activity
20212026
most citedMISSRec: Pre-training and Transferring Multi-modal Interest-aware Sequence Representation for Recommendation

60 citations · 92 across the 31 of their papers we have counts for

collaborators
Showing cs.AIShow all

1 paper · 1 filter

cs.AI2026

DocMemo: Dynamic Evidence Discovery via Probabilistic Memory-Guided Retrieval for Multi-Modal Document Understanding

Hanshu Yao, Janfeng Zhong, Niu Lian +1

Long-document understanding requires locating sparse and heterogeneous evidence across hundreds of pages, yet existing systems remain limited by static retrieval and fragile cross-…