Frequent verification codes may appear for non-Mainland China IP visits. If visitors are severely affected, please send [IP|ASN](|AS14618) to the bottom mailbox to add to the whitelist


2024-01-05 01:02   Splitwise improves GPU usage by splitting LLM inference phases    #Microsoft Research Blog #安全文章 Expanded LLM use creates new demands on cloud GPU capacity. Splitwise presents an efficient solution by separating the two essential phases of LLM inference, achieving higher throughput within a limited power budget.The post Splitwise improves GPU usage by splitting LLM inference phases appeared fi

2023-12-23 01:00   Research at Microsoft 2023: A year of groundbreaking AI advances and discoveries    #Microsoft Research Blog #安全文章 AI saw unparalleled growth in 2023, reaching millions daily. This progress owes much to the extensive work of Microsoft researchers and collaborators. In this review, learn about the advances in 2023, which set the stage for further progress in 2024.The post Research at Microsoft 2023: A year of gro

2023-12-21 01:00   Research Focus: Week of December 18, 2023    #Microsoft Research Blog #安全文章 In this issue of Research Focus: Optimized exit-augmented models for scalable efficient inference; NeurIPS LLM Efficiency Challenge; LLM-empowered automated data exploration; Boosting cloud efficiency with data-driven decision-making and optimization.The post Research Focus: Week of December 18, 202

2023-12-19 02:00   AI Frontiers: A deep dive into deep learning with Ashley Llorens and Chris Bishop    #Microsoft Research Blog #安全文章 In this episode of “AI Frontiers,” AI4Science Director Chris Bishop talks about the state of deep learning; his new textbook, “Deep Learning: Foundations and Concepts,” and the impact the field is having on the natural sciences.The post AI Frontiers: A deep dive into deep learning with Ashley Lloren

2023-12-13 20:07   Abstracts: December 12, 2023    #Microsoft Research Blog #安全文章 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, Senior Principal Research Manager Tao

2023-12-12 22:40   Steering at the Frontier: Extending the Power of Prompting    #Microsoft Research Blog #安全文章 We’re seeing exciting capabilities of frontier foundation models, including intriguing powers of abstraction, generalization, and composition across numerous areas of knowledge and expertise. Even seasoned AI researchers have been impressed with the ability to steer the models with straightforward,

2023-12-12 22:00   Phi-2: The surprising power of small language models    #Microsoft Research Blog #安全文章 Phi-2 is now accessible on the Azure model catalog. Its compact size and new innovations in model scaling and training data curation make it ideal for exploration around mechanistic interpretability, safety improvements, and fine-tuning experimentation on a variety of tasks.The post Phi-2: The surpr

2023-12-12 06:01   Abstracts: December 11, 2023    #Microsoft Research Blog #安全文章 By treating language models as layers in a network and prompts as learnable parameters, researchers aim for more adaptable, reusable LLM architectures. Check out the work in the “Abstracts” podcast series with guest Alessandro Sordoni and at #NeurIPS2023:The post Abstracts: December 11, 2023 appeare

2023-12-11 23:00   NeurIPS 2023 highlights breadth of Microsoft’s machine learning innovation    #Microsoft Research Blog #安全文章 We’re proud to have 100+ accepted papers At NeurIPS 2023, plus 18 workshops. Several submissions were chosen as oral presentations and spotlight posters, reflecting groundbreaking concepts, methods, or applications. Here’s an overview of those submissions.The post NeurIPS 2023 highlights breadth of

2023-12-08 04:32   MatterGen: Property-guided materials design    #Microsoft Research Blog #安全文章 The central problem in materials science is to discover materials with desired properties. MatterGen enables broad property-guided materials design.The post MatterGen: Property-guided materials design appeared first on Microsoft Research.

2023-12-08 01:00   LLMLingua: Innovating LLM efficiency with prompt compression    #Microsoft Research Blog #安全文章 Advanced prompting technologies for LLMs can lead to excessively long prompts, causing issues. Learn how LLMLingua compresses prompts up to 20x, maintaining quality, reducing latency, and supporting improved UX.The post LLMLingua: Innovating LLM efficiency with prompt compression appeared first on M

2023-12-07 02:35   Abstracts: December 6, 2023    #Microsoft Research Blog #安全文章 "Abstracts”—your source for world-class research in brief—welcomes Senior Principal Research Manager Xing Xie to the podcast series to discuss his paper on evaluating general-purpose AI with psychometrics.The post Abstracts: December 6, 2023 appeared first on Microsoft Research.

2023-12-07 01:00   Microsoft at ESEC/FSE 2023: AI techniques for a streamlined coding workflow    #Microsoft Research Blog #安全文章 Explore the latest AI innovations aiming to advance the software development lifecycle. AdaptivePaste adapts and refines pasted code snippets in an IDE. InferFix automates bug detection and repair. Discover how.The post Microsoft at ESEC/FSE 2023: AI techniques for a streamlined coding workflow appe

2023-12-06 22:54   Research Focus: Week of December 4, 2023    #Microsoft Research Blog #安全文章 Research Focus: Using LLMs in a Rust-based formal verification framework; Rethinking network measurements with user feedback; 3D telemedicine using HoloportationTM communication technology could enhance overseas surgical visits.The post Research Focus: Week of December 4, 2023 appeared first on Micr

2023-12-06 01:00   Exploring LLMs’ potential to help facilitators enhance online healthcare communities    #Microsoft Research Blog #安全文章 Many patients in low- and middle-income countries rely on facilitated online health communities for information and support. Discover how large language models can assist the facilitators and boost outcomes.The post Exploring LLMs’ potential to help facilitators enhance online healthcare communities