CADENZA in Action: Breaking the Monolith with Intent-Dependent Plan Spaces for Semantic Queries
Summary: CADENZA compiles natural-language intents into decomposed, intent-dependent plan spaces, replacing monolithic LLM/embedding optimization. It selects and tunes physical implementations under user quality–latency–cost preferences, exposed via an interactive multimodal-data demo. (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. Jaehyun Ha (Pohang University of Science and Technology)
- 2. Yongjoo Park (University of Illinois Urbana-Champaign)
- 3. Wook-Shin Han (Pohang University of Science and Technology)
BibTeX Citation
@article{ha_vldb26,
title = {{CADENZA in Action: Breaking the Monolith with Intent-Dependent Plan Spaces for Semantic Queries}},
author = {Ha, Jaehyun and Park, Yongjoo and Han, Wook-Shin},
journal = {PVLDB},
series = {{VLDB} '26},
volume = {19},
number = {12},
pages = {4634--4637},
doi = {10.14778/3827998.3828084},
url = {https://doi.org/10.14778/3827998.3828084},
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 7 of 7 cited papers.
Citations counted here include only citations to other VLDB/SIGMOD/CIDR/PODS papers in this database.
| Rank | Cited Paper | Year | Venue | Pagerank |
|---|---|---|---|---|
| 630 | DocETL: Agentic Query Rewriting and Evaluation for Complex Document Processing | 2025 | VLDB | 0.00015402076 |
| 697 | Palimpzest: Optimizing AI-Powered Analytics with Declarative Query Processing | 2025 | CIDR | 0.00014665686 |
| 2,611 | Semantic Operators and Their Optimization: Enabling LLM-Based Data Processing with Accuracy Guarantees in LOTUS | 2025 | VLDB | 8.2027761e-05 |
| 2,924 | Abacus: A Cost-Based Optimizer for Semantic Operator Systems | 2026 | VLDB | 7.8407467e-05 |
| 3,914 | AOP: Automated and Interactive LLM Pipeline Orchestration for Answering Complex Queries | 2025 | CIDR | 6.9084826e-05 |
| 4,996 | SemBench: A Benchmark for Semantic Query Processing Engines | 2026 | VLDB | 6.3095672e-05 |
| 5,908 | Unify: A System For Unstructured Data Analytics | 2025 | VLDB | 5.9343313e-05 |
Previous
Page 1 / 1
Next
Semantically Similar Papers
| # | Overall Rank | Paper | Year | Venue |
|---|---|---|---|---|
| 1 | 605 | CAESURA: Language Models as Multi-Modal Query Planners | 2024 | CIDR |
| 2 | 5,908 | Unify: A System For Unstructured Data Analytics | 2025 | VLDB |
| 3 | 10,185 | Deep Research is the New Analytics System: Towards Building the Runtime for AI-Driven Analytics | 2026 | CIDR |
| 4 | 2,611 | Semantic Operators and Their Optimization: Enabling LLM-Based Data Processing with Accuracy Guarantees in LOTUS | 2025 | VLDB |
| 5 | 2,924 | Abacus: A Cost-Based Optimizer for Semantic Operator Systems | 2026 | VLDB |
| 6 | 4,996 | SemBench: A Benchmark for Semantic Query Processing Engines | 2026 | VLDB |
| 7 | 10,928 | Sema: A High-performance System for LLM-based Semantic Query Processing | 2026 | VLDB |
| 8 | 10,694 | Beyond Relational: Semantic-Aware Multi-Modal Analytics with LLM-Native Query Optimization | 2026 | SIGMOD |
| 9 | 11,056 | Demonstrating Samsara: A Super-Optimizer for Multimodal Stream Processing | 2026 | VLDB |
| 10 | 10,388 | CADENZA: Compiling Natural-Language Intent into Task-Specific Operator DAGs for Semantic Query Processing | 2027 | SIGMOD |