Exploring the Benefits of Just-in-time Model Replacement
Summary: JITR transparently replaces expensive LLM inference for repetitive tasks with automatically searched, fine-tuned surrogate models, preserving usability while reducing cost. JITR-Explore exposes savings, accuracy, throughput, and amortization trade-offs, highlighting fast model-store search as the key bottleneck. (summarized by gpt-5.6-luna on Aug 28 2026)
Incoming Non-self Citations Over Time
No non-self incoming citations found for this paper in this database.
Authors
- 1. Nils Strassenburg (Hasso Plattner Institute)
- 2. Boris Glavic (University of Illinois Chicago)
- 3. Tilmann Rabl (Hasso Plattner Institute)
BibTeX Citation
@article{strassenburg_vldb26,
title = {{Exploring the Benefits of Just-in-time Model Replacement}},
author = {Strassenburg, Nils and Glavic, Boris and Rabl, Tilmann},
journal = {PVLDB},
series = {{VLDB} '26},
volume = {19},
number = {12},
pages = {4674--4677},
doi = {10.14778/3827998.3828094},
url = {https://doi.org/10.14778/3827998.3828094},
year = {2026}
}Incoming Citations (Sorted by Pagerank)
Showing 0 of 0 citing papers.
| Rank | Citing Paper | Year | Venue | Pagerank |
|---|
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 |
|---|---|---|---|---|
| 5,553 | Sommelier: Curating DNN Models for the Masses | 2022 | SIGMOD | 6.0858703e-05 |
| 11,176 | Alsatian: Optimizing Model Search for Deep Transfer Learning | 2025 | SIGMOD | 4.9793485e-05 |
Previous
Page 1 / 1
Next
Semantically Similar Papers
| # | Overall Rank | Paper | Year | Venue |
|---|---|---|---|---|
| 1 | 11,164 | Sentence to Model: Cost-Effective Data Collection LLM Agent | 2025 | SIGMOD |
| 2 | 9,069 | Unveiling Challenges for LLMs in Enterprise Data Engineering | 2026 | VLDB |
| 3 | 501 | Language Models Enable Simple Systems for Generating Structured Views of Heterogeneous Data Lakes | 2024 | VLDB |
| 4 | 8,997 | Cut Costs, Not Accuracy: LLM-Powered Data Processing with Guarantees | 2026 | SIGMOD |
| 5 | 9,158 | Database Perspective on LLM Inference Systems | 2025 | VLDB |
| 6 | 8,888 | Optimized Batch Prompting for Cost-effective LLMs | 2025 | VLDB |
| 7 | 5,149 | LLM for Data Management | 2024 | VLDB |
| 8 | 11,161 | ScaleLLM: A Technique for Scalable LLM-augmented Data Systems | 2025 | SIGMOD |
| 9 | 8,316 | ThriftLLM: On Cost-Effective Selection of Large Language Models for Classification Queries | 2025 | VLDB |
| 10 | 6,860 | SpareLLM: Automatically Selecting Task-Specific Minimum-Cost Large Language Models under Equivalence Constraint | 2025 | SIGMOD |