公开(公告)号：US20240427998A1

公开(公告)日：2024-12-26

申请号：US18339694

申请日：2023-06-22

Applicant: Adobe Inc.

Inventor： Haoliang Wang ,  Tong Yu ,  Sungchul Kim ,  Ruiyi Zhang ,  Paiheng Xu ,  Junda Wu ,  Handong Zhao ,  Ani Nenkova

IPC: G06F40/30 ,  G06N5/04

Abstract: Contextual query generation techniques are described that enable generation of a contextual query for output to a question-answering (QA) model. A content processing system, for instance, configures a language model using in-context learning to generate queries based on semantic contexts of input documents, e.g., based on one or more linguistic cues from text of the input documents. The content processing system receives an input that includes a document having text and a reference query. The content processing system leverages the language model to generate a contextual query based on a semantic context of the text of the document and the reference query. The content processing system then outputs the contextual query and the document to a QA model. Using the QA model, the content processing system generates a response as an answer to the contextual query based on the contextual query and the document.

公开(公告)号：US20240169410A1

公开(公告)日：2024-05-23

申请号：US17980790

申请日：2022-11-04

Applicant: Adobe Inc.

Inventor： Handong Zhao ,  Zhankui He ,  Tong Yu ,  Fan Du ,  Sungchul Kim

IPC: G06Q30/06

CPC classification number: G06Q30/0631

Abstract: Techniques for predicting and recommending item bundles in a multi-round conversation to discover a target item bundle that would be accepted by a client. An example method includes receiving an input response in reply to a first item bundle that includes one or more items. A state model is updated to reflect the input response to the first item bundle. A machine-learning (ML) conversation module is applied to the state model to determine an action type as a follow-up to the input response to the first item bundle. Based on selection of a recommendation action as the action type, an ML bundling module is applied to the state model to generate a second item bundle different than the first item bundle. The second item bundle is then recommended.

公开(公告)号：US20250013866A1

公开(公告)日：2025-01-09

申请号：US18347877

申请日：2023-07-06

Applicant: ADOBE INC.

Inventor： Handong Zhao ,  Yue Bai ,  Zhe Lin ,  Ajinkya Gorakhnath Kale ,  Jiuxiang Gu ,  Tong Yu ,  Sungchul Kim

IPC: G06N3/082 ,  G06N3/04

Abstract: Systems and methods for reducing inference time of vision-language models, as well as for multimodal search, are described herein. Embodiments are configured to obtain an embedding neural network. The embedding neural network is pretrained to embed inputs from a plurality of modalities into a multimodal embedding space. Embodiments are further configured to perform a first progressive pruning stage, where the first progressive pruning stage includes a first pruning of the embedding neural network and a first fine-tuning of the embedding neural network. Embodiments then perform a second progressive pruning stage based on an output of the first progressive pruning stage, where the second progressive pruning stage includes a second pruning of the embedding neural network and a second fine-tuning of the embedding neural network.

公开(公告)号：US20240311221A1

公开(公告)日：2024-09-19

申请号：US18120773

申请日：2023-03-13

Applicant: Adobe Inc.

Inventor： Jaeho Bang ,  Sungchul Kim ,  Ryan A. Rossi ,  Tong Yu ,  Handong Zhao

IPC: G06F11/07 ,  G06N20/00

CPC classification number: G06F11/0769 ,  G06F11/0778 ,  G06N20/00

Abstract: In implementations of systems for detection and interpretation of log anomalies, a computing device implements an anomaly system to receive input data describing a two-dimensional representation of log templates and timestamps. The anomaly system processes the input data using a machine learning model trained on training data to detect anomalies in two-dimensional representations of log templates and timestamps. A log anomaly is detected in the two-dimensional representation using the machine learning model based on processing the input data. The anomaly system generates an indication of an interpretation of the log anomaly for display in a user interface based on a log template included in the two-dimensional representation.

公开(公告)号：US20230230198A1

公开(公告)日：2023-07-20

申请号：US17576091

申请日：2022-01-14

Applicant: Adobe Inc.

Inventor： Ruiyi Zhang ,  Yufan Zhou ,  Christopher Tensmeyer ,  Jiuxiang Gu ,  Tong Yu ,  Tong Sun

IPC: G06T3/00 ,  G06T11/00 ,  G10L15/22 ,  G10L15/26 ,  G06N3/04

CPC classification number: G06T3/0056 ,  G06T11/00 ,  G10L15/22 ,  G10L15/26 ,  G06N3/04 ,  G10L2015/223

Abstract: The present disclosure relates to systems, non-transitory computer-readable media, and methods that implement a neural network framework for interactive multi-round image generation from natural language inputs. Specifically, the disclosed systems provide an intelligent framework (i.e., a text-based interactive image generation model) that facilitates a multi-round image generation and editing workflow that comports with arbitrary input text and synchronous interaction. In particular embodiments, the disclosed systems utilize natural language feedback for conditioning a generative neural network that performs text-to-image generation and text-guided image modification. For example, the disclosed systems utilize a trained model to inject textual features from natural language feedback into a unified joint embedding space for generating text-informed style vectors. In turn, the disclosed systems can generate an image with semantically meaningful features that map to the natural language feedback. Moreover, the disclosed systems can persist these semantically meaningful features throughout a refinement process and across generated images.

公开(公告)号：US20250028751A1

公开(公告)日：2025-01-23

申请号：US18355901

申请日：2023-07-20

Applicant: Adobe Inc.

Inventor： Tong Yu ,  Kaige Xie ,  Haoliang Wang ,  Junda Wu ,  Handong Zhao ,  Ruiyi Zhang ,  Kanak Vivek Mahadik ,  Ani Nenkova

IPC: G06F16/34 ,  G06F40/35

Abstract: Dialogue skeleton assisted prompt transfer for dialogue summarization techniques are described that support training of a language model to perform dialogue summarization in a few-shot scenario. A processing device, for instance, receives a training dataset that includes training dialogues. The processing device then generates dialogue skeletons based on the training dialogues using one or more perturbation-based probes. The processing device trains a language model using prompt transfer between a source task, e.g., dialogue state tracking, and a target task, e.g., dialogue summarization, using the dialogue skeletons as supervision. The processing device then receives an input dialogue and uses the trained language model to generate a summary of the input dialogue.

公开(公告)号：US12079217B2

公开(公告)日：2024-09-03

申请号：US17741811

申请日：2022-05-11

Applicant: Adobe Inc.

Inventor： Subrata Mitra ,  Yash Gadhia ,  Tong Yu ,  Shaddy Garg ,  Nikhil Sheoran ,  Arjun Kashettiwar ,  Anjali Yadav

IPC: G06F16/2455 ,  G06F16/2453 ,  G06F16/2457 ,  G06F16/2458 ,  G06F18/21

CPC classification number: G06F16/2455 ,  G06F16/24542 ,  G06F16/2457 ,  G06F16/2474 ,  G06F18/217

Abstract: Some techniques described herein relate to utilizing a machine-learning (ML) model to select respective samples for queries of a query sequence. In one example, a method includes receiving a query in a query sequence, where the query is directed toward a dataset. Samples are available as down-sampled versions of the dataset. The method further include applying an agent to select, for the query, a sample from among the samples of the dataset. The agent includes an ML model trained, such as via intent-based reinforcement learning, to select respective samples for queries. The query is then executed against the sample to output a response.

公开(公告)号：US20240152771A1

公开(公告)日：2024-05-09

申请号：US17979843

申请日：2022-11-03

Applicant: Adobe Inc.

Inventor： Can Qin ,  Sungchul Kim ,  Tong Yu ,  Ryan A. Rossi ,  Handong Zhao

IPC: G06N5/02

CPC classification number: G06N5/02

Abstract: Tabular data machine-learning model techniques and systems are described. In one example, common-sense knowledge is infused into training data through use of a knowledge graph to provide external knowledge to supplement a tabular data corpus. In another example, a dual-path architecture is employed to configure an adapter module. In an implementation, the adapter module is added as part of a pre-trained machine-learning model for general purpose tabular models. Specifically, dual-path adapters are trained using the knowledge graphs and semantically augmented trained data. A path-wise attention layer is applied to fuse a cross-modality representation of the two paths for a final result.

公开(公告)号：US20230143721A1

公开(公告)日：2023-05-11

申请号：US17524282

申请日：2021-11-11

Applicant: ADOBE INC.

Inventor： Sungchul Kim ,  Subrata Mitra ,  Ruiyi Zhang ,  Rui Wang ,  Handong Zhao ,  Tong Yu

IPC: G06F40/295 ,  G06N20/00

CPC classification number: G06F40/295 ,  G06N20/00

Abstract: Embodiments of the technology described herein describe a machine classifier capable of continually learning new classes through a continual few-shot learning approach. A natural language processing (NLP) machine classifier may initially be trained to identify a plurality of other classes through a conventional training process. In order to learn a new class, natural-language training data for a new class is generated. The training data for the new class may be few-shot training data. The training also uses synthetic training data that represents each of the plurality of other classes. The synthetic training data may be generated through a model inversion of the original classifier. The synthetic training data and the natural-language training data are used to retrain the NLP classifier to identify text in the plurality of other classes and the new class using.

公开(公告)号：US20230030341A1

公开(公告)日：2023-02-02

申请号：US17383114

申请日：2021-07-22

Applicant: Adobe Inc.

Inventor： Eunyee Koh ,  Tak Yeon Lee ,  Andrew Thomson ,  Vasanthi Holtcamp ,  Ryan Rossi ,  Fan Du ,  Caroline Kim ,  Tong Yu ,  Shunan Guo ,  Nedim Lipka ,  Shriram Venkatesh Shet Revankar ,  Nikhil Belsare

IPC: G06N3/08 ,  H04L12/26 ,  G06F40/186 ,  G06N3/04

Abstract: The present disclosure relates to systems, non-transitory computer-readable media, and methods that utilize a dynamic user interface and machine learning tools to generate data-driven digital content and multivariate testing recommendations for distributing digital content across computer networks. In particular, in one or more embodiments, the disclosed systems utilize machine learning models to generate digital recommendations at multiple development stages of digital communications that are targeted on particular performance metrics. For example, the disclosed systems utilize historical information and recipient profile data to generate recommendations for digital communication templates, fragment variants of content fragments, and content variants of digital content items. Ultimately, the disclosed systems generate multivariate testing recommendations incorporating selected fragment variants to intelligently narrow multivariate testing candidates and generate more meaningful and statistically significant multivariate testing results.