VikingMem: A Memory Base Management System for Stateful LLM-based Applications
Summary: Introduces Memory Base, a stateful data-management paradigm for selective, evolving, temporally weighted LLM memories. VikingMem implements event/entity updates, timeline compression, time-weighted recall, and multi-vector reranking, improving retrieval by up to 30% at low latency. (summarized by gpt-5.6-luna on Aug 28 2026)
Incoming Non-self Citations Over Time
Authors
- 1. Jiajie Fu (Zhejiang University)
- 2. Junwen Chen (ByteDance)
- 3. Mengzhao Wang (Zhejiang University)
- 4. Aoxiang He (ByteDance)
- 5. Maojia Sheng (ByteDance)
- 6. Xiangyu Ke (Zhejiang University)
- 7. Yifan Zhu (Zhejiang University)
- 8. Yunjun Gao (Zhejiang University)
BibTeX Citation
@article{fu_vldb26,
title = {{VikingMem: A Memory Base Management System for Stateful LLM-based Applications}},
author = {Fu, Jiajie and Chen, Junwen and Wang, Mengzhao and He, Aoxiang and Sheng, Maojia and Ke, Xiangyu and Zhu, Yifan and Gao, Yunjun},
journal = {PVLDB},
series = {{VLDB} '26},
volume = {19},
number = {12},
pages = {4344--4357},
doi = {10.14778/3827998.3828037},
url = {https://doi.org/10.14778/3827998.3828037},
year = {2026}
}Incoming Citations (Sorted by Pagerank)
Showing 1 of 1 citing papers.
| Rank | Citing Paper | Year | Venue | Pagerank |
|---|---|---|---|---|
| 10,974 | MemLens: A Value-Aware Memory Management System with Interactive Analytics for LLM-based Agents | 2026 | VLDB | 4.9793485e-05 |
Previous
Page 1 / 1
Next
Outgoing Citations (Sorted by Pagerank)
Showing 4 of 4 cited papers.
Citations counted here include only citations to other VLDB/SIGMOD/CIDR/PODS papers in this database.
| Rank | Cited Paper | Year | Venue | Pagerank |
|---|---|---|---|---|
| 804 | RaBitQ: Quantizing High-Dimensional Vectors with a Theoretical Error Bound for Approximate Nearest Neighbor Search | 2024 | SIGMOD | 0.00013832333 |
| 4,114 | Automatic Database Configuration Debugging using Retrieval-Augmented Language Models | 2025 | SIGMOD | 6.7971182e-05 |
| 4,229 | Cracking SQL Barriers: An LLM-based Dialect Translation System | 2025 | SIGMOD | 6.7165534e-05 |
| 10,527 | In-context Clustering-based Entity Resolution with Large Language Models: A Design Space Exploration | 2026 | SIGMOD | 4.9793485e-05 |
Previous
Page 1 / 1
Next