Abstract: Computer-implemented techniques for multimodal content relevance prediction using neural networks involves processing multimodal content comprising a digital image and text. Initially, dense embeddings are obtained: an image embedding from a pretrained convolutional neural network, and a text embedding from a pretrained transformer network. These embeddings encapsulate the features of the image and text respectively. Two pretrained dense neural sub-networks then reduce the dimensionality of these embeddings. A third dense neural sub-network determines a numerical score for the multimodal content using the reduced embeddings and an additional feature embedding. This score reflects various aspects of the multimodal content, leading to an action taken based on this numerical evaluation, providing a comprehensive and nuanced understanding and management of multimodal digital content.

Abstract: Embodiments of the disclosed technologies include generating a first thread classification prompt based on a first thread portion of an online dialog involving a user of a computing device, sending the first thread classification prompt to a first large language model, receiving a first thread classification generated and output by the first large language model based on the first thread classification prompt, formulating a plan execution prompt based on the first thread classification, sending the plan execution prompt to a second large language model, receiving a second thread portion generated and output by the second large language model based on the plan execution prompt and the online dialog, and generating a label for a third thread portion of the online dialog.

Abstract: System and techniques for activity sensing online preference assay are described herein. An initial indication of an online activity preference for a member of a social network service may be obtained. A plurality of member activities corresponding with the online activity preference for a period of time subsequent to obtaining the initial indication may be collected. Respective decision trees of a set of decision trees may be traversed based on a set of inputs comprising the collected plurality of member activities to determine a probability that the online activity preference corresponds with the member. An actual online activity preference may be derived for the member using an aggregation of the determined probability for the respective decision trees of the set of decision trees. Social network content items may be filtered for the member based on the actual online activity preference.

Abstract: System and techniques for activity sensing online preference assay are described herein. An initial indication of an online activity preference for a member of a social network service may be obtained. A plurality of member activities corresponding with the online activity preference for a period of time subsequent to obtaining the initial indication may be collected. Respective decision trees of a set of decision trees may be traversed based on a set of inputs comprising the collected plurality of member activities to determine a probability that the online activity preference corresponds with the member. An actual online activity preference may be derived for the member using an aggregation of the determined probability for the respective decision trees of the set of decision trees.

Abstract: System and techniques for activity sensing online preference assay are described herein. A count for an action completed by a member of a social network service may be detected over a first period of time. The member may be labeled with an online activity preference based on the count and a subset of the first period of time. A plurality of member activities corresponding with the online activity preference may be collected for a second period of time prior to obtaining the initial indication. Respective decision trees of a set of decision trees may be traversed based on a set of inputs comprising the collected plurality of member activities to determine a probability that the online activity preference corresponds with the member. An actual online activity preference may be derived for the member using an aggregation of the determined probability for the respective decision trees of the set of decision trees.