公开(公告)号：US20240386712A1

公开(公告)日：2024-11-21

申请号：US18500986

申请日：2023-11-02

Applicant: QUALCOMM Incorporated

Inventor： Apratim BHATTACHARYYA ,  Roland MEMISEVIC ,  Sunny Praful Kumar PANCHAL ,  Reza POURREZA ,  Mingu LEE ,  Pulkit MADAN

IPC: G06V10/82 ,  G06F40/10 ,  G06F40/284

Abstract: A processor-implemented method for generating grounded rationales for visual reasoning tasks includes receiving, by a first artificial neural network (ANN), an interleaved sequence of images and textual information. The first ANN extracts grid features of the images of the interleaved sequence of the images and the textual information to generate a representation of the interleaved sequence of the images and the textual information based on the grid features. A second ANN maps the grid features to a textual domain. The second ANN extracts visual information of the interleaved sequence of the images and the textual information based on the grid features in the textual domain. The second ANN determines a rationale based on the visual information. The visual information comprises one or more lower-level surrogate tasks.

公开(公告)号：US20250021761A1

公开(公告)日：2025-01-16

申请号：US18545804

申请日：2023-12-19

Applicant: QUALCOMM Incorporated

Inventor： Arvind Vardarajan SANTHANAM ,  Joseph Binamira SORIAGA ,  Roland MEMISEVIC ,  Mingu LEE ,  Christopher LOTT

IPC: G06F40/284

Abstract: Techniques and apparatus for generating a response to a query input into a generative artificial intelligence model. An example method generally includes generating, based on an input query and a first generative artificial intelligence model, a sequence of tokens corresponding to a candidate response to the input query. The sequence of tokens and the input query are output to a second generative artificial intelligence model for verification. One or more first guidance signals for the generated sequence of tokens are received from the second generative artificial intelligence model. The candidate response to the input query is revised based on the generated sequence of tokens and the one or more first guidance signals, and the revised candidate response is output as a response to the received input query.

公开(公告)号：US20240354346A1

公开(公告)日：2024-10-24

申请号：US18538965

申请日：2023-12-13

Applicant: QUALCOMM Incorporated

Inventor： Christopher LOTT ,  Mingu LEE ,  Wonseok JEON ,  Roland MEMISEVIC

IPC: G06F16/901 ,  G06F40/284

CPC classification number: G06F16/9027 ,  G06F40/284

Abstract: Certain aspects of the present disclosure provide techniques and apparatus for generating a response to a query input in a generative artificial intelligence model. An example method generally includes receiving a plurality of sets of tokens generated based on an input prompt and a first generative artificial intelligence model, each set of tokens in the plurality of sets of tokens corresponding to a candidate response to the input prompt; selecting, using a second generative artificial intelligence model and recursive adjustment of a target distribution associated with the received plurality of sets of tokens, a set of tokens from the plurality of sets of tokens; and outputting the selected set of tokens as a response to the input prompt.

公开(公告)号：US20240126987A1

公开(公告)日：2024-04-18

申请号：US18477515

申请日：2023-09-28

Applicant: QUALCOMM Incorporated

Inventor： Roland MEMISEVIC ,  Mingu LEE ,  Sunny Praful Kumar PANCHAL

IPC: G06F40/20

CPC classification number: G06F40/20

Abstract: A processor-implemented method includes receiving an input comprising a previous language stream, and generating an output language stream by a pre-trained language model, based on the input. The method further includes detecting a well-formed action based on patterns in the output language stream, and performing an operation, by an environment, in response to detecting the well-formed action. The operation returns a result. The method also includes appending the result to the output language stream to obtain an updated output language stream. The method includes repeating the generating, with the updated output language stream as the input, the detecting, the performing, and the appending until a termination condition is satisfied.

公开(公告)号：US20250131020A1

公开(公告)日：2025-04-24

申请号：US18492480

申请日：2023-10-23

Applicant: QUALCOMM Incorporated

Inventor： Vikram GUPTA ,  Wesley James HOLLAND ,  Ziad ASGHAR ,  Vinesh SUKUMAR ,  Roland MEMISEVIC

IPC: G06F16/332 ,  G06F16/335

Abstract: Various embodiments include systems and methods for improving the user experience with LXMs. A computing device may be configured to receive a user prompt, observe user responses to an output received from a LXM in response to a prompt that is at least partially based on the user's prompt, and take an action to improve the user's experience with the LXM based on the observed user response.

公开(公告)号：US20250148015A1

公开(公告)日：2025-05-08

申请号：US19012626

申请日：2025-01-07

Applicant: QUALCOMM Incorporated

Inventor： Christopher LOTT ,  Mingu LEE ,  Wonseok JEON ,  Roland MEMISEVIC

IPC: G06F16/901 ,  G06F40/284

Abstract: Certain aspects of the present disclosure provide techniques and apparatus for generating a response to a query input in a generative artificial intelligence model. An example method generally includes receiving a plurality of sets of tokens generated based on an input prompt and a first generative artificial intelligence model, each set of tokens in the plurality of sets of tokens corresponding to a candidate response to the input prompt; selecting, using a second generative artificial intelligence model and recursive adjustment of a target distribution associated with the received plurality of sets of tokens, a set of tokens from the plurality of sets of tokens; and outputting the selected set of tokens as a response to the input prompt.

公开(公告)号：US20250131024A1

公开(公告)日：2025-04-24

申请号：US18492379

申请日：2023-10-23

Applicant: QUALCOMM Incorporated

Inventor： Vikram GUPTA ,  Ziad ASGHAR ,  Wesley James HOLLAND ,  Vinesh SUKUMAR ,  Khaled Helmi EL-MALEH ,  Roland MEMISEVIC

IPC: G06F16/33 ,  G06F11/34 ,  G06F16/335 ,  H04L67/50

Abstract: Various embodiments include systems and methods for generating a prompt for a generative artificial intelligence (AI) models. A processing system including at least one processor may be configured to recognize a user of the computing device, obtain user context information from a source of physical context information in the computing device, receive a user prompt for the large generative AI model (LXM), select a user profile from among a plurality of user profiles based on the user, the user context information and the user prompt, generate an enhanced prompt based on the user prompt and information included in the selected user profile, and submit the enhanced prompt to the LXM.

公开(公告)号：US20240394936A1

公开(公告)日：2024-11-28

申请号：US18466747

申请日：2023-09-13

Applicant: QUALCOMM Incorporated

Inventor： Reza POURREZA ,  Roland MEMISEVIC ,  Apratim BHATTACHARYYA ,  Sunny Praful Kumar PANCHAL ,  Mingu LEE ,  Pulkit MADAN

IPC: G06T11/20 ,  G06N3/0464 ,  G06N3/084 ,  G06T11/60

Abstract: A processor-implemented method for image generation using an artificial neural network (ANN) includes receiving an input including one or more of an image or a text prompt. The ANN processes the input to determine one or more virtual brush strokes to generate an output image or one or more commands for controlling an image drawing application to generate the output image. A list of the one or more virtual brush strokes to generate the output image or the one or more commands for controlling the image drawing application to generate the output image. The one or more virtual brush strokes or commands may be executed to generate a sketch based on the input.

公开(公告)号：US20240354345A1

公开(公告)日：2024-10-24

申请号：US18538912

申请日：2023-12-13

Applicant: QUALCOMM Incorporated

Inventor： Christopher LOTT ,  Mingu LEE ,  Wonseok JEON ,  Roland MEMISEVIC

IPC: G06F16/901 ,  G06F40/284

CPC classification number: G06F16/9027 ,  G06F40/284

Abstract: Certain aspects of the present disclosure provide techniques and apparatus for generating a response to a query input in a generative artificial intelligence model. An example method generally includes receiving a plurality of sets of tokens generated based on an input prompt and a first generative artificial intelligence model, each set of tokens in the plurality of sets of tokens corresponding to a candidate response to the input prompt; selecting, using a second generative artificial intelligence model and recursive adjustment of a target distribution associated with the received plurality of sets of tokens, a set of tokens from the plurality of sets of tokens; and outputting the selected set of tokens as a response to the input prompt.