-
公开(公告)号：US11861263B1
公开(公告)日：2024-01-02
申请号：US17846351
申请日：2022-06-22
Applicant: X Development LLC
Inventor： Thomas Hunt , David Andre , Nisarg Vyas , Rebecca Radkoff , Rishabh Singh
IPC: G06F3/0481 , G06F3/16 , G06F3/0484 , G10L15/22
CPC classification number: G06F3/167 , G06F3/0481 , G06F3/0484 , G10L15/22
Abstract: This specification is generally directed to techniques for robust natural language (NL) based control of computer applications. In many implementations, the NL control is at least selectively interactive in that the user feedback input is solicited, and received, in resolving action(s), resolving action set(s), generating domain specific knowledge, and/or in providing feedback on implemented action set(s). The user feedback input can be utilized in further training of machine learning model(s) utilized in the NL based control of the computer applications.
-
公开(公告)号：US20230004366A1
公开(公告)日：2023-01-05
申请号：US17901128
申请日：2022-09-01
Applicant: X Development LLC
Inventor： Qianyu Zhang , Bin Ni , Rishabh Singh , Olivia Hatalsky
Abstract: Implementations are described herein for adapting existing source code snippets to new contexts. In various implementations, a command may be detected to incorporate an existing source code snippet into destination source code. An embedding may be generated based on the existing source code snippet, e.g., by processing the existing source code snippet using an encoder. The destination source code may be processed to identify one or more decoder constraints. Subject to the one or more decoder constraints, the embedding may be processed using a decoder to generate a new version of the existing source code snippet that is adapted to the destination source code.
-
公开(公告)号：US11487522B1
公开(公告)日：2022-11-01
申请号：US17318687
申请日：2021-05-12
Applicant: X Development LLC
Inventor： Rishabh Singh , Nisarg Vyas , Jayendra Parmar , Dhara Kotecha , Artem Goncharuk , David Andre
Abstract: Training and/or utilization of a neural decompiler that can be used to generate, from a lower-level compiled representation, a target source code snippet in a target programming language. In some implementations, the lower-level compiled representation is generated by compiling a base source code snippet that is in a base programming language, thereby enabling translation of the base programming language (e.g., C++) to a target programming language (e.g., Python). In some of those implementations, output(s) from the neural decompiler indicate canonical representation(s) of variables. Technique(s) can be used to match those canonical representation(s) to variable(s) of the base source code snippet. In some implementations, multiple candidate target source code snippets are generated using the neural decompiler, and a subset (e.g., one) is selected based on evaluation(s).
-
公开(公告)号：US11481210B2
公开(公告)日：2022-10-25
申请号：US17136968
申请日：2020-12-29
Applicant: X Development LLC
Inventor： Rishabh Singh , David Andre , Bin Ni , Owen Lewis
Abstract: Implementations are described herein for using machine learning to perform various tasks related to migrating source code based on relatively few (“few shots”) demonstrations. In various implementations, an autoregressive language model may be conditioned based on demonstration tuple(s). In some implementations, a demonstration tuple may include a pre-migration version of a first source code snippet and a post-migration version of the first source code snippet. In other implementations, demonstration tuples may include other data, such as intermediate forms (e.g., natural language descriptions or pseudocode), input-output pairs demonstrating intended behavior, etc. The autoregressive language model may be trained on corpora of source code and natural language documentation on the subject of computer programming. A pre-migration version of a source code file may be processed based on the conditioned autoregressive language model, and a post-migration version may be generated based on output generated based on the conditioned autoregressive model.
-
公开(公告)号：US20220206785A1
公开(公告)日：2022-06-30
申请号：US17136968
申请日：2020-12-29
Applicant: X Development LLC
Inventor： Rishabh Singh , David Andre , Bin Ni , Owen Lewis
Abstract: Implementations are described herein for using machine learning to perform various tasks related to migrating source code based on relatively few (“few shots”) demonstrations. In various implementations, an autoregressive language model may be conditioned based on demonstration tuple(s). In some implementations, a demonstration tuple may include a pre-migration version of a first source code snippet and a post-migration version of the first source code snippet. In other implementations, demonstration tuples may include other data, such as intermediate forms (e.g., natural language descriptions or pseudocode), input-output pairs demonstrating intended behavior, etc. The autoregressive language model may be trained on corpora of source code and natural language documentation on the subject of computer programming. A pre-migration version of a source code file may be processed based on the conditioned autoregressive language model, and a post-migration version may be generated based on output generated based on the conditioned autoregressive model.
-
Patent Agency Ranking
公开(公告)号：US20220236971A1
公开(公告)日：2022-07-28
申请号：US17159524
申请日：2021-01-27
Applicant: X Development LLC
Inventor： Qianyu Zhang , Bin Ni , Rishabh Singh , Olivia Hatalsky
Abstract: Implementations are described herein for adapting existing source code snippets to new contexts. In various implementations, a command may be detected to incorporate an existing source code snippet into destination source code. An embedding may be generated based on the existing source code snippet, e.g., by processing the existing source code snippet using an encoder. The destination source code may be processed to identify one or more decoder constraints. Subject to the one or more decoder constraints, the embedding may be processed using a decoder to generate a new version of the existing source code snippet that is adapted to the destination source code.
-
公开(公告)号：US20250028995A1
公开(公告)日：2025-01-23
申请号：US18224889
申请日：2023-07-21
Applicant: X Development LLC
Inventor： Rishabh Singh , David Andre , Garrett Raymond Honke , Falak Shah , Nisarg Vyas , Jayendra Parmar , Brian M. Rosen , Shaili Trivedi
IPC: G06N20/00
Abstract: Disclosed implementations relate to adding “bottleneck” models to machine learning pipelines that already apply domain models to translate and/or transfer representations of high-level semantic concepts between domains. In various implementations, an initial representation in a first domain of a transition from an initial state of an environment to a goal state of the environment may be processed based on a pre-trained first domain encoder to generate a first embedding that semantically represents the transition. The first embedding may be processed based on one or more bottleneck models to generate a second embedding with fewer dimensions than the first embedding. In various implementations, the second embedding may be processed in various ways to train one or more of the bottleneck model(s) based on various different auxiliary loss functions.
-
公开(公告)号：US20230018088A1
公开(公告)日：2023-01-19
申请号：US17945376
申请日：2022-09-15
Applicant: X Development LLC
Inventor： Rishabh Singh , David Andre , Bin Ni , Owen Lewis
Abstract: Implementations are described herein for using machine learning to perform various tasks related to migrating source code based on relatively few (“few shots”) demonstrations. In various implementations, an autoregressive language model may be conditioned based on demonstration tuple(s). In some implementations, a demonstration tuple may include a pre-migration version of a first source code snippet and a post-migration version of the first source code snippet. In other implementations, demonstration tuples may include other data, such as intermediate forms (e.g., natural language descriptions or pseudocode), input-output pairs demonstrating intended behavior, etc. The autoregressive language model may be trained on corpora of source code and natural language documentation on the subject of computer programming. A pre-migration version of a source code file may be processed based on the conditioned autoregressive language model, and a post-migration version may be generated based on output generated based on the conditioned autoregressive model.
-
公开(公告)号：US11461081B2
公开(公告)日：2022-10-04
申请号：US17159524
申请日：2021-01-27
Applicant: X Development LLC
Inventor： Qianyu Zhang , Bin Ni , Rishabh Singh , Olivia Hatalsky
IPC: G06F9/44 , G06F8/41 , G06F8/34 , G06F8/36 , G06F8/71 , G06F16/00 , G06F16/242 , G06N3/08 , G06N3/04
Abstract: Implementations are described herein for adapting existing source code snippets to new contexts. In various implementations, a command may be detected to incorporate an existing source code snippet into destination source code. An embedding may be generated based on the existing source code snippet, e.g., by processing the existing source code snippet using an encoder. The destination source code may be processed to identify one or more decoder constraints. Subject to the one or more decoder constraints, the embedding may be processed using a decoder to generate a new version of the existing source code snippet that is adapted to the destination source code.
-
10.发明公开公开(公告)号：US20230359789A1
公开(公告)日：2023-11-09
申请号：US18142472
申请日：2023-05-02
Applicant: X Development LLC
Inventor： David Andre , Rishabh Singh , Rebecca Radkoff , Yu-Ann Madan , Nisarg Vyas , Jayendra Parmar , Falak Shah , Shaili Trivedi
IPC: G06F30/27 , G10L15/183
CPC classification number: G06F30/27 , G10L15/183
Abstract: As opposed to a rigid approach, implementations disclosed herein utilize a flexible approach in automatically determining an action set to utilize in attempting performance of a task that is requested by natural language input of a user. The approach is flexible at least in that embedding technique(s) and/or action model(s), that are utilized in generating action set(s) from which the action set to utilize is determined, are at least selectively varied. Put another way, implementations leverage a framework via which different embedding technique(s) and/or different action model(s) can at least selectively be utilized in generating different candidate action sets for given NL input of a user. Further, one of those action sets can be selected for actual use in attempting real-world performance of a given task reflected by the given NL input. The selection can be based on a suitability metric for the selected action set and/or other considerations.
-
-
-
-
-
-
-
-
-
Search Results
10
records
(took 0.017 seconds)
