NVIDIA Introduces Kumo Relational for Database Predictions Without Task-Specific Training
NVIDIA Kumo Relational Outperforms Supervised Machine Learning on Relational Data, No Training Required
- Who
- NVIDIA
- What
- introduces Kumo Relational, a pretrained foundation model for relational data
- Quote
Today, we are introducing Kumo Relational ( paper , documentation ), a pre-trained foundation model that brings this paradigm to relational data.
What happened
NVIDIA introduced Kumo Relational, a pre-trained foundation model that predicts directly from relational databases using up to 10,000 historical examples as context, without task-specific training or feature engineering. NVIDIA reports that it outperforms supervised approaches across 41 tasks on 15 databases and surpasses AutoGluon ensembles by 8% in MRR on SAP SALT. It is available through the open-source structured-data-models library or as an NVIDIA NIM, with optional fine-tuning.
Why it matters
The benchmark comparisons offer a concrete basis for assessing when relational in-context learning can replace engineered prediction pipelines, with task size and relationship structure defining practical limits.
The story so far
NVIDIA introduced Kumo Relational, a pretrained model for making predictions directly from relational databases, and made it available through its structured-data-models library and as an NVIDIA NIM. NVIDIA says the model uses up to 10,000 historical examples as context without requiring task-specific training or feature engineering; optional fine-tuning is also supported. NVIDIA reports that Kumo Relational outperforms supervised approaches across 41 tasks on 15 databases and surpasses AutoGluon ensembles by 8% in mean reciprocal rank (MRR) on SAP SALT. The library’s code is released under Apache 2.0, while the model weights use the OpenMDW License Agreement, version 1.1.
Keep reading
Latest daily · Issue 28Mistral AI releases Voxtral 3 speech models and a voice agent SDKTrending now
- 1Mistral and NVIDIA Announce Industrial Engineering AI Collaboration and Open Benchmarks
- 2Mistral Releases Voxtral 3 Speech Models, Voice Agents API and LiveKit-Based SDK
- 3PHP releases security updates after OpenAI says its models helped researchers find critical flaws
- 4DeepSeek Open-Sources DeepInfer and API Components, With Model and Hardware Limits
Tomorrow at 08:00, a briefing like this arrives in your inbox.
The same kind of briefing as the one above: a few stories worth reading. Free. Mail starts after you confirm, and every letter has a one-click unsubscribe. Read a past issue · 2026-10-21