Call for Papers

IMPORTANT DATES:

• Submission deadline:  June 13, 2026.
• Author notification: July 13, 2026.
• Camera-ready version: July 17, 2026.
• Workshop day: August 31, 2026.

All deadlines are 11:59PM PST.

Submission website: https://openreview.net/group?id=VLDB.org/2026/Workshop/NOVAS 

ABOUT NOVAS

The advent of transformer-based architectures has disrupted the current technological landscape. One key feature that enables the success of these models is the extensive access to data: first, they are pre-trained on terabytes of data thanks to self-supervision and scalable data processing; then, they can leverage large input contexts during inference thanks to advances in model sizes, GPU optimizations, and caching strategies. 

Interesting research questions are consolidating around this novel paradigm of data processing:

• How to design systems that process large, heterogeneous collections of data?

• How to optimize data processing under time, economic, and performance constraints?

• How can database management techniques be leveraged to optimize the storage and retrieval of data for large transformer-based models?

• How can we integrate LLMs with traditional database systems to enhance data query performance and ensure reliable outputs?

The workshop name, NOVAS stands for Novel Optimizations for Visionary AI Systems: with our workshop, we aim to provide a platform that can help bridge the current perceived gap between "data management'' and "generative AI'' research. We are calling for work or early ideas which may be deemed innovative, controversial, or disruptive if considered from the perspective of more established research areas.

For any questions regarding the workshop please contact us at chairs@novasworkshop.org

TOPICS OF INTEREST

Topics of particular interest for the workshop include, but are not limited to:

• Declarative and “multi-agent" systems for large-scale, agentic data processing.

• Implementation and optimization for semantic operations, including semantic joins, semantic aggregations, semantic filters.

• Multimodal question answering and data processing

• DB-inspired techniques to optimize workloads of hybrid relational-AI queries.

• System-level methods for efficient LLM serving: performance, energy, and cost trade-offs

• New model architectures for relational data processing (e.g. relational transformers)

• Vector databases for embeddings in RAG systems.

• Benchmarks for data processing tasks using LLMs.

SUBMISSION GUIDELINES

• Regular papers: 6 pages.
• Short papers: 4 pages.

All submissions (in PDF format) should be sent to OpenReview.

Submission link: https://openreview.net/group?id=VLDB.org/2026/Workshop/NOVAS 

REVIEWING PROCESS

Submissions will be single blind: authors cannot see reviewer names, but reviewers can see author names. We use OpenReview to host papers and the reviewing process will be public. This means that reviewers' comments can be seen by all, during the submission and for accepted papers after decision, although the reviewers' identity will remain anonymous.

Conflicts of Interests (COIs) are handled using the same rules of VLDB 2026.

The use of LLMs is allowed as a general-purpose assist tool.  Authors and reviewers should understand that they take full responsibility for the contents written under their name, including content generated by LLMs that could be construed as plagiarism or scientific misconduct (e.g., fabrication of facts).  LLMs are not eligible for authorship.