Abstract: Embodiments described herein provide a system and method for unsupervised anomaly detection. The system receives, via a communication interface, a dataset of instances that include anomalies. The system determines, via an inlier model, a set of noisy labels. The system trains a causality-based label-noise model based at least in part on the set of noisy labels and the set of high-confidence instances. The system determines an estimated proportion of anomalies in the dataset of instances. The system retrains the inlier model based on the estimated inlier samples. The system iteratively retrains the inlier model and the trained causality-based label-noise model based on the output from the corresponding retrained models not converging within the convergence threshold. The system extracts the anomaly detection model from the iteratively trained causality-based label-noise model.

Abstract: Methods, apparatuses, and computer-program products are disclosed. The method may include deriving a first intermediate LLM based on a broad spectrum LLM. The first intermediate LLM may be associated with a first level of a hierarchy and deriving the first intermediate LLM may include training the first intermediate LLM on first training data associated with the first level of the hierarchy. The method may include deriving a user-level LLM based on the first intermediate LLM, where the user-level LLM is associated with a user associated with a second level of the hierarchy included in the first level of the hierarchy. Deriving the user-level LLM may include training the user-level LLM on second training data associated with the user, where deriving the user-level LLM may further include inheriting one or more first characteristics from the first intermediate LLM.

Abstract: Systems and techniques are described for a unified data pipeline interface. The pipeline interface provides an interface illustrating key metrics, activities, insight, and/or other categories. The pipeline interface provides such data as to a specific opportunity. The systems and techniques described herein allow for the determination, presentation, and standardization of such data through a specifically configured graphical user interface.

Abstract: Techniques for streaming generative machine learned model (or LLM) output to a virtual space are described herein. A system may receive a request to perform an action. The system may leverage LLMs to assist in performing aspects of the requested action. The system can generate input data to input into the LLM. When generating the input data, the system can identify sensitive data associated with the request. The system can modify the input data to mask and/or anonymize the sensitive data. The system can input the input data into an LLM trained to output a subset (e.g., less than all) of the response at a time. The system can add the output subset to a buffer and upon identifying the masked data in the buffer, the system can demask the sensitive data and output the sensitive data to the user profile in a streaming manner.

Abstract: Disclosed are some implementations of systems, apparatus, methods and computer program products for implementing a database backup system.

Abstract: Embodiments described herein provide a unified debugging framework that adapts a pretrained programming language model for line-level debugging and repair. Specifically, the debugging framework follow the logic of programmers on how to debug their code. For example, the debugging framework first determines whether or not a function is buggy. If it is buggy, the debugging framework localizes the problematic line and provide a patch (repair).

Abstract: An automated data extraction pipeline for large language model (LLM) training may include extracting a set of code segments from a set of natural language question-answer (Q&A) combinations that each include a provided input, a provided output, and a provided code segment formatted to transform the provided input into the provided output. The data extraction pipeline may then generate a predicted output from a question portion of a first natural language Q&A combination using a first LLM. A first extracted code segment from the extracted set of code segments may then be executed to generate a first actual output of the first extracted code segment. One or more data samples may then be generated for training a second LLM based on a comparison of the first actual output to the predicted output. The second LLM may then be trained using the one or more data samples.

Abstract: Techniques for modifying the display of task data are discussed herein. A user profile may request to modify a user interface object from a compressed state to an expanded state. Based on the request, the communication platform may convert the user interface object into an expanded state such that one or more columns of the task are presented in a single user interface. The communication platform may determine an updated organization of the columns and use such data to determine a modified size of the user interface object. The communication platform can generate a modified user interface object in an expanded state that includes an increased number of the columns. The communication platform may cause the modified user interface object to be displayed via a user interface of a mobile device.

Abstract: Embodiments described herein provide a universal item learning framework that generates universal item embeddings for zero-shot items. Specifically, the universal item learning framework performs generic features extraction of items and product knowledge characterization based on a product knowledge graph (PKG) to generate embeddings of input items. A pretrained language model (PLM) may be adopted to extract features from generic item side information, such as titles, descriptions, etc., of an item. A PKG may be constructed to represent recommendation-oriented knowledge, which comprise a plurality of nodes representing items and a plurality of edges connecting nodes represent different relations between items. As those relations in PKG are usually retrieved from user-item interactions, the PKG adapts the universal representation for recommendation with knowledge of user-item interactions.

Abstract: A computing services environment may include a database system, a generative language model interface, a communication interface, and a messaging interface. The database system may store database records reflecting interactions between tenants of the computer services environment and individuals interacting with the tenants, and may determine an input description of a communication campaign between a tenant of the plurality of tenants and a corresponding segment of the individuals. The generative language model interface may determine a textual description of one or more elements of the communication campaign by completing a campaign brief generation prompt via a generative language model. The communication interface may transmit to a client machine authenticated to a database system account linked to the tenant an instruction to generate a graphical user interface at the client machine. The messaging interface may transmit messages based on the input description and the refinement.

Abstract: Embodiments described herein provide a method of generating a vision-language task output to a text instruction relating to an input image, the method comprising receiving, via a data interface, the input image and the text instruction comprising an instruction relating to the image. The method further includes encoding, via an image encoder, the image into a first image representation. The method further includes generating, by a multimodal encoder, a second image representation based on cross-attending the first image representation to the text instruction. The method further includes generating, by a neural network based language model, a vision-language task output in response to the text instruction based on an input combining the second image representation and the text instruction.

Abstract: A runtime agent that is executable on a virtual machine may obtain one or more identifiers that correspond to one or more software classes from a first configuration file that is configured for the runtime agent. The runtime agent may monitor for loading of the one or more software classes by a first computer program that is being executed on the virtual machine. Further, the runtime agent may execute one or more actions based on detecting the loading of the one or more software classes by the first computer program where the one or more actions may impact the execution of the first computer program on the virtual machine.

Abstract: Techniques are disclosed that relate to skip lists. A computer system maintains a skip list having towers of varying depths and entries storing pointers to other towers. A first tower includes an entry at a particular depth storing a pointer to access an entry of a second tower. The pointer includes first similarity information indicating an amount of similarity between a key of the first tower and a key of the second tower. The computer system performs a traversal of the skip list for a search key. The computer system generates second similarity information indicating an amount of similarity between the first tower's key and the search key. Based on a comparison involving the first and second similarity information and without accessing the second tower to obtain information about its key, the computer system determines whether to traverse to the second tower using the pointer or descend the first tower.

Abstract: Disclosed are systems, methods, apparatus and computer program products for facilitating voice-based interaction by a mobile device with an enterprise database. In some implementations, a command and a type of enterprise work record are identified in a first one or more voice signals obtained at the mobile device. One or more fields of the identified record type required by the enterprise database to be populated to carry out the identified command is determined. Field data can be identified in a second one or more voice signals obtained at the mobile device. Structured text data comprising the identified command, the identified record type and the identified field data can be sent to a server.

Abstract: A computing services environment may include application servers providing computing services including access to a database system, a unified metadata framework including autonomous agent definitions referencing action definitions defining a plurality of actions capable of being performed within the computing services environment, an agent service configured to instantiate an autonomous agent instance based on an autonomous agent definition, and an orchestration layer configured to determine an orchestration plan based on novel planning text generated by a generative language model. The orchestration plan may include a subset of the plurality of actions identified in the novel planning text. The computing services environment may execute the subset of the plurality of actions within the computing services environment.

Abstract: Techniques are disclosed that pertain to linked database systems. A computer system implements a first database system that manages a table storing data for a tenant. The computer system may receive an indication to provision, at a second database system having a database management engine of a different type than a database management engine of the first database system, data of the tenant stored in the table. The computer system provisions the data in data structures at the second database system and permits the tenant to perform, on the data, a first set of operations at the first database system and a second set of operations at the second database system. The second set of operations includes functionality not included in the first set of operations. The computer system may receive a result of processing by the tenant using the second database system and store the result in the table.

Abstract: An extensible platform-as-a-service (PaaS) system is used during the software development lifecycle (SDLC) processes of an application. The system facilitates the process of getting security approval for the application. The system allows developers to use software bundles including software modules that are pre-approved. The system allows a developer to customize one or more software modules of the software bundle if necessary. The system monitors the development of the application to check if the developer customizes any software module to use a configuration that is not pre-approved. The system automatically generates a report noting the customization to the software module and requests the security team to review the modified configuration for security approval.