Abstract: Implementations relate to reducing latency in generating and/or rendering a given stream of natural language (NL) based output generated using a large language model (LLM). Processor(s) of a system can: receive NL based input associated with a client device, generate the stream of NL based output utilizing the LLM that is responsive to the NL based input and that is for a given dialog context of an ongoing dialog, and cause the stream of NL based output to be rendered at the client device. Notably, the processor(s) can employ attribute classifier(s) and a multi-objective scorer to implement a blockwise controlled decoding technique in generating the stream of NL based output utilizing the LLM. By implementing the blockwise controlled decoding technique in generating the stream of NL based output utilizing the LLM, the processor(s) can reduce latency in generating and/or of the stream of NL based output generated utilizing the LLM.

Abstract: Implementations relate to a method implemented by one or more processors, the method including: receiving an input prompt for a large language model (LLM); generating first LLM output that is usable to generate a set of user interface (UI) each associated with a corresponding sub-prompt of the input prompt; causing, based on the first LLM output, the set of UI elements to be rendered at a user device; receiving further user input based on user interactions with one or more of the UI elements of the set of UI elements; and in response to determining that one or more termination conditions are satisfied: generating a final response to the input prompt based on generating second LLM output that is usable to generate the final response; and causing the final response to be rendered at the user device.

Abstract: Implementations relate to a method implemented by one or more processors, the method including: receiving an input prompt for a large language model (LLM); generating first LLM output that is usable to generate a set of user interface (UI) each associated with a corresponding sub-prompt of the input prompt; causing, based on the first LLM output, the set of UI elements to be rendered at a user device; receiving further user input based on user interactions with one or more of the UI elements of the set of UI elements; and in response to determining that one or more termination conditions are satisfied: generating a final response to the input prompt based on generating second LLM output that is usable to generate the final response; and causing the final response to be rendered at the user device.

Abstract: The invention discloses a copyright protection and royalty distribution method based on a NFT and its associated smart contracts. The smart contracts govern the initial minting, derivative minting, and trading of the NFT as well as the royalty distributions of every trades in the lifetime of the NFT, This method uses blockchain and NFT technology to manage and protect the copyright of digital music. The ownership and trade transaction records of the NFT are verified through blockchain technology and the distribution of digital music royalties are automated via smart contracts. According to the method of the present invention, the copyright of digital music can be made more transparent and secure, the distribution of royalties can be more just and efficient, and copyright infringement and improper resale can be avoided.

Abstract: Implementations relate to reducing latency in generating and/or rendering a given stream of natural language (NL) based output generated using a large language model (LLM). Processor(s) of a system can: receive NL based input associated with a client device, generate the stream of NL based output utilizing the LLM that is responsive to the NL based input and that is for a given dialog context of an ongoing dialog, and cause the stream of NL based output to be rendered at the client device. Notably, the processor(s) can employ attribute classifier(s) and a multi-objective scorer to implement a blockwise controlled decoding technique in generating the stream of NL based output utilizing the LLM. By implementing the blockwise controlled decoding technique in generating the stream of NL based output utilizing the LLM, the processor(s) can reduce latency in generating and/or of the stream of NL based output generated utilizing the LLM.

Abstract: The present invention discloses a simulation device for a preferential flow of a fissured-porous dual-permeability media and an experimental method, and belongs to the technical field of geological engineering. The simulation device comprises a support. The support is detachably connected with a transparent container. The interior of the transparent container is filled with a fissured-porous dual-permeability media experimental model. The top of the transparent container is open. A spraying device is arranged above the transparent container. Liquid rapid outflow ports are formed in the bottom of the transparent container and are connected with a liquid collection device. The present invention further discloses an experimental method of the simulation device and a manufacturing method of the fissured-porous dual-permeability media experimental model. The simulation device of the present invention can highlight and enhance the preferential flow experiment effect.

Abstract: Implementations provide an improved system for presenting search results based on entity associations of the search items. An example method includes generating first-level clusters of items responsive to a query, each cluster representing an entity in a knowledge base and including items mapped to the entity, merging the first-level clusters based on entity ontology relationships, applying hierarchical clustering to the merged clusters, producing final clusters, and initiating display of the items according to the final clusters. Another example method includes generating first-level clusters from items responsive to a query, each cluster representing an entity in a knowledge base and including items mapped to the entity, producing final clusters by merging the first-level clusters based on an entity ontology and an embedding space that is generated from an embedding model that uses the mapping, and initiating display of the items responsive to the query according to the final clusters.

Abstract: The present invention discloses a simulation device for a preferential flow of a fissured-porous dual-permeability media and an experimental method, and belongs to the technical field of geological engineering. The simulation device comprises a support. The support is detachably connected with a transparent container. The interior of the transparent container is filled with a fissured-porous dual-permeability media experimental model. The top of the transparent container is open. A spraying device is arranged above the transparent container. Liquid rapid outflow ports are formed in the bottom of the transparent container and are connected with a liquid collection device. The present invention further discloses an experimental method of the simulation device and a manufacturing method of the fissured-porous dual-permeability media experimental model. The simulation device of the present invention can highlight and enhance the preferential flow experiment effect.

Abstract: Embodiments relate to user attitude modeling and behavior prediction for a social media network. One aspect includes collecting data relating to previously demonstrated sentiments, opinions, and actions attributed to network users toward a topic. Another aspect includes creating a model from the data, which includes factorizing the actions for behavior inference, factorizing auxiliary content from the network for opinion and sentiment inferences, and applying sentiment and opinion regularization to constrain user preferences on implicit topics to explicit sentiments and explicit opinions. Another aspect includes applying the model to a new user of the network with respect to the topic, and generating a prediction with respect to the user that includes predicting sentiment and opinion as a function of the auxiliary content and feature coefficients learned during a training process, and predicting a future action of the user as a function of the auxiliary content and latent profiles of the topic.

Abstract: Implementations provide an improved system for presenting search results based on entity associations of the search items. An example method includes generating first-level clusters of items responsive to a query, each cluster representing an entity in a knowledge base and including items mapped to the entity, merging the first-level clusters based on entity ontology relationships, applying hierarchical clustering to the merged clusters, producing final clusters, and initiating display of the items according to the final clusters. Another example method includes generating first-level clusters from items responsive to a query, each cluster representing an entity in a knowledge base and including items mapped to the entity, producing final clusters by merging the first-level clusters based on an entity ontology and an embedding space that is generated from an embedding model that uses the mapping, and initiating display of the items responsive to the query according to the final clusters.

Abstract: Implementations provide an improved system for presenting search results based on entity associations of the search items. An example method includes, for each of a plurality of crowdsource workers, initiating display of a first randomly selected cluster set from a plurality of cluster sets to the crowdsource worker. Each cluster set represents a different clustering algorithm applied to a set of search items responsive to a query. The method also includes receiving cluster ratings for the first cluster set from the crowdsource worker and calculating a cluster set score for the first cluster set based on the cluster ratings. This is repeated for remaining cluster sets in the plurality of cluster sets. The method also includes storing a cluster set definition for a highest scoring cluster set, associating the cluster set definition with the query, and using the definition to display search items responsive to the query.

Abstract: Provided are techniques for tailoring correspondence based upon individual recipients, comprising receiving a correspondence for dissemination to a set of recipients; annotating text within the composition to identify words and characteristics of the words; identifying a customization criteria based upon a target audience; generating, a template, wherein the template comprises: the customization criteria; and modification constraints; and applying the template and the customization criteria to the annotated text to generate a revised correspondence.

Abstract: A computer-implemented method for optimizing information workforce selection is provided. The computer-implemented method includes providing a ground-truth data collection of information of a plurality of candidates for a group or a team workforce selection. The computer-implemented method further includes determining at least one expertise and at least one trait characteristic, or at least one feature of each of the candidates within the plurality of candidates. The computer-implemented method further includes performing trait compability analysis that provides a compatibility score of potential candidates of the plurality of candidates, for a group. The computer-implemented method further includes performing a collaboration compability analysis that provides a collaboration compatibility score of plurality of potential candidate within the plurality of candidates.

Abstract: A computer-implemented method, computer program product, and computer system for selecting strangers for information spreading on a social network. For the strangers who are users of the social network and not related to each other, information spreading probabilities based on features, information reach, and information spreading probabilities based on a wait time are computed. Fitness scores of the strangers are computed; the fitness scores are a function of the information spreading probabilities, the information reach, and the information spreading probabilities. The strangers are ranked, based on the fitness scores, in a sorted set. One or more of the strangers for the information spreading are selected from the sorted set. The one or more of the strangers for the information spreading are selected by determining an interval in the sorted set, and the interval satisfies an optimization objective of maximizing unit information reach per stranger.