Accenture Global Solutions Limited

Asml Us, Inc.

Yuan He

Anwitha Paruchuri

Sukryool Kang

Lan Guan

Anupam Anurag Tripathi

Sujeong Cha

Surya Raghavendra Vadlamani

Andrew Francis Hickl

Jie Lin

Guanglei Xiong

Jayashree Subrahmonia

Jiangwei Li

Neeraj D Vadhan

Ke Zhao

Jihui Huang

Louise Noreen Barrere

Thomas Wayne Hancock

Jill Gengelbach-wylie

Peter Royer Smith, Jr

Ivan Wong

The present disclosure relates to systems, methods, and products for using machine-learning networks to generate trustworthy audio and face mesh. A system, serving as a digital avatar, generates a trust audio and trust face mesh corresponding to an input text. A method includes generating a set of trust embedding vectors based on a reference audio; generate a text embedding vector based on the input text; generate a conditioned vector based on the set of trust embedding vectors and the text embedding vector; synthesize an audio representation based on the conditioned vector; generate the trust audio based on the synthesized audio representation; obtain a speech feature representation based on the trust audio; obtain an abstract feature vector based on the speech feature representation; and generate positions of vertices based on the abstract feature vector, the positions of vertices being used for generating the trust face mesh.

Systems and methods to automate trust delivery

Methods, systems, and apparatus are provided for generating an image. A personalized text prompt is generated by processing an input embedding using a transformer model followed by a first fully connected neural network. The input embedding comprises a multi-dimensional embedding vector associated with a user profile and a plurality of user items. A scored label set is generated identifying a user's preferences by processing a set of attributes for the plurality of user items using a second fully connected neural network. The image is generated by processing the personalized text prompt and the scored label set using a diffusion model.

Hyper-personalized prompt based content generation

A system and method for lead conversion using conversational virtual avatar is disclosed. System comprising processor causes Conversation Virtual Avatar Platform (CVAP) to receive, for first entity, from lead prioritization engine, leads applicable to first entity via lead repository based on scores associated with respective leads. Processor causes CVAP to receive, through conversation management engine (CME) configured in CVAP, from leads, responses to questions pertaining to product attributes and information pertaining to lead. The processor causes CVAP to process responses to determine action and/or state, which includes whether to issue additional product-attribute based questions through Virtual Avatar (VA) using Response To Motion Module (RTME) or to, through recommender engine that uses recommendation model, in real-time, recommend products associated with first entity to respective at least one lead based on any or combination of responses received from lead, information pertaining to lead, and products ordered by entities similar to lead.

System, method, and medium for lead conversion using a conversational virtual avatar

Methods, apparatuses, and systems for determining a binary mask pattern from a pixelated mask pattern include: determining, by a processor, based on a fast marching method (FMM), arrival values for pixels of a portion of the pixelated mask pattern; determining the binary mask pattern based on the arrival values; and updating at least one of the arrival values based on a comparison between a design pattern corresponding to the pixelated mask pattern and a substrate pattern simulated based on the binary mask pattern.

Mask pattern generation based on fast marching method

A method for optimizing a binary mask pattern includes determining, by a processor, an evaluation value based on a comparison between a design pattern and a substrate pattern simulated based on the binary mask pattern. The method also includes, based on the evaluation value, using, by the processor, a gradient-based optimization method to generate a first adjusted binary mask pattern. The method also includes determining, by the processor, a first updated evaluation value based on a comparison between the design pattern and a first updated substrate pattern simulated based on the first adjusted binary mask pattern. The method also includes, based on the first updated evaluation value, using, by the processor, a product of a Hessian matrix and an arbitrary vector to generate a second adjusted binary mask pattern. The method also includes simulating, by the processor, a second updated substrate pattern based on the second adjusted binary mask pattern.

Hessian-free calculation of product of Hessian matrix and vector for lithography optimization

Growing community of inventors

San Jose, CA, United States of America

Yuan He