-
公开(公告)号：US11755948B2
公开(公告)日：2023-09-12
申请号：US16719244
申请日：2019-12-18
Applicant: Google LLC
Inventor： Andrei Kapishnikov , Tolga Bolukbasi , Fernanda Bertini Viégas , Michael Andrew Terry
Abstract: Methods, systems, devices, and tangible non-transitory computer readable media for saliency visualization are provided. The disclosed technology can include receiving a data input including a plurality of features. The data input can be segmented into regions. At least one of the regions can include two or more of the features. Attribution scores can be respectively generated for features of the data input. The attribution scores for each feature can be indicative of a respective saliency of such feature. A respective gain value for each region can be determined over one or more iterations based on the respective attribution scores associated with the features included in the region. Further, at each iteration one or more of the regions with the greatest gain values can be added to a saliency mask. Furthermore, at each iteration a saliency visualization can be produced based on the saliency mask.
-
2.发明申请公开(公告)号：US20230112921A1
公开(公告)日：2023-04-13
申请号：US17957526
申请日：2022-09-30
Applicant: Google LLC
Inventor： Carrie Cai , Tongshuang Wu , Michael Andrew Terry
Abstract: The present disclosure provides to transparent and controllable human-AI interaction via chaining of machine-learned language models. In particular, although existing language models (e.g., so-called “large language models” (LLMs)) have demonstrated impressive potential on simple tasks, their breadth of scope, lack of transparency, and insufficient controllability can make them less effective when assisting humans on more complex tasks. In response, the present disclosure introduces the concept of chaining instantiations of machine-learned language models (e.g., LLMs) together, where the output of one instantiation becomes the input for the next, and so on, thus aggregating the gains per step.
-
3.发明申请公开(公告)号：US20250036376A1
公开(公告)日：2025-01-30
申请号：US18915020
申请日：2024-10-14
Applicant: Google LLC
Inventor： Carrie Cai , Tongshuang Wu , Michael Andrew Terry
Abstract: The present disclosure provides to transparent and controllable human-AI interaction via chaining of machine-learned language models. In particular, although existing language models (e.g., so-called “large language models” (LLMs)) have demonstrated impressive potential on simple tasks, their breadth of scope, lack of transparency, and insufficient controllability can make them less effective when assisting humans on more complex tasks. In response, the present disclosure introduces the concept of chaining instantiations of machine-learned language models (e.g., LLMs) together, where the output of one instantiation becomes the input for the next, and so on, thus aggregating the gains per step.
-
Patent Agency Ranking
4.发明授权公开(公告)号：US12141556B2
公开(公告)日：2024-11-12
申请号：US17957526
申请日：2022-09-30
Applicant: Google LLC
Inventor： Carrie Cai , Tongshuang Wu , Michael Andrew Terry
Abstract: The present disclosure provides to transparent and controllable human-AI interaction via chaining of machine-learned language models. In particular, although existing language models (e.g., so-called “large language models” (LLMs)) have demonstrated impressive potential on simple tasks, their breadth of scope, lack of transparency, and insufficient controllability can make them less effective when assisting humans on more complex tasks. In response, the present disclosure introduces the concept of chaining instantiations of machine-learned language models (e.g., LLMs) together, where the output of one instantiation becomes the input for the next, and so on, thus aggregating the gains per step.
-
公开(公告)号：US12236326B2
公开(公告)日：2025-02-25
申请号：US18363277
申请日：2023-08-01
Applicant: Google LLC
Inventor： Andrei Kapishnikov , Fernanda Bertini Viégas , Michael Andrew Terry , Tolga Bolukbasi
Abstract: Methods, systems, devices, and tangible non-transitory computer readable media for saliency visualization are provided. The disclosed technology can include receiving a data input including a plurality of features. The data input can be segmented into regions. At least one of the regions can include two or more of the features. Attribution scores can be respectively generated for features of the data input. The attribution scores for each feature can be indicative of a respective saliency of such feature. A respective gain value for each region can be determined over one or more iterations based on the respective attribution scores associated with the features included in the region. Further, at each iteration one or more of the regions with the greatest gain values can be added to a saliency mask. Furthermore, at each iteration a saliency visualization can be produced based on the saliency mask.
-
公开(公告)号：US20240311652A1
公开(公告)日：2024-09-19
申请号：US18183429
申请日：2023-03-14
Applicant: Google LLC
Inventor： Chinmay Kulkarni , Alexander John Fiannaca , Michael Andrew Terry
IPC: G06N3/10 , G06N3/0475 , G06N3/08
CPC classification number: G06N3/10 , G06N3/0475 , G06N3/08
Abstract: Systems and methods for prompt generation for generative models can include utilizing a specialized markup language. A markup language transform can be utilized to augment user input data to generate a prompt that includes structure and/or wording that facilitates the generation of a generative output that reflects a user's intent. The systems and methods can leverage the specialized markup language and/or an integrated development environment interface to inform a user of the prompt parts and provide editing options.
-
公开(公告)号：US20240054402A1
公开(公告)日：2024-02-15
申请号：US18363277
申请日：2023-08-01
Applicant: Google LLC
Inventor： Andrei Kapishnikov , Fernanda Bertini Viégas , Michael Andrew Terry , Tolga Bolukbasi
Abstract: Methods, systems, devices, and tangible non-transitory computer readable media for saliency visualization are provided. The disclosed technology can include receiving a data input including a plurality of features. The data input can be segmented into regions. At least one of the regions can include two or more of the features. Attribution scores can be respectively generated for features of the data input. The attribution scores for each feature can be indicative of a respective saliency of such feature. A respective gain value for each region can be determined over one or more iterations based on the respective attribution scores associated with the features included in the region. Further, at each iteration one or more of the regions with the greatest gain values can be added to a saliency mask. Furthermore, at each iteration a saliency visualization can be produced based on the saliency mask.
-
公开(公告)号：US20210192382A1
公开(公告)日：2021-06-24
申请号：US16719244
申请日：2019-12-18
Applicant: Google LLC
Inventor： Andrei Kapishnikov , Tolga Bolukbasi , Fernanda Bertini Viégas , Michael Andrew Terry
Abstract: Methods, systems, devices, and tangible non-transitory computer readable media for saliency visualization are provided. The disclosed technology can include receiving a data input including a plurality of features. The data input can be segmented into regions. At least one of the regions can include two or more of the features. Attribution scores can be respectively generated for features of the data input. The attribution scores for each feature can be indicative of a respective saliency of such feature. A respective gain value for each region can be determined over one or more iterations based on the respective attribution scores associated with the features included in the region. Further, at each iteration one or more of the regions with the greatest gain values can be added to a saliency mask. Furthermore, at each iteration a saliency visualization can be produced based on the saliency mask.
-
-
-
-
-
-
-
Search Results
8
records
(took 0.016 seconds)
