Kim Martineau

News

Research

Explainer

Why we’re teaching LLMs to forget things 

An air traffic controller for LLMs 

Serving customized AI models at scale with LoRA

A new tool to unlock data from enterprise documents for generative AI 

IBM Granite has new experimental features for developers to test

Can a personalized AI be more useful?

A benchmark for evaluating conversational RAG

AAAI 2025

Trustworthy AI

Foundation Models

Natural Language Processing

Generative AI

Granite

Most enterprises rely on large volumes of aging code that are a challenge to debug, maintain, and update. At IBM Research, we’re using AI to help modernize software stacks, designing automated programming and refactoring systems to help businesses keep up with the speed of modern life. 

AI for Code

Much of the information that can help transform enterprises is locked away in text, like documents, tables, and charts. We’re building advanced AI systems that can parse vast bodies of text to help unlock that data, but also ones flexible enough to be applied to any language problem.

We see Neuro-symbolic AI as a pathway to achieve artificial general intelligence. By augmenting and combining the strengths of statistical AI, like machine learning, with the capabilities of human-like symbolic knowledge and reasoning, we're aiming to create a revolution in AI, rather than an evolution. 

Neuro-symbolic AI

As more of the world moves online, the demand for systems that can understand users and speak to them in natural language is growing exponentially. At IBM Research, we're working on next-generation AI that learns to decipher and replicate the way humans speak.

Speech

The demand for virtual agents that can handle customer needs has continued to increase dramatically. At IBM Research, we’re building the next generation of artificial intelligence systems that can understand what’s being asked of them and how best to respond as efficiently as possible.

Conversational AI

Screenshot of the App Builder interface from the BeeAI application

Natural Language Processing

Our work

A benchmark for evaluating conversational RAG

Can a personalized AI be more useful?

IBM Granite has new experimental features for developers to test

A new tool to unlock data from enterprise documents for generative AI

Serving customized AI models at scale with LoRA

An air traffic controller for LLMs

Publications

QGen Studio: An Adaptive Question-Answer Generation, Training and Evaluation Platform

Sentence-level Aggregation of Lexical Metrics Correlate Stronger with Human Judgements than Corpus-level Aggregation

Bridging Planning and Reasoning in Natural Languages with Foundational Models (PLAN-FM)

Data Wrangling task automation using Code-Generating Language Models

Token Highlighter: Inspecting and Mitigating Jailbreak Prompts for Large Language Models

Retention Score: Quantifying Jailbreak Risks for Vision Language Models

Related topics