QStore: Quantization-Aware Compressed Model Storage

Summary: Introduces QStore, a quantization-aware lossless format that stores a low-precision model plus compact residuals to reconstruct high-precision variants, avoiding duplicate files. Achieves up to 2.2× storage reduction and faster save/load (≈1.7–1.8×) via lightweight decoding. (summarized by gpt-5-mini on Mar 13 2026)

Paper ID: 14340
Venue: VLDB
Year: 2026
Pagerank: 5.1725247e-05
Overall Rank: 10,298 | 28.43%
DOI: 10.14778/3778092.3778100

Incoming Non-self Citations Over Time

No non-self incoming citations found for this paper in this database.

Authors

Incoming Citations (Sorted by Pagerank)

Showing 1 of 1 citing papers.

Rank	Citing Paper	Year	Venue	Pagerank
10,314	Chipmink: Efficient Delta Identification for Massive Object Graphs	2026	VLDB	5.1725247e-05

Outgoing Citations (Sorted by Pagerank)

Showing 10 of 10 cited papers.

Citations counted here include only citations to other VLDB/SIGMOD/CIDR/PODS papers in this database.

Rank	Cited Paper	Year	Venue	Pagerank
635	Materialization Optimizations for Feature Selection Workloads	2014	SIGMOD	0.00015616114
1,618	Compressed Linear Algebra for Large-Scale Machine Learning	2016	VLDB	0.00010273817
3,149	DeepSqueeze: Deep Semantic Compression for Tabular Data	2020	SIGMOD	7.7622766e-05
3,798	ALP: Adaptive Lossless floating-Point Compression	2023	SIGMOD	7.1689367e-05
6,420	Tuple-oriented Compression for Large-scale Mini-batch Stochastic Gradient Descent	2019	SIGMOD	5.9469476e-05
8,996	AirIndex: Versatile Index Tuning Through Data and Storage	2023	SIGMOD	5.4009155e-05
9,922	ElasticNotebook: Enabling Live Migration for Computational Notebooks	2024	VLDB	5.2412669e-05
10,444	Demo of Kishu: Time-Traveling for Computational Notebooks	2025	SIGMOD	5.1725247e-05
10,767	SIEVE: Effective Filtered Vector Search with Collection of Indexes	2025	VLDB	5.1725247e-05
10,892	Kishu: Time-Traveling for Computational Notebooks	2025	VLDB	5.1725247e-05

Semantically Similar Papers

Overall Rank	Paper	Year	Venue	Pagerank
7,016	MorphStore: Analytical Query Engine with a Holistic Compression-Enabled Processing Model	2020	VLDB	5.7830692e-05
13,098	Waiting to Decompress: The Economics of LLM-Based Compression	2026	CIDR	-
6,104	Progressive Compressed Records: Taking a Byte out of Deep Learning Data	2021	VLDB	6.0387881e-05
9,409	Experimental Analysis of Large-scale Learnable Vector Storage Compression	2024	VLDB	5.3341661e-05
10,622	QPET: A Versatile and Portable Quantity-of-Interest-Preservation Framework for Error-Bounded Lossy Compression	2025	VLDB	5.1725247e-05
9,674	Frequency-Store: Scaling Image AI by A Column-Store for Images	2025	CIDR	5.2947004e-05
10,508	Privacy and Accuracy-Aware AI/ML Model Deduplication	2025	SIGMOD	5.1725247e-05
6,185	PQCache: Product Quantization-based KVCache for Long Context LLM Inference	2025	SIGMOD	6.0213899e-05
8,524	Everything You Always Wanted to Know About Storage Compressibility of Pre-Trained ML Models but Were Afraid to Ask	2024	VLDB	5.4795936e-05
10,095	NeurStore: Efficient In-database Deep Learning Model Management System	2026	SIGMOD	5.1725247e-05