PROSE
AI-Assisted Programming
Nouvelles et reportages
Research Focus: Week of November 11, 2024
Holistic motion-capture calibration technique without calibration, manual intervention or custom hardware; Research on AI agents for autonomous clouds; Automating proof-oriented program construction; One-to-many testing for natural language code generation.
Research Focus: Week of October 28, 2024
New Research | FLASH: Workflow automation agent for diagnosing recurring incidents; METAREFLECTION: Learning instructions for language agents using past reflections; Boosting LLM training efficiency through faster communication between GPUs; and more.
Research Focus: Week of October 7, 2024
Simplifying secure decision tree training; Improving accuracy of audio content detection; A novel neurosymbolic system for converting text to tables; New video series: AI for Business Transformation; TEE security protections for container workloads.
RUBICON: Evaluating conversations between humans and AI systems
| Param Biyani, Yasharth Bajpai, Arjun Radhakrishna, Gustavo Soares, et Sumit Gulwani
RUBICON evaluates AI-driven conversations and improves their quality by learning detailed domain-specific rubrics from minimal data. It gathers insights on AI assistant performance while maintaining user privacy and data security.
Research Focus: Week of April 29, 2024
In this edition: Can LLMs transform natural language into formal method postconditions; Semantically aligned question + code generation for automated insight generation; Explaining CLIP performance disparities on blind/low vision data; plus recent news.
Research Focus: Week of March 18, 2024
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) have shown impressive capabilities, yet they still struggle with…
Research Focus: Week of July 3, 2023
In this issue: A new study looks at engineers’ views on hybrid work; prompt engineering adds context and specificity to generative AI models; Overwatch learns code edit patterns to aid developers; a Qlib update addresses financial market challenges.
Safe program merges at scale: A grand challenge for program repair research
| Shuvendu Lahiri
Since the computing world began embracing an open-source approach to programming, building software has become increasingly collaborative. Members of development teams with as few as two developers and as many as thousands are simultaneously editing different components in creating software…
Creating the Future of Software Development
“If you think about the world that we’re in now, software plays a key role in our lives – in everything we do. And at the core of solving big problems and fundamental challenges is the ability to use software…