Preprint
Aug 2026
Does More Retrieved Evidence Help Visual Retrieval-Augmented Generation with Diffusion Language Models?
It is shown that broader retrieval benefits visual DLM-RAG through selective evidence admission rather than unconditional evidence expansion, and the Entropy-Based Candidate Filter (ECF), a training-free evidence-admission framework is proposed, shows that broader retrieval benefits visual DLM-RAG through selective evi...
Jiankun Wang, Yi-Sen Gao, Zi-Wei Zhang et al.
· 0 citations