DBScholar

Back to papers

Beyond Relational: Semantic-Aware Multi-Modal Analytics with LLM-Native Query Optimization

Summary: Nirvana: LLM-native semantic multi-modal analytics beyond relational operators, with programmable semantic operators and optimizer support for semantically aware query processing. Novel agentic logical optimization via NL rewrite rules + random-walk search, plus cost-aware LLM backend selection, reuse, and pushdown; strong runtime/cost gains. (summarized by gpt-5-mini on Apr 11 2026)

Paper ID
7645
Venue
SIGMOD
Year
2026
Pagerank
5.093636e-05
Overall Rank
10,433 | 28.43%
DOI
10.1145/3786628

Incoming Non-self Citations Over Time

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

Authors

BibTeX Citation

@inproceedings{zhu_sigmod26,
        title = {{Beyond Relational: Semantic-Aware Multi-Modal Analytics with LLM-Native Query Optimization}},
        author = {Zhu, Junhao and Chen, Lu and Ke, Xiangyu and Fang, Ziquan and Li, Tianyi and Gao, Yunjun and Jensen, Christian S.},
        series = {{SIGMOD} '26},
        booktitle = {Proceedings of the {ACM} {SIGMOD} International Conference on Management of Data},
        publisher = {Association for Computing Machinery},
        doi = {10.1145/3786628},
        url = {https://dl.acm.org/doi/10.1145/3786628},
        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 11 of 11 cited papers.

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

Previous Page 1 / 1 Next

Semantically Similar Papers