Back to papers
ThalamusDB: Approximate Query Processing on Multi-Modal Data
Summary: ThalamusDB: AQPs for complex SQL over multi-modal data, combining relational operators with zero-shot vision/audio/text models and small user label requests for NL predicates. Distinctive for deterministic approximation + user-tunable tradeoffs among error, latency, and labeling overhead via optimizer-guided plans.
(summarized by gpt-5.4-mini on May 24 2026)
Paper ID
h5bc1ae29215bf7a6
Venue
SIGMOD
Year
2024
Pagerank
8.7996555e-05
Overall Rank
2,225 | 85.09%
DOI
10.1145/3654989
Incoming Non-self Citations Over Time
BibTeX Citation
@inproceedings{jo_sigmod24,
title = {{ThalamusDB: Approximate Query Processing on Multi-Modal Data}},
author = {Jo, Saehan and Trummer, Immanuel},
series = {{SIGMOD} '24},
booktitle = {Proceedings of the {ACM} {SIGMOD} International Conference on Management of Data},
publisher = {Association for Computing Machinery},
doi = {10.1145/3654989},
url = {https://dl.acm.org/doi/10.1145/3654989},
year = {2024}
}
Incoming Citations (Sorted by Pagerank)
Showing 23 of 23 citing papers.
Rank
Citing Paper
Year
Venue
Pagerank
3,717
Logical and Physical Optimizations for SQL Query Execution over Large Language Models 2025
SIGMOD
7.05392e-05
4,583
QUEST: Query Optimization in Unstructured Document Analysis 2025
VLDB
6.5079225e-05
4,996
SemBench: A Benchmark for Semantic Query Processing Engines 2026
VLDB
6.3095672e-05
6,615
Multi-Objective Agentic Rewrites for Unstructured Data Processing 2026
VLDB
5.7164252e-05
6,893
Doctopus: Budget-aware Structural Table Extraction from Unstructured Documents 2025
VLDB
5.6385194e-05
8,708
Unstructured Data Analysis Using LLMs: A Comprehensive Benchmark 2026
VLDB
5.2705676e-05
9,494
SQLBarber: A System Leveraging Large Language Models to Generate Customized and Realistic SQL Workloads 2026
SIGMOD
5.1541298e-05
10,231
Task Cascades for Efficient Unstructured Data Processing 2026
SIGMOD
5.0432098e-05
10,232
Featurized-Decomposition Join: Low-Cost Semantic Joins with Guarantees 2026
VLDB
5.0432098e-05
10,388
CADENZA: Compiling Natural-Language Intent into Task-Specific Operator DAGs for Semantic Query Processing 2027
SIGMOD
4.9605343e-05
10,418
Evergreen: Efficient Claim Verification for Semantic Aggregates 2027
VLDB
4.9605343e-05
10,420
Rethinking Query Optimization for Multi-Agent Systems 2027
VLDB
4.9605343e-05
10,425
KathDB: Explainable Multimodal Database Management System with Human-AI Collaboration 2026
CIDR
4.9605343e-05
10,478
100x Cost & Latency Reduction: Performance Analysis of AI Query Approximation using Lightweight Proxy Models: [Experiments & Analysis] 2026
SIGMOD
4.9605343e-05
10,480
Accelerating Approximate Analytical Join Queries over Unstructured Data with Statistical Guarantees 2026
SIGMOD
4.9605343e-05
10,529
Factorized and Vectorized Execution: Optimizing Analytical and Semantic Queries over Relations 2026
SIGMOD
4.9605343e-05
10,565
OctoSelector: Efficient and Effective Batch-Aware Model Selection for Large Language Models 2026
SIGMOD
4.9605343e-05
10,694
Beyond Relational: Semantic-Aware Multi-Modal Analytics with LLM-Native Query Optimization 2026
SIGMOD
4.9605343e-05
10,912
Bolt-on, Verifiable Provenance for LLM-Powered Data Processing 2026
VLDB
4.9605343e-05
10,968
stratum: A System Infrastructure for Massive Agent-Centric ML Workloads 2026
VLDB
4.9605343e-05
11,056
Demonstrating Samsara: A Super-Optimizer for Multimodal Stream Processing 2026
VLDB
4.9605343e-05
11,068
Demonstrating TACT: Tunable Accuracy-Cost Trade-offs for Semantic Image Filtering 2026
VLDB
4.9605343e-05
11,094
Bridging LLMs and Database Systems: A Deep Dive into Enhanced Relational Operators 2026
VLDB
4.9605343e-05
Outgoing Citations (Sorted by Pagerank)
Showing 20 of 20 cited papers.
Citations counted here include only citations to other VLDB/SIGMOD/CIDR/PODS papers in this database.
Rank
Cited Paper
Year
Venue
Pagerank
1
Access Path Selection in a Relational Database Management System 1979
SIGMOD
0.0023948467
9
Online Aggregation 1997
SIGMOD
0.00076079812
36
Accurate Estimation Of The Number Of Tuples Satisfying A Condition 1984
SIGMOD
0.00047770864
71
DuckDB: an Embeddable Analytical Database 2019
SIGMOD
0.00037688945
541
BlazeIt: Optimizing Declarative Aggregation and Limit Queries for Neural Network-Based Video Analytics 2020
VLDB
0.00016627384
564
Congressional Samples for Approximate Answering of Group-By Queries 2000
SIGMOD
0.00016251304
951
Aqua: A Fast Decision Support System Using Approximate Query Answers 1999
VLDB
0.00012886042
1,065
Approximate Query Processing: No Silver Bullet 2017
SIGMOD
0.00012181098
1,358
Symphony: Towards Natural Language Query Answering over Multi-modal Data Lakes 2023
CIDR
0.00010902306
2,231
DAQ: A New Paradigm for Approximate Query Processing 2015
VLDB
8.7882698e-05
2,393
DeepLens: Towards a Visual Data Management System 2019
CIDR
8.5162362e-05
3,611
Plato: Approximate Analytics over Compressed Time Series with Tight Deterministic Error Guarantees 2020
VLDB
7.1443694e-05
3,629
TASTI: Semantic Indexes for Machine Learning-based Queries over Unstructured Data 2022
SIGMOD
7.1286458e-05
3,747
Accelerating Approximate Aggregation Queries with Expensive Predicates 2021
VLDB
7.0351475e-05
4,284
VIVA: An End-to-End System for Interactive Video Analytics 2022
CIDR
6.6710929e-05
5,030
VisualWorldDB: A DBMS for the Visual World 2020
CIDR
6.2951049e-05
5,951
VOCAL: Video Organization and Interactive Compositional AnaLytics 2022
CIDR
5.9185041e-05
6,198
Combining Aggregation and Sampling (Nearly) Optimally for Approximate Query Processing 2021
SIGMOD
5.8362492e-05
7,265
SeeSaw: Interactive Ad-hoc Search Over Image Databases 2023
SIGMOD
5.5546592e-05
12,102
BitGourmet: Deterministic Approximation via Optimized Bit Selection 2020
CIDR
4.9605343e-05
Semantically Similar Papers