2 papers
cs.IR2026
RandSlot: Learning Compact Visual Document Representations with Random Soft Tokens
Dewen Guo, Shi Yu, Lingxiao Zhang +3
Visual document retrieval requires expressive representations to match queries with evidence distributed across text, tables, and page layouts. Multi-vector representations capture…
cs.IR2025
UltraRAG: A Modular and Automated Toolkit for Adaptive Retrieval-Augmented Generation
Yuxuan Chen, Dewen Guo, Sen Mei +12
Retrieval-Augmented Generation (RAG) significantly enhances the performance of large language models (LLMs) in downstream tasks by integrating external knowledge. To facilitate res…