IBM’s text-to-SQL generator takes top place on a benchmark for handling complex database queries
News
Kim Martineau
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’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
Towards Efficient Key-Value Cache Management for Prefix Prefilling in LLM Inference
- Yue Zhu
- Hao Yu
- et al.
- 2025
- CLOUD 2025
Speeding up Model Loading with fastsafetensors
- 2025
- CLOUD 2025
TabSketchFM: Sketch-based Tabular Representation Learning for Data Discovery over Data Lakes
- Aamod Khatiwada
- Harsha Kokel
- et al.
- 2025
- ICDE 2025
CodeGenWrangler: Data Wrangling task automation using Code-Generating Models
- Akella Ashlesha
- Abhijit Manatkar
- et al.
- 2025
- NAACL 2025
Rationalization Models for Text-to-SQL
- Gaetano Rossiello
- Nhan Pham
- et al.
- 2025
- ICLR 2025
DELIFT: DATA EFFICIENT LANGUAGE MODEL INSTRUCTION FINE-TUNING
- Ishika Agarwal
- Krishnateja Killamsetty
- et al.
- 2025
- ICLR 2025
IBM Solution: Data Fabric
Our research is regularly developed into new features for Data Fabric in IBM Cloud Pak for Data.
Learn more
