Researcher in Microsoft Research Asia
Beijing, China
Joined April 2009
- Tweets93
- Following150
- Followers260
- Likes12
Xing Xie (谢幸) retweeted
Today, we welcome the 2026 Microsoft Research Fellowship cohort, an inspiring global community of fellows and advisors helping to shape what’s next across science, technology, and society. Join us in celebrating this year’s recipients: msft.it/6013Q45bX
These contributions span the following themes:
• AI for global and societal impact
• AI fundamentals: scalable reasoning, model adaption and evaluation
• Biological and scientific modeling
• Foundational systems & infrastructure for AI
• Human-AI collaboration and interaction
• Multimodal & embodied intelligence
Xing Xie (谢幸) retweeted
ADeLe profiles AI models across a set of core abilities and compares them to task requirements. Published in @Nature, this framework enables accurate prediction of model performance on tasks they have not encountered before: msft.it/6015QLEuN
Xing Xie (谢幸) retweeted
Discover how Microsoft Research is leveraging AI to transform research processes, accelerate innovation, and drive growth. Learn more about the strategies and tools empowering researchers here: msft.it/6011SZK8U
How do we evaluate AI on tasks it's never seen before?
In our Societal AI white paper, we pose this key question. With Jose's team, we're developing ADeLe, a psychometrics-inspired framework to assess AI abilities beyond benchmarks. #SocietalAI #ResponsibleAI #MicrosoftResearch
ADeLe, a new evaluation method, explains what AI systems are good at—and where they’re likely to fail. By breaking tasks into ability-based requirements, it has the potential to provide a clearer way to evaluate and predict AI model performance: msft.it/6014SkVGC
Paper: microsoft.com/en-us/research…
AFMR Program: microsoft.com/en-us/research…
Societal AI white paper: microsoft.com/en-us/research…
Xing Xie (谢幸) retweeted
ADeLe, a new evaluation method, explains what AI systems are good at—and where they’re likely to fail. By breaking tasks into ability-based requirements, it has the potential to provide a clearer way to evaluate and predict AI model performance: msft.it/6014SkVGC
Excited to share the Societal AI research agenda—a cross-disciplinary effort to align AI with human values and societal needs. Check out our white paper and podcast hosted by Gretchen Huizinga! Thanks to all contributors! #SocietalAI #ResponsibleAI #MicrosoftResearch
Learn about a new white paper on Societal AI, an interdisciplinary framework for guiding AI development that reflects shared human values. It presents key research challenges and emphasizes collaboration across disciplines: msft.it/6016Sp3Na
ALT A diagram with a gradient background transitioning from blue on the left to pink on the right. In the center, there is a circle labeled 'Societal AI.' On the left side of the circle, there is an icon of a computer monitor with the text 'Computer Science' below it. On the right side of the circle, there are two abstract human figures with the text 'Social Science' below them. Arrows connect 'Computer Science' and 'Social Science' to 'Societal AI.'
White paper: microsoft.com/en-us/research…
Podcast: microsoft.com/en-us/research…
Xing Xie (谢幸) retweeted
“Abstracts”—your source for world-class research in brief—welcomes Senior Principal Research Manager @xingustc to the podcast series to discuss his paper on evaluating general-purpose AI with psychometrics: msft.it/6010iRDUA
Xing Xie (谢幸) retweeted
During the "Building User Trust through Privacy, Identity, and Responsible AI" track at #MSFTResearchSummit, sessions address the question: What role can research play in understanding and building trust in technology? Learn more: msft.it/6019dyrgb
Registration for the MIND News Recommendation Competition (msnews.github.io/competition…) will be closed in three days! Official test data and ranking will be made available since Aug. 21. There will be also a total prize of $20K for winners. Please do not miss it and register NOW!
Xing Xie (谢幸) retweeted
Let the MIND Games begin! The MIND team challenges you to imagine unique ways to rank news articles that align with user interests. Download the training dataset to test algorithms until August 20, 2020. Competition begins Aug 21 & offers $20K in prizes: aka.ms/AA91teh
Xing Xie (谢幸) retweeted
本日は MIRF 2011で講演予定です．NICT 木俵さん，阪大 原先生もご講演．
mirf2011.org/
Xing Xie (谢幸) retweeted
Xing Xie from MSRA now talking about learning location naming from user check-in histories at #mirf2011
Best papers for @ubicomp2011, Nurturing Natural Sensors, Haptic Reassurance in the Pitch Black for an Immersive Theatre Experience.
The hottest @ubicomp2011 tutorial is "Building&Deploying Mobile Systems for Activity Recognition" by @niclane7, Tanzeem & Pedja. 50 people!
USB disk for @ubicomp2011, very Chinese style, designed and sponsoed by Vivick. t.cn/ar8YXP
