Introducing the IBM Granite 4.1 family of models
Release
Mike Murphy
Generative AI
Generative AI is revolutionizing how the world computes, but there are still roadblocks for scaling to solve real business problems. At IBM Research, we’re working on trustworthy models, software, and infrastructure to allow any business to harness the power of generative AI.
Our work
How an extra training step can unlock AI’s reasoning power
ReleaseKim MartineauDonating llm-d to the Cloud Native Computing Foundation
NewsPeter HessHow IBM Granite became a leader in responsible AI
ExplainerKim MartineauAI for seeing the forest — and the trees
NewsKim MartineauLLMs have model cards. Now, benchmarks do, too
ReleaseKim Martineau- See more of our work on Generative AI
Publications
Agent Lifecycle Toolkit (ALTK): Reusable Middleware Components for Robust AI Agents
- Zidane Wright
- Jason Tsay
- et al.
- 2026
- ACM CAIS 2026
Demo paperContext-Aware Visual Multi-Turn Conversation Generation from Wikipedia and Wikidata
- Basel Shbita
- Pengyuan Li
- et al.
- 2026
- ESWC 2026
Conference paperSPEAKER ATTRIBUTED AUTOMATIC SPEECH RECOGNITION USING SPEECH AWARE LLMS
- Hagai Aronowitz
- Zvi Kons
- et al.
- 2026
- ICASSP 2026
Conference paperAdvancing Speech Understanding in Speech-Aware Language Models with GRPO
- Avishai Elmakies
- Hagai Aronowitz
- et al.
- 2026
- ICASSP 2026
Conference paperAdaptive Decoding via Test-Time Policy Learning for Self-Improving Generation
- Asmita Bhardwaj
- Yuya Ong
- et al.
- 2026
- ICLR 2026
Workshop paperEvaluating Ill-Defined Tasks in Large Language Models
- 2026
- ICLR 2026
Workshop paper