Bringing the power of semantic AI to IBM Db2
Technical note
Donna Dillenberger, Prabhakar Kudva, Apoorva Nitsure, Petr Novotny, and Hong Min
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
IBM demonstrates extreme scale for content-aware storage with a 100-billion vector database
NewsPeter HessAccelerating AI inference with IBM Storage Scale
Technical noteTalia Gershon, Swaminathan Sundararaman, Yue Zhu, Radu Stoica, Animesh Trivedi, Jonathan Terner, Frank Schmuck, Jeremy Cohn, Christof Schmitt, Anthony Hsu, Guy Margalit, Vasily Tarasov, 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
ResearchCarlos Costa, Raghu Ganti, Nick Fuller, Bishwaranjan Bhattacharjee, and Mudhakar Srivatsa4 minute read
Publications
Text-to-SQL Evaluation Toolkit
- 2026
- VLDB 2026
Demo paperData valuation model for non-monetary exchanges
- Julia Blyumen
- Eitan Farchi
- 2026
- arXiv
PaperMarkdown Mayhem : Taming the Agentic Documentation Explosion
- 2026
- ACM CAIS 2026
Workshop paperUnsupervised Cycle Detection in Agentic Applications
- Felix George
- Divya Pathak
- et al.
- 2026
- ICPE 2026
Short paperPRACTICAL EMBEDDING WORKFLOWS WITH TERRATORCH, THE GEOSPATIAL FINE-TUNING TOOLKIT
- Romeo Kienzler
- Isabelle Wittmann
- et al.
- 2026
- ICLR 2026
Workshop paperLanguage Model Representations for Efficient Few-Shot Tabular Classification
- Inwon Kang
- Parikshit Ram
- et al.
- 2026
- WWW 2026
Conference 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.
