Search papers, labs, and topics across Lattice.
Chungbuk National University
2
0
3
Multimodal retrieval can be boosted by over 10 points on a challenging benchmark by unifying LLM-based query expansion, a reasoning-enhanced retriever, and chain-of-thought reranking.
LLMs can supercharge multimodal retrieval by iteratively "querying, hypothesizing, and verifying" to bridge visual-text reasoning gaps, yielding a 14-point nDCG@10 boost over the best multimodal model.
