Microsoft Research Podcast

A lack of appropriate data, decreased model performance, and other obstacles have made it difficult to expand the input language models can receive. Li Lyna Zhang introduces LongRoPE, a method capable of extending content windows to more than 2 million tokens.Read the paperGet the code

Senior Researcher Arindam Mitra introduces AgentInstruct. Using raw data sources, the automated multi-agent framework can create diverse, high-quality synthetic data at scale for the post-training of small and large language models.Read the paper

Printed circuit boards are abundant—in the stuff we use and in landfills. Researcher Jake Smith and professor Aniruddh Vashisth discuss the development of vitrimer-based PCBs that perform comparably to traditional PCBs but have less environmental impact.Learn more:* Recyclable vitrimer-based printed circuit boards for sustainable electronics (https://www.microsoft.com/en-us/research/publication/recyclable-vitrimer-based-printed-circuit-boards-for-sustainable-electronics/) | Nature Sustainability, April 2024* Microsoft Climate Research Initiative (https://www.microsoft.com/en-us/research/collaboration/microsoft-climate-research-initiative/)* Microsoft Research AI for Science (https://www.microsoft.com/en-us/research/lab/microsoft-research-ai-for-science/)* Storing digital data in synthetic DNA with Dr. Karin Strauss (https://www.microsoft.com/en-us/research/podcast/storing-digital-data-in-synthetic-dna-with-dr-karin-strauss/) | Microsoft Research Podcast, October 2018

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 (https://www.microsoft.com/en-us/research/publication/solving-max-min-fair-resource-allocations-quickly-on-large-graphs/) | Publication, February 2024* Finding Adversarial Inputs for Heuristics using Multi-level Optimization (https://www.microsoft.com/en-us/research/publication/finding-adversarial-inputs-for-heuristics-using-multi-level-optimization/) | Publication, February 2024* MetaOpt: Examining, explaining, and improving heuristic performance (https://www.microsoft.com/en-us/research/blog/metaopt-examining-explaining-and-improving-heuristic-performance/) | Microsoft Research blog, January 2024* A Holistic View of AI-driven Network Incident Management (https://www.microsoft.com/en-us/research/publication/a-holistic-view-of-ai-driven-network-incident-management/) | Publication, October 2023* Behnaz Arzani: Painting, storytelling, and other hobbies (https://www.microsoft.com/en-us/research/people/bearzani/painting-and-other-hobbies/) | Microsoft Research bio page

Principal PM Manager Weishung Liu shares how a career delivering products and customer experiences aligns with her love of people and storytelling and how—despite efforts to defy the expectations that come with growing up in Silicon Valley—she landed in tech.Learn more:* Weishung Liu at Microsoft Research (https://www.microsoft.com/en-us/research/people/weisliu/)* Watch For (https://www.microsoft.com/en-us/research/project/watch-for/overview/) | Project page* Developer Tech Minutes: Watch For (https://www.microsoft.com/en-us/research/video/developer-tech-minutes-watch-for/) | Video, 2021

Social scientist and HCI expert Abigail Sellen explores the critical understanding needed to build human-centric AI through the lens of the new AICE initiative, a collective of interdisciplinary researchers studying AI impact on human cognition and the economy.Learn more:* AI, Cognition, and the Economy (AICE) (https://www.microsoft.com/en-us/research/collaboration/ai-cognition-and-the-economy-aice/) * Responsible AI Principles and Approach | Microsoft AI (https://www.microsoft.com/en-us/ai/principles-and-approach/)  * The Rise of the AI Co-Pilot: Lessons for Design from Aviation and Beyond (https://www.microsoft.com/en-us/research/publication/the-rise-of-the-ai-co-pilot-lessons-for-design-from-aviation-and-beyond/) * The Myth of the Paperless Office (https://www.microsoft.com/en-us/research/publication/myth-paperless-office/)

Andrey Kolobov discusses WindSeer, a small CNN capable of estimating the wind field around an sUAV in flight more finely and with less compute and data than traditional models. The advancement can help support longer and safer autonomous flights.Learn more:* WindSeer: Real-time volumetric wind prediction over complex terrain aboard a small uncrewed aerial vehicle (https://www.microsoft.com/en-us/research/publication/windseer-real-time-volumetric-wind-prediction-over-complex-terrain-aboard-a-small-uav/)

Jacki O'Neill saw an opportunity to expand Microsoft research efforts to Africa. She now leads Microsoft Research Africa, Nairobi (formerly MARI). O'Neill talks about the choices that got her there, the lab’s impact, and how living abroad is good for innovation. Learn more:* Jacki O'Neill at Microsoft Research (https://www.microsoft.com/en-us/research/people/jaoneil/?msockid=23b9b9353d686c6e3047ad083c866df5)* Microsoft Research Africa (formerly MARI) (https://www.microsoft.com/en-us/research/group/microsoft-africa-research-institute-mari/)

Researcher Michel Galley explores how he and fellow researchers combined new and existing data to create MathVista, an open-source benchmark for measuring the mathematical reasoning capabilities of foundation models in scenarios that involve text and images.Read the paperGet the code & dataset

Energized by disruption, partner group product manager Rafah Hosn is helping to drive scientific advancement in AI for Microsoft. She talks about the mindset needed to work at the frontiers of AI and how the research-to-product pipeline is changing in the GenAI era.Learn more:* AI Frontiers - Microsoft Research (https://www.microsoft.com/en-us/research/lab/ai-frontiers/)* Responsible AI Principles and Approach | Microsoft AI (https://www.microsoft.com/en-us/ai/principles-and-approach/)