An Interactive Multi-modal Query Answering System with Retrieval-Augmented Large Language Models
Summary: Presents MQA: an interactive retrieval-augmented LLM system with a multi-modal retrieval framework and navigation-graph index for efficient multimodal search. Uses contrastive learning to weight modalities and a pluggable coordinator pipeline to swap embeddings, graph indexes, and LLMs. (summarized by gpt-5-mini on Feb 09 2026)
Incoming Non-self Citations Over Time
Authors
- 1. Mengzhao Wang
- 2. Haotian Wu
- 3. Xiangyu Ke
- 4. Yunjun Gao
- 5. Xiaoliang Xu
- 6. Lu Chen
Incoming Citations (Sorted by Pagerank)
Showing 2 of 2 citing papers.
| Rank | Citing Paper | Year | Venue | Pagerank |
|---|---|---|---|---|
| 9,240 | ThriftLLM: On Cost-Effective Selection of Large Language Models for Classification Queries | 2025 | VLDB | 4.3648789e-05 |
| 10,275 | Balancing the Blend: An Experimental Analysis of Trade-offs in Hybrid Search | 2026 | VLDB | 4.1905499e-05 |
Previous
Page 1 / 1
Next
Outgoing Citations (Sorted by Pagerank)
Showing 2 of 2 cited papers.
Citations counted here include only citations to other VLDB/SIGMOD/CIDR/PODS papers in this database.
| Rank | Cited Paper | Year | Venue | Pagerank |
|---|---|---|---|---|
| 494 | Milvus: A Purpose-Built Vector Data Management System | 2021 | SIGMOD | 0.00021769407 |
| 2,692 | Starling: An I/O-Efficient Disk-Resident Graph Index Framework for High-Dimensional Vector Similarity Search on Data Segment | 2024 | SIGMOD | 8.2857267e-05 |
Previous
Page 1 / 1
Next