Google Inc.

Microsoft Technology Licensing, LLC

Sanil Jain

Michael Andrew Goodman

Wei Yu

Ágoston Weisz

Thang Minh Luong

Golnaz Ghiasi

Yifeng Lu

Amin Ghafouri

Igor Petrovski

Evgeny Sluzhaev

Oscar Akerlund

Rakesh Shivanna

Vikas Peswani

Diana Avram

Komal Singh

Khyatti Gupta

Kartik Paramasivam

Samarth Shetty

Prateek Maheshwari

Yaguang Li

Yu Qing Du

Bharath Kumarasubramanian

Abhishek Shivanna

Apoorv Kulshreshtha

Dustin Tran

Rayman Preet Singh

Fan Xie

Pawas Chhokra

Implementations relate to managing multimedia content that is obtained by large language model(s) (LLM(s)) and/or generated by other generative model(s). Processor(s) of a system can: receive natural language (NL) based input that requests multimedia content, generate a response that is responsive to the NL based input, and cause the response to be rendered. In some implementations, and in generating the response, the processor(s) can process, using a LLM, LLM input to generate LLM output, and determine, based on the LLM output, at least multimedia content to be included in the response. Further, the processor(s) can evaluate the multimedia content to determine whether it should be included in the response. In response to determining that the multimedia content should not be included in the response, the processor(s) can cause the response, including alternative multimedia content or other textual content, to be rendered.

Multimedia content management for large language model(s) and/or other generative model(s)

Implementations relate to generating multi-modal response(s) through utilization of large language model(s) (LLM(s)). Processor(s) of a system can: receive natural language (NL) based input, generate a multi-modal response that is responsive to the NL based output, and cause the multi-modal response to be rendered. In some implementations, and in generating the multi-modal response, the processor(s) can process, using a LLM, LLM input (e.g., that includes at least the NL based input) to generate LLM output, and determine, based on the LLM output, textual content for inclusion in the multi-modal response and multimedia content for inclusion in the multi-modal response. In some implementations, the multimedia content can be obtained based on a multimedia content tag that is included in the LLM output and that is indicative of the multimedia content. In various implementations, the multimedia content can be interleaved between segments of the textual content.

Generating multi-modal response(s) through utilization of large language model(s)

Techniques are provided for automatically resizing applications. In one technique, policy data that indicates an order of multiple policies is stored. The policies include (1) a first policy that corresponds to a first computer resource and a first resizing action and (2) a second policy that is lower in priority than the first policy and that corresponds to a second resizing action and a second computer resource. Resource utilization data is received from at least one application executing in a cloud environment. Based on the order, the first policy is identified. Based on the resource utilization data, it is determined whether criteria associated with the first policy are satisfied with respect to the application. If satisfied, then the first resizing action is performed with respect to the application; otherwise, based on the computer resource utilization data, it is determined whether criteria associated with the second policy are satisfied.

Auto-sizing for stream processing applications

Growing community of inventors

Sunnyvale, CA, United States of America

Sanil Jain