Abstract: Disclosed implementations provide executable data, such as artificial intelligence models that can be owned, traded, and used in various execution environments. By coupling a model with a strictly defined interface definition, the model can be executed in various execution environments that support the interface. Coupling the model with a non-fungible cryptographic token allows the model and other components to be owned and traded as a unit. The tradeable composite units have utility across multiple supported execution environments, such as video game environments, chat bot environments and financial trading environments. Additionally, the interface allows for the creation of pipelines and systems from multiple complementary composite units that can be used to train other models and composite units.

Abstract: Methods and systems for sharing user information with computing resources over a computer network. The method includes monitoring user interactions of a user device with at least one remote computing resource using a monitoring module installed on the user device. User preference information is determined based on the user interactions and stored in a preference database. A machine learning prediction module is trained based on the user preference information. In response to establishing a connection of the user device with at least one specific remote computing resource, the machine learning prediction module predicts information to share with the at least one specific remote computing resource based on the user preference information. The predicted information is then transmitted to the at least one specific computing resource.

Abstract: Methods for configuring learning model for price optimization. Item ontologies defining categories, properties, and relationships between multiple items, and sales data for items are used to aggregate sales data for subsets of the items and create sales vectors for the items, A price optimization target for items can be specified as a function of a price vector and the sales vector. A learning model is trained based on the price vectors and the sales vectors to optimize the price of each specific item in accordance with the price optimization target.

Abstract: The present disclosure provides a method for configuring a learning model for music generation and the corresponding learning model. The method includes training a masked autoencoder with training data comprising a combination of a reconstruction loss over time and frequency domains and a patch-based adversarial objective operating at different resolutions. An omnidirectional latent diffusion model is trained based on music data represented in a latent space to obtain a pretrained diffusion model. The pretrained diffusion model is fine-tuned based on text-guided music generation, bidirectional music in-painting, and unidirectional music continuation. The method enables high-fidelity music generation conditioned on text or music representations while maintaining computational efficiency.

Abstract: Disclosed implementations provide executable data, such as artificial intelligence models that can be owned, traded, and used in various execution environments. By coupling a model with a strictly defined interface definition, the model can be executed in various execution environments that support the interface. Coupling the model with a non-fungible cryptographic token allows the model and other components to be owned and traded as a unit. The tradeable composite units have utility across multiple supported execution environments, such as video game environments, chat bot environments and financial trading environments. Additionally, the interface allows for the creation of pipelines and systems from multiple complementary composite units.

Abstract: The present disclosure provides a method for configuring a learning model for music generation and the corresponding learning model. The method includes training a masked autoencoder with training data comprising a combination of a reconstruction loss over time and frequency domains and a patch-based adversarial objective operating at different resolutions. An omnidirectional latent diffusion model is trained based on music data represented in a latent space to obtain a pretrained diffusion model. The pretrained diffusion model is fine-tuned based on text-guided music generation, bidirectional music in-painting, and unidirectional music continuation. The method enables high-fidelity music generation conditioned on text or music representations while maintaining computational efficiency.

Abstract: Disclosed implementations provide executable data, such as artificial intelligence models that can be owned, traded, and used in various execution environments. By coupling a model with a strictly defined interface definition, the model can be executed in various execution environments that support the interface. Coupling the model with a non-fungible cryptographic token allows the model and other components to be owned and traded as a unit. The tradeable composite units have utility across multiple supported execution environments, such as video game environments, chat bot environments and financial trading environments. Additionally, the interface allows for the creation of pipelines and systems from multiple complementary composite units.

Abstract: A computation model package including a plurality of composite data structures, each of the composite data structures including, a pointer specifying execution data associated with a computation model, and an interface definition module. A package input interface is coupled to each of the input interfaces, wherein the package input interface is compatible with the input interface of each of the composite data units, the package input interface being configured for receiving package input data and transmitting the input data to each of the input interfaces. A blending unit includes a blending input interface coupled to each of the output interfaces, whereby output data of each of the composite data structures is input into the blending input interface. The blending computation model is configured to process data received by the blending input interface to thereby provide a combination of the computation models at the blending output interface.

Abstract: The present disclosure provides a method for configuring a learning model for music generation and the corresponding learning model. The method includes training a masked autoencoder with training data comprising a combination of a reconstruction loss over time and frequency domains and a patch-based adversarial objective operating at different resolutions. An omnidirectional latent diffusion model is trained based on music data represented in a latent space to obtain a pretrained diffusion model. The pretrained diffusion model is fine-tuned based on text-guided music generation, bidirectional music in-painting, and unidirectional music continuation. The method enables high-fidelity music generation conditioned on text or music representations while maintaining computational efficiency.

Abstract: A computation model package including a plurality of composite data structures, each of the composite data structures including, a pointer specifying execution data associated with a computation model, and an interface definition module. A package input interface is coupled to each of the input interfaces, wherein the package input interface is compatible with the input interface of each of the composite data units, the package input interface being configured for receiving package input data and transmitting the input data to each of the input interfaces. A blending unit includes a blending input interface coupled to each of the output interfaces, whereby output data of each of the composite data structures is input into the blending input interface. The blending computation model is configured to process data received by the blending input interface to thereby provide a combination of the computation models at the blending output interface.

Abstract: Disclosed implementations provide executable data, such as artificial intelligence models that can be owned, traded, and used in various execution environments. By coupling a model with a strictly defined interface definition, the model can be executed in various execution environments that support the interface. Coupling the model with a non-fungible cryptographic token allows the model and other components to be owned and traded as a unit. The tradeable composite units have utility across multiple supported execution environments, such as video game environments, chat bot environments and financial trading environments. Additionally, the interface allows for the creation of pipelines and systems from multiple complementary composite units that can be used to train other models and composite units.

Abstract: Disclosed implementations provide executable data, such as artificial intelligence models that can be owned, traded, and used in various execution environments. By coupling a model with a strictly defined interface definition, the model can be executed in various execution environments that support the interface. Coupling the model with a non-fungible cryptographic token allows the model and other components to be owned and traded as a unit. The tradeable composite units have utility across multiple supported execution environments, such as video game environments, chat bot environments and financial trading environments. Additionally, the interface allows for the creation of pipelines and systems from multiple complementary composite units.

Abstract: A computation model package including a plurality of composite data structures, each of the composite data structures including, a pointer specifying execution data associated with a computation model, and an interface definition module. A package input interface is coupled to each of the input interfaces, wherein the package input interface is compatible with the input interface of each of the composite data units, the package input interface being configured for receiving package input data and transmitting the input data to each of the input interfaces. A blending unit includes a blending input interface coupled to each of the output interfaces, whereby output data of each of the composite data structures is input into the blending input interface. The blending computation model is configured to process data received by the blending input interface to thereby provide a combination of the computation models at the blending output interface.