generative retrieval formulates multimodal retrieval as discrete identifier generation, eliminating the need for explicit similarity search over external embeddings. Existing approaches construct identifiers via residual quantization and decode them with trie-constrained beam search. This combination introduces an indexing-decoding gap: identifier learning objectives, including reconstruction and contrastive losses, do not explicitly...