-
Dec 4, 2024 | 
microsoft.com | Brenda Potts
Welcome to Research Focus, a series of blog posts that highlights notable publications, events, code/datasets, new hires and other milestones from across the research community at Microsoft. n-party Multi-Party Computation (MPC) is a cryptographic protocol technique that allows separate parties to securely compute a function on their joint data while keeping their inputs private.
-
Nov 25, 2024 | 
microsoft.com | Darren Edge |Ha Trinh |Jonathan Larson |Brenda Potts
The GraphRAG project (opens in new tab) aims to expand the class of questions that AI systems can answer over private datasets by leveraging the implicit relationships within unstructured text. A key advantage of GraphRAG over conventional vector RAG (or “semantic search”) is its ability to answer global queries that address the entire dataset, such as “what are the main themes in the data?”, or “what are the most important implications for X?”.
-
Nov 18, 2024 | 
microsoft.com | Hoifung Poon |Brenda Potts
In cancer diagnosis or advanced treatments like immunotherapy, every detail in a medical image counts. Radiologists and pathologists rely on these images to track tumors, understand their boundaries, and analyze how they interact with surrounding cells. This work demands pinpoint accuracy across several tasks—identifying whether a tumor is present, locating it precisely, and mapping its contours on complex CT scans or pathology slides.
-
Nov 14, 2024 | 
microsoft.com | Arindam Mitra |Ahmed Awadallah |Yash Lara |Brenda Potts
Our work on Orca and Orca 2 demonstrated the power of using synthetic data for the post-training of small language models and getting them to levels of performance previously found only in much larger language models. Orca-AgentInstruct is another step in this direction, where we explore using agentic flows to generate diverse and high-quality data at scale. Orca-AgentInstruct is an agentic solution for synthetic-data generation.
-
Nov 13, 2024 | 
microsoft.com | Darya Moldavskaya |Alessandro Sordoni |Brenda Potts |Lucas Caccia
Today, development of generalizable AI models requires access to sufficient data and compute resources, which may create challenges for some researchers. Democratizing access to technology across the research community can advance the development of generalizable AI models. By applying the core software development concept of modularity to AI, we can build models that are powerful, efficient, adaptable, and transparent. Until recently, AI models were primarily built using monolithic architecture.
-
Nov 13, 2024 | 
microsoft.com | Brenda Potts
Welcome to Research Focus, a series of blog posts that highlights notable publications, events, code/datasets, new hires and other milestones from across the research community at Microsoft. Motion-capture technologies used in film and game production typically focus solely on face, body, or hand capture, requiring complex and expensive hardware and lots of manual intervention from skilled operators.
-
Oct 9, 2024 | 
microsoft.com | Brenda Potts
Welcome to Research Focus, a series of blog posts that highlights notable publications, events, code/datasets, new hires and other milestones from across the research community at Microsoft. In a recent paper: Securely Training Decision Trees Efficiently that will appear at ACM CCS 2024, researchers from Microsoft significantly reduce the communication complexity of secure decision tree training. Decision trees are an important class of supervised learning algorithms.
-
Sep 26, 2024 | 
microsoft.com | Brenda Potts
Microsoft Research Forum is a continuous exchange of ideas about science and technology research in the era of general AI. In the latest episode (opens in new tab), researchers discussed the latest multimodal AI models, advanced benchmarks for AI evaluation and model self-improvement, and an entirely new kind of computer for AI inference and hard optimization.
-
Sep 12, 2024 | 
microsoft.com | Brenda Potts
Welcome to Research Focus, a series of blog posts that highlights notable publications, events, code/datasets, new hires and other milestones from across the research community at Microsoft. Large language models (LLMs) are the de facto standard for numerous machine learning tasks, ranging from text generation and summarization to even code generation. They also play an integral role in various natural language processing (NLP) tasks.
-
Sep 10, 2024 | 
microsoft.com | Robert Osazuwa Ness |Brenda Potts
Large language models (LLMs) have achieved unprecedented accuracy on medical question-answering benchmarks, showcasing their potential to revolutionize healthcare by supporting clinicians and patients. However, these benchmarks often fail to capture the full complexity of real-world medical scenarios. To truly harness the power of LLMs in healthcare, we must go beyond these benchmarks by introducing challenges that bring us closer to the nuanced realities of clinical practice.
