Microsoft Technology Licensing, LLC

Shawn Cantin Callegari

Devis Lucato

Adrian Bonar

Nicholas Becker

Chad Michael Roberts

Ashish Gupta

Umesh Madan

Joseph Alton Schrader

Susan Chory

Rowan Forster

Jared Frew

Alice Jane Brush

Michael John Bray

Melissa Nicole Lim

Samuel Edward Schillace

Ryan H Volum

Brian Scott Krabach

Terri L Chudzik

David Warren Stevens

Tara Eve Walker

Mark Karle

Nicole E Berdy

Gina Elizabeth Triolo

Mollie Munoz

Abby Harrison

Alexander Chao

Jennifer Fox

LeRoy F Miller

Audrey Yung Chin Sousa

Renle Xia

Tyler N Jensen

Richard Lawrence Harrington

Brad Steven Kertson

Audrey Yung Sousa

Chad Roberts

Methods and systems for generating completely automated public Turing test (CAPTCHA) images are provided. In some examples, a method includes generating a plurality of images using a generative imaging model, providing the plurality of images to a user with a description that corresponds to one of a similarity or difference between the plurality of images, receiving a selection of an image of the plurality of images, determining if the selection is correct based on the provided description, and outputting an indication of whether the selection is correct.

Generating captchas using generative imaging models

The techniques disclosed herein enable systems for spoken natural stylistic conversations with large language models. In contrast to many existing modalities for interacting with large language models that are limited to text, the techniques presented herein enable users to carry a fully spoken conversation with a large language model. This is accomplished by converting a user speech audio input to text and utilizing a prompt engine to analyze a sentiment expressed by the user. A large language model, having been trained on example conversations, by generating a text response as well as a style cue to express emotion in response to the sentiment expressed by speech audio input. A text-to-speech engine can subsequently interpret the text response and style cue to generate an audio output which emulates the sensation of human conversation.

Real-time system for spoken natural stylistic conversations with large language models

In accordance with examples of the present disclosure, a collaborative platform provides a digital collaboration assistant that continuously monitors and analyzes shared meeting contents (e.g., voice, text chat messages, shared links and documents, presentation materials, and the like) by participants during a collaborative meeting in near real-time, periodically updates a structure summary log of the meeting contents that are deemed important during the collaborative meeting, and interacts with the participants throughout the collaborative meeting in near real-time, for example, to answer questions or provide additional information.

Meeting insights with large language models

A virtual skeleton may be adapted based on a capability profile. The virtual skeleton adapted based on a capability profile may be generated from a master virtual skeleton. The adapted virtual skeleton may be less complex than the master virtual skeleton. The adapted virtual skeleton may include fewer virtual skeletal joints than a number of virtual skeletal joints associated with the master virtual skeleton.

Virtual skeleton based on computing device capability profile

Embodiments of the disclosure aggregate and present event information relating to a calendar event associated with an application executing on a computing device. In some embodiments, data relating to the calendar event is obtained from a content source that is outside an execution context of the application. The data relating to the calendar event is obtained and/or presented intermittently in a user interface element associated with the application. The content source that is outside the execution context of the application may be within an execution context of one or more other applications, an operating system of the computing device, and/or a web service.

Aggregating and presenting event information

The present application relates to message account linking that allows users to selectively link message accounts and customize those linked message accounts. In one embodiment, the user selects a number of message accounts for selective linking. A message application updates a message account database to selectively link the message accounts and create a combined message box. When a user selects the combined message box for display, all messages from the selectively linked message accounts are displayed. In one embodiment, a user can create multiple combined message boxes on a single device, and may assign names to each of the combined message boxes. In yet another embodiment, an icon associated with a combined message box is added to the device's home screen.

Selective linking of message accounts

Growing community of inventors

Redmond, WA, United States of America

Shawn Cantin Callegari