Eric Poe Xing (Chinese: 邢波) is an American computer scientist who has been serving as president of Mohamed bin Zayed University of Artificial Intelligence (MBZUAI) since January 2021. He is also a professor in the Carnegie Mellon University School of Computer Science where he founded the SAILING Lab in 2004, and is the co-founder of the AI companies Petuum and GenBio AI. Xing's research focuses on statistical machine learning, probabilistic graphical models, and systems for distributed machine learning. He was elected a Fellow of the Institute of Electrical and Electronics Engineers in 2019 for "contributions to machine learning algorithms and systems" and a Fellow of the Association for Computing Machinery in 2022 for "contributions to algorithms, architectures, and applications in machine learning." == Education == Xing earned a B.Sc. in physics from Tsinghua University in 1993, and an M.Sc. in computer science from Rutgers University in 1998. He earned a Ph.D. in molecular biology and biochemistry from Rutgers in 1999, supervised by molecular cancer researcher Chung S. Yang. His dissertation examined the inactivation of the Rb and p53 pathways in human esophageal squamous cell carcinoma. He earned a second Ph.D. in computer science from the University of California, Berkeley in 2004, supervised by Richard Karp, Michael I. Jordan, and Stuart J. Russell. His thesis applied probabilistic graphical models to motif identification and haplotype inference in genomic data. == Career == Xing joined Carnegie Mellon University (CMU) as a faculty member in 2004, where he created the Statistical Artificial Intelligence and Integrative Genomics (SAILING) Lab. He held visiting appointments from 2010 to 2011, serving as a visiting research professor at Facebook Inc. and as a visiting associate professor in the Department of Statistics at Stanford University. He served as co-Program Chair of the International Conference on Machine Learning (ICML) in 2014 and General Chair in 2019. Xing served as the founding director of CMU’s Center for Machine Learning and Health, established in 2015 as part of the Pittsburgh Health Data Alliance, a collaboration between CMU, the University of Pittsburgh, and the University of Pittsburgh Medical Center. In 2016, Xing co-founded Petuum Inc., a US-based startup. In 2017, Petuum raised $93 million in a round of venture funding from SoftBank. In 2018 Petuum was named a World Economic Forum Technology Pioneer. In 2019, Xing received the Carnegie Science Award for Startup Entrepreneurs in recognition of his leadership of Petuum. On 29 November 2020, Xing was appointed president of the Mohamed bin Zayed University of Artificial Intelligence (MBZUAI), with the appointment taking effect in January 2021. In 2024, Xing co-founded GenBio AI where he is chief scientist. The US-based startup, which he co-founded with David Baker, Ziv Bar-Joseph, Emma Lundberg, Le Song and Fred Hu, aims to create AI-driven digital organisms (AIDO) for the purposes of modeling medical treatments. Xing has overseen the launch of the MBZUAI Institute of Foundation Models (IFM), which focuses on research and development of large-scale foundation models. In 2025–2026, IFM released the open-source reasoning model K2 Think, which was covered internationally as part of the UAE’s push to develop domestically controlled (“sovereign”) AI capabilities. IFM presented PAN as a “world model” research project and demonstrated related systems publicly. MBZUAI also collaborated with G42 and Cerebras Systems on the Jais language model, an open-source Arabic–English large language model released in 2023, according to Reuters. == Awards and honors == Xing is a recipient of the National Science Foundation (NSF) Career Award and the Alfred P. Sloan Research Fellowship. Xing is an elected Fellow of the following institutes and associations: Association for the Advancement of Artificial Intelligence (AAAI) 2016 Institute of Electrical and Electronics Engineers (IEEE) 2019 for "contributions to machine learning algorithms and systems" American Statistical Association (ASA) 2022 Association for Computing Machinery (ACM) 2022 for "contributions to algorithms, architectures, and applications in machine learning" Institute of Mathematical Statistics (IMS) 2023 International Society for Computational Biology (ISCB) 2026 == Selected publications == Eric P. Xing; Michael I. Jordan; Stuart J. Russell; Andrew Y. Ng (2003). "Distance Metric Learning with Application to Clustering with Side-Information" (PDF). Advances in Neural Information Processing Systems 15. Advances in Neural Information Processing Systems. Wikidata Q77691192. Edoardo M. Airoldi; David M. Blei; Stephen E Fienberg; Eric P Xing (1 September 2008). "Mixed Membership Stochastic Blockmodels". Journal of Machine Learning Research. 9: 1981–2014. ISSN 1533-7928. PMC 3119541. PMID 21701698. Wikidata Q35058357. Eric P. Xing; Michael I. Jordan; Richard M. Karp (28 June 2001), Feature selection for high-dimensional genomic microarray data, vol. 18, pp. 601–608, Wikidata Q138678867 Xing EP; Karp RM (1 January 2001). "CLIFF: clustering of high-dimensional microarray data via iterative feature filtering using normalized cuts". Bioinformatics. 17 Suppl 1: S306-15. doi:10.1093/BIOINFORMATICS/17.SUPPL_1.S306. ISSN 1367-4803. PMID 11473022. Wikidata Q30657299.
ShowScoop
ShowScoop is a website and mobile app platform on which users can rate and review artists, concerts, and music festivals that they have seen/attended. The reviews and ratings are designed to be informative of how well such performances are live. This helps concert-goers decide which live music events they want to attend. == History == ShowScoop was founded in August 2012 by Micah Smurthwaite and is based out of San Diego, CA. In February 2013, ShowScoop launched its mobile app at the SF Music Tech Summit. The application is currently available on the iPhone, with plans to expand into the Android market in the future. == Services == ShowScoop uses crowdsourcing to provide accurate ratings of live concert experiences. In addition to viewing ratings, users are encouraged to rate and review concerts they have attended. The ShowScoop database includes nearly one million artists and over 2.5 million live music events. ShowScoop users can rate artists on four aspects of the performance: stage presence, crowd interaction, sound quality, and visual effects. The rating system uses an ascending scale from one to five in each of the aspects, with five being the highest score. In addition to the quantitative ratings, ShowScoop users are also free to write qualitative reviews in a provided comment section. This allows users to explain their ratings and add further insight or opinion. ShowScoop incorporates several facets of social media into its services. Users can create a user profile to share limited personal information and store their ratings and reviews. Users are also given the option of sharing their evaluations with their social networks on Facebook and Twitter. Users can "like" reviews, follow artists, and follow other ShowScoop users. The mobile app allows users to take photos, apply filters, and share the final image in conjunction with reviews and through Instagram. == Road Crew == ShowScoop's "Road Crew" is a group made up of top contributors within the ShowScoop community. The Road Crew assists in curating artist pages, assuring information quality and accuracy. In return, members of the Road Crew are given incentives, including free tickets to concerts and personal invitations to exclusive shows. Applicants to the Road Crew are judged on the number and quality of their reviews, the photos and videos they have posted, and their general engagement with the ShowScoop community in following and liking users and reviews.
Tail latency
Tail latency is a term used to describe the high-percentile response times seen in a system. This is usually measured at the 95th, 99th, or 99.9th percentile, not the average latency. In distributed systems, cloud computing, and large-scale web services, even a small number of slow requests can make the user experience and system performance much worse. Tail latency often happens because of things like resource contention, network variability, garbage collection pauses, and hardware heterogeneity. A major problem in system design is managing tail latency, because lowering average latency doesn't always make the worst-case performance better. To lessen its effects, people often use techniques like request hedging, replication, load balancing, and adaptive timeouts. In latency-sensitive applications like search engines, financial systems, and real-time services, where service-level objectives (SLOs) are often based on high-percentile latencies, it is especially important to understand and improve tail latency.
GeneXus
GeneXus is a low code, cross-platform, knowledge representation-based development tool, mainly oriented towards enterprise-class applications for web applications, smart devices, and the Microsoft Windows platform. GeneXus uses mostly declarative language to generate native code for multiple environments. It includes a normalization module, which creates and maintains an optimal database structure based on user views. The languages for which code can be generated include COBOL, Java, Objective-C, RPG, Ruby, Visual Basic, and Visual FoxPro. Some of the DBMSs supported are Microsoft SQL Server, Oracle, IBM Db2, Informix, PostgreSQL, and MySQL. GeneXus was developed by Uruguayan company ARTech Consultores SRL which later renamed to Genexus SA. The latest version is GeneXus 18, which was released on November 10, 2022.
Scripped
Scripped was an online screenplay services company offering three services: script writing, script registration, and script coverage. Scripped did not facilitate collaboration among screenwriters. It combined with Zhura in 2010. According to Techcrunch, Scripped had more than 60,000 writers as of March 2010. Scripped was administered by Sunil Rajaraman, Ryan Buckley and Zak Freer. Actor, writer, and director Edward Burns and screenwriter Steven E. de Souza joined Scripped's Board of Advisers in May 2008. In 2008, the company formed a partnership with Write Brothers, makers of Movie Magic Screenwriter software. On March 29, 2010, Scripped announced that it closed $250,000 in private investment and merged with competitor Zhura. Scripped's CEO, Sunil Rajaraman, remains the merged company's Chief Executive Officer. On April 1, 2015, citing a serious technical failure, Scripped shuttered its service. As part of the announcement, it was disclosed that their backup servers had failed as well, losing all of its users' stored scripts. The website URL currently redirects to WriterDuet's website, another online scriptwriting service; Scripped had advertised WriterDuet in Scripped's shutdown open letter. == Features == The Scripped Writer provided a built-in screenplay template which formatted the document to a standard for scripts as recommended by the AMPAS. The screenplay document was composed of seven elements: scene, action, character, dialog, parenthetical, transition and general. Each element had a specific style to which the Scripped Writer conformed as text was entered. Like other client-side screenplay software, Scripped offered Tab-Enter toggling between screenplay elements, making the writing process much faster. Text files could be imported into the Scripped Writer and automatically conformed to the screenplay template. Completed scripts could be exported as PDF files. In May 2011 the administrators of Scripped launched Scripted.com - a sister site focused on freelance writing jobs. Subsequent to the service's launch, the company was renamed to Scripted, Inc.
Orleans (software framework)
Orleans is a cross-platform software framework for building scalable and robust distributed interactive applications based on the .NET Framework or on the more recent .NET. == Overview == Orleans was originally created by the eXtreme Computing Group at Microsoft Research and introduced the virtual actor model as a new approach to building distributed systems for the cloud. Orleans scales from a single on-premises server to highly-available and globally distributed applications in the cloud. The virtual actor model is based on the actor model but has several differences: A virtual actor always exists, it cannot be explicitly created or destroyed. Virtual actors are automatically instantiated. If a server hosting an actor crashes, the next message sent to the actor causes it to be reinstantiated automatically. The server that an actor is on is transparent to the application code. Orleans can automatically create multiple instances of the same stateless actor. Starting with cloud services for the Halo franchise, the framework has been used by a number of cloud services at Microsoft and other companies since 2011. The core Orleans technology was transferred to 343 Industries and is available as open source since January 2015. The source code is licensed under MIT License and hosted on GitHub. Orleans runs on Microsoft Windows, Linux, and macOS and is compatible with .NET Standard 2.0 and above. == Features == Some Orleans features include: Persistence Distributed ACID transactions Streams Timers & Reminders Fault tolerance == Related implementations == The Electronic Arts BioWare division created Project Orbit. It is a Java implementation of virtual actors that was heavily inspired by the Orleans project.
Brownout (software engineering)
Brownout in software engineering is a technique that involves disabling certain features of an application. == Description == Brownout is used to increase the robustness of an application to computing capacity shortage. If too many users are simultaneously accessing an application hosted online, the underlying computing infrastructure may become overloaded, rendering the application unresponsive. Users are likely to abandon the application and switch to competing alternatives, hence incurring long-term revenue loss. To better deal with such a situation, the application can be given brownout capabilities: The application will disable certain features – e.g., an online shop will no longer display recommendations of related products – to avoid overload. Although reducing features generally has a negative impact on the short-term revenue of the application owner, long-term revenue loss can be avoided. The technique is inspired by brownouts in power grids, which consists in reducing the power grid's voltage in case electricity demand exceeds production. Some consumers, such as incandescent light bulbs, will dim – hence originating the term – and draw less power, thus helping match demand with production. Similarly, a brownout application helps match its computing capacity requirements to what is available on the target infrastructure. Brownout complements elasticity. The former can help the application withstand short-term capacity shortage, but does so without changing the capacity available to the application. In contrast, elasticity consists of adding (or removing) capacity to the application, preferably in advance, so as to avoid capacity shortage altogether. The two techniques can be combined; e.g., brownout is triggered when the number of users increases unexpectedly until elasticity can be triggered, the latter usually requiring minutes to show an effect. Brownout is relatively non-intrusive for the developer, for example, it can be implemented as an advice in aspect-oriented programming. However, surrounding components, such as load-balancers, need to be made brownout-aware to distinguish between cases where an application is running normally and cases where the application maintains a low response time by triggering brownout. == Usage in phased deprecation == A related use of the brownout concept in software engineering is the deliberate introduction of temporary outages to a system, API or feature that is being phased out. This is sometimes also called a "scream test" when it is used to discover unknown dependents of a system or API. The intention is to allow detection of downstream consumers of an API or service who may otherwise have missed deprecation announcements or to uncover hidden side-effects of the deprecation that may have been overlooked. The intention is that developers of dependent systems will notice their own system failures caused by the upstream brownout. Such brownouts are typically pre-announced scheduled outages or probabilistic in nature (such as artificially failing a percentage of requests). As a brownout is only a temporary or partial outage, it provides downstream consumers of an API or service time to remove any discovered dependencies on the deprecated API before it is fully retired. For consumers that have already prepared for the deprecation, a brownout provides valuable testing that the final removal of the service won't cause any unexpected problems.