Microsoft Research Podcast

Behnaz Arzani loves hard problems and the freedom to explore. That makes research a great fit! She discusses her work in network management, including the potential role of LLMs in the field; the challenges that excite her; and how storytelling changed her life.

Learn more:

• Solving Max-Min Fair Resource Allocations Quickly on Large Graphs | Publication, February 2024
• Finding Adversarial Inputs for Heuristics using Multi-level Optimization | Publication, February 2024
• MetaOpt: Examining, explaining, and improving heuristic performance | Microsoft Research blog, January 2024
• A Holistic View of AI-driven Network Incident Management | Publication, October 2023
• Behnaz Arzani: Painting, storytelling, and other hobbies | Microsoft Research bio page

Researcher Jindong Wang and Associate Professor Steven Euijong Whang explore the NeurIPS 2024 work ERBench. ERBench leverages relational databases to create LLM benchmarks that can verify model rationale via keywords in addition to checking answer correctness.

Read the paper

Get datasets and codes

Members of the research community at Microsoft work continuously to advance their respective fields. Abstracts brings its audience to the cutting edge with them through short, compelling conversations about new and noteworthy achievements.

In this episode, Dr. Sheng Zhang, a Senior Researcher at Microsoft Research, joins host Dr. Gretchen Huizinga to discuss “UniversalNER: Targeted Distillation from Large Language Models for Open Named Entity Recognition.” In this paper, Zhang and his coauthors present mission-focused instruction tuning, a method for distilling large language models into smaller, more efficient ones for a broad application class. Their UniversalNER models achieved state-of-the-art performance in named entity recognition, an important natural language processing (NLP) task. Model distillation has the potential to make NLP and other capabilities more accessible, particularly in specialized domains such as biomedicine, which could benefit from more resource-efficient and transparent options.

Learn more:

• View the paper
• UniversalNER project website with demo
• Code on GitHub
• Dataset and models on Hugging Face

Transforming research ideas into meaningful impact is no small feat. It often requires the knowledge and experience of individuals from across disciplines and institutions. Collaborators, a new Microsoft Research Podcast series, explores the relationships—both expected and unexpected—behind the projects, products, and services being pursued and delivered by researchers at Microsoft and the diverse range of people they’re teaming up with.

In this episode, Dr. Gretchen Huizinga talks with Microsoft Health Futures Senior Director Javier Alvarez and Dr. Raj Jena, a radiation oncologist at Addenbrooke’s hospital, part of Cambridge University Hospitals in the United Kingdom, about Project InnerEye, a Microsoft Research effort that applies machine learning to medical image analysis. The pair shares how a 10-plus-year collaborative journey—and a combination of research and good software engineering—has resulted in the hospital’s creation of an AI system that is helping to decrease the time cancer patients have to wait to begin treatment. Alvarez and Jena chart the path of their collaboration in AI-assisted medical imaging, from Microsoft Research’s initiation of Project InnerEye and its decision to make the resulting research tools available in open source to Addenbrooke’s subsequent testing and validation of these tools to meet the regulatory requirements for use in a clinical setting. They also discuss supporting clinician productivity—and ultimately patient outcomes—and the important role patients play in incorporating AI into healthcare.

Learn more:

• Project InnerEye | Project page
• How AI is helping to shrink waiting times for NHS cancer patients | Microsoft News Centre UK blog post, June 2023
• Accounting for past imaging studies: Enhancing radiology AI and reporting | Microsoft Research blog, June 2023
• Microsoft Health Futures | Lab page
• Biomedical Imaging | Research group page
• Evaluation of Deep Learning to Augment Image Guided Radiotherapy for Head and Neck and Prostate Cancers | JAMA publication, November 2020

Powerful large-scale AI models like GPT-4 are showing dramatic improvements in reasoning, problem-solving, and language capabilities. This marks a phase change for artificial intelligence—and a signal of accelerating progress to come.

In this Microsoft Research Podcast series, AI scientist and engineer Ashley Llorens hosts conversations with his collaborators and colleagues about what these models—and the models that will come next—mean for our approach to creating, understanding, and deploying AI, its applications in areas such as healthcare and education, and its potential to benefit humanity.

This episode features Partner Research Manager Hanna Wallach, whose research into fairness, accountability, transparency, and ethics in AI and machine learning has helped inform the use of AI in Microsoft products and services for years. Wallach describes how she and a team of applied scientists expanded their tools for measuring fairness-related harms in AI systems to address harmful content more broadly during their involvement in the deployment of Bing Chat; her interest in filtering, a technique for mitigating harms that she describes as widely used but not often talked about; and the cross-company collaboration that brings policy, engineering, and research together to evolve and execute the Microsoft approach to developing and deploying AI responsibly.

Learn more:

Microsoft AI: Responsible AI Principles and Approach

AI and Microsoft Research