Abstract: Systems, methods and non-transitory computer readable media for attributing aspects of generated visual contents to training examples are provided. A first visual content generated using a generative model may be received. The generative model may be a result of training a machine learning model using a plurality of training examples. Properties of an aspect of the first visual content and properties of visual contents associated with the plurality of training examples may be used to attribute the aspect of the first visual content to a subgroup of the plurality of training examples. For each source of the sources associated with the visual contents associated with the training examples of the subgroup, a data-record associated with the source may be updated based on the attribution of the aspect of the first visual content.

Abstract: Systems, methods and non-transitory computer readable media for attributing generated audio contents to training examples are provided. A first audio content generated using a generative model may be received. The generative model may be a result of training a machine learning model using training examples. Each training example may be associated with a respective audio content. Properties of the first audio content may be determined. For each training example of the training examples, the respective audio content may be analyzed to determine properties of the respective audio content. The properties of the first audio content and the properties of the audio contents associated with the training examples may be used to attribute the first audio content to a subgroup of the training examples. A respective data-record associated with a source associated with the training examples of the subgroup may be updated based on the attribution.

Abstract: Systems, methods and non-transitory computer readable media for attributing aspects of generated visual contents to training examples are provided. A first visual content generated using a generative model may be received. The generative model may be a result of training a machine learning model using a plurality of training examples. Properties of an aspect of the first visual content and properties of visual contents associated with the plurality of training examples may be used to attribute the aspect of the first visual content to a subgroup of the plurality of training examples. For each source of the sources associated with the visual contents associated with the training examples of the subgroup, a data-record associated with the source may be updated based on the attribution of the aspect of the first visual content.

Abstract: Systems, methods and non-transitory computer readable media for inference based on different portions of a training set using a single inference model are provided. Textual inputs may be received, each of which may include a source-identifying-keyword. An inference model may be a result of training a machine learning model using a plurality of training examples. Each training example may include a respective textual content and a respective media content. The training examples may be grouped based on source-identifying-keywords included in the textual contents. Different parameters of the inference model may be based on different groups, and thereby be associated with different source-identifying-keywords. When generating new media content using the inference model and a textual input, parameters associated with the source-identifying-keyword included in the textual input may be used.

Abstract: Systems, methods and non-transitory computer readable media for providing diverse visual contents based on prompts are provided. A textual input in a natural language indicative of a desire of an individual to receive at least one visual content of an inanimate object of a particular category may be received. Further, a demographic requirement may be obtained. For example, the textual input may be analyzed to determine a demographic requirement. Further, a visual content may be obtained based on the demographic requirement and the textual input. The visual content may include a depiction of at least one inanimate object of the particular category and a depiction of one or more persons matching the demographic requirement. Further, a presentation of the visual content to the individual may be caused.

Abstract: Systems, methods and non-transitory computer readable media for prompt based background replacement are provided. A visual content including a background portion and at least one foreground object may be accessed. Further, a textual input indicative of a desire of an individual to modify the visual content may be received. The textual input and the visual content may be analyzed to generate a modified version of the visual content. The modified version may differ from the visual content in the background portion. Further, the modified version may include a depiction of the at least one foreground object substantially identical to a depiction of the at least one foreground object in the visual content. Further, a presentation of the modified version of the visual content to the individual may be caused.

Abstract: Systems, methods and non-transitory computer readable media for identifying prompts used for training of inference models are provided. In some examples, a specific textual prompt in a natural language may be received. Further, data based on at least one parameter of an inference model may be accessed. The inference model may be a result of training a machine learning model using a plurality of training examples. Each training example of the plurality of training examples may include a respective textual content and a respective media content. The data and the specific textual prompt may be analyzed to determine a likelihood that the specific textual prompt is included in at least one training example of the plurality of training examples. A digital signal indicative of the likelihood that the specific textual prompt is included in at least one training example of the plurality of training examples may be generated.

Abstract: Systems, methods and non-transitory computer readable media for attributing aspects of generated visual contents to training examples are provided. A first visual content generated using a generative model may be received. The generative model may be a result of training a machine learning model using a plurality of training examples. Properties of an aspect of the first visual content and properties of visual contents associated with the plurality of training examples may be used to attribute the aspect of the first visual content to a subgroup of the plurality of training examples. For each source of the sources associated with the visual contents associated with the training examples of the subgroup, a data-record associated with the source may be updated based on the attribution of the aspect of the first visual content.

Abstract: Systems, methods and non-transitory computer readable media for attributing generated audio contents to training examples are provided. A first audio content generated using a generative model may be received. The generative model may be a result of training a machine learning model using training examples. Each training example may be associated with a respective audio content. Properties of the first audio content may be determined. For each training example of the training examples, the respective audio content may be analyzed to determine properties of the respective audio content. The properties of the first audio content and the properties of the audio contents associated with the training examples may be used to attribute the first audio content to a subgroup of the training examples. A respective data-record associated with a source associated with the training examples of the subgroup may be updated based on the attribution.

Abstract: Systems, methods and non-transitory computer readable media for prompt-based attribution of generated media contents to training examples are provided. In some examples, a first media content generated using a generative model in response to a first textual input may be received. The generative model may be a result of training a machine learning model using a plurality of training examples. Each training example of the plurality of training examples may include a respective textual content and a respective media content. Properties of the first textual input and properties of the textual contents included in the plurality of training examples may be used to attribute the first media content to a first subgroup of the plurality of training examples. The training examples of the first subgroup may be associated with a source. Further, a data-record associated with the source may be updated based on the attribution.

Abstract: Systems, methods and non-transitory computer readable media for identifying prompts used for training of inference models are provided. In some examples, a specific textual prompt in a natural language may be received. Further, data based on at least one parameter of an inference model may be accessed. The inference model may be a result of training a machine learning model using a plurality of training examples. Each training example of the plurality of training examples may include a respective textual content and a respective media content. The data and the specific textual prompt may be analyzed to determine a likelihood that the specific textual prompt is included in at least one training example of the plurality of training examples. A digital signal indicative of the likelihood that the specific textual prompt is included in at least one training example of the plurality of training examples may be generated.

Abstract: A system includes a fluid valve metering system which regulates a flow of a fluid within a gas turbine engine. The fluid valve metering system includes an inlet manifold, an outlet manifold in fluid communication with the inlet manifold, and multiple fluid conduits extending between the inlet manifold and the outlet manifold. Each respective fluid conduit of the multiple fluid conduits includes a respective fluid conduit valve of the multiple fluid conduit valves. Each fluid conduit valve regulates fluid the flow of the fluid through the respective fluid conduit. The fluid valve metering system also includes multiple differently sized orifices and a controller. The controller is coupled to the fluid valve metering system and programmed to monitor a usage of each orifice of multiple differently sized orifices, of each fluid conduit valve of multiple fluid conduit valves, or a combination thereof.

Abstract: A fuel metering valve system for use with a flow of fuel in a gas turbine engine may include a number of orifice plate lines, a number of differently sized orifice plates, and a number of orifice plate line valves. One of the orifice plate line valves opens and closes one of the orifice plates on the orifice plate lines.

Abstract: The “Positive Displacement Turbine” engine (PDT) presented herein conforms to the classical definition of a heat engine. It operates in a thermodynamic cycle approximating the Otto, Diesel and Muller cycles but the primary motive force is developed at the pressure face of a blade rather than at the head of a reciprocating piston. The machine is therefore truly rotary with turbine-like characteristics, nevertheless, a fixed mass of air and fuel is compressed, ignited and expanded in a truly positive displacement process. Improvements offered by the present invention arise from the novel application of compression and expansion cycles being executed in adjacent and isolated chambers dynamically linked via internally mounted rotating combustion chambers hither too unseen as prior art. The means provided by this unique aspect of the present invention place it into a class of prime mover all of its own.