IBM demonstrates extreme scale for content-aware storage with a 100-billion vector database
News
Peter Hess
Data Management
The future of computing lies in the hybrid cloud. We're creating a hybrid data fabric that provides secure, governed data access from anywhere, enables self-service discovery of the right data at the right time, and takes a holistic view at minimizing total cost of ownership for AI and analytics.
Our work
Accelerating AI inference with IBM Storage Scale
Technical noteYue Zhu, Radu Stoica, Animesh Trivedi, Jonathan Terner, Frank Schmuck, Jeremy Cohn, Christof Schmitt, Anthony Hsu, Guy Margalit, Vasily Tarasov, Swaminathan Sundararaman, Talia Gershon, and Vincent HsuIBM’s text-to-SQL generator takes top place on a benchmark for handling complex database queries
NewsKim MartineauIBM’s CodeFlare significantly cuts the time to automate transfer learning tasks for foundation models
ResearchBishwaranjan Bhattacharjee, Raghu Ganti, Carlos Costa, Mudhakar Srivatsa, and Nick Fuller4 minute read
Publications
Unsupervised Cycle Detection in Agentic Applications
- Felix George
- Divya Pathak
- et al.
- 2026
- ICPE 2026
Short paperIn-depth Analysis of LLM-based Schema Linking
- George Katsogiannis-meimarakis
- Katya Mirylenka
- et al.
- 2026
- EDBT 2026
Conference paperThe Pitfalls of Underspecified Workloads in Benchmarking
- John Lewars
- John Divirgilio
- et al.
- 2026
- FAST 2026
PosterRetrieval with Multiple Query Vectors through Anomalous Pattern Detection
- Allassan Tchangmena A Nken
- Baimam Jean Jaques Boukar
- et al.
- 2026
- AAAI 2026
Workshop paperQueryGym: Step-by-Step Interaction with Relational Databases
- Haritha Ananthakrishnan
- Harsha Kokel
- et al.
- 2026
- AAAI 2026
Demo paperDFAgent: From Natural Language Data Interactions to Reusable Agent-Ready Tools
- 2026
- AAAI 2026
Demo paper
IBM Solution: Data Fabric
Our research is regularly developed into new features for Data Fabric in IBM Cloud Pak for Data.
Learn more
Projects
An LLM-Powered System for Enterprise Data
Reducing friction for scientific and foundation model workflows in Kubernetes.
A lineage data management system for tracking data in hybrid cloud deployments.
