Abstract: Methods, systems, and apparatuses for performing natural language prompt compression, the method being performed by an electronic device and including: obtaining a prompt for an artificial intelligence (AI) inference model, wherein the prompt corresponds to a first plurality of tokens; providing the prompt as an input to an AI compression model; and obtaining a compressed prompt based on an output of the AI compression model, wherein the compressed prompt corresponds to a second plurality of tokens which is smaller than the first plurality of tokens, and wherein the prompt and the compressed prompt are expressed using natural language.

Abstract: A method includes receiving wireless fingerprint data identifying multiple locations within a specified area and, for each location, one or more signal strength values associated with wireless signals received from one or more of multiple wireless transmitters. The wireless fingerprint data is missing signal strength values for one or more transmitters at one or more specific locations. The method also includes generating a training dataset by adding filler signal strength values in place of at least some missing values. The method further includes training a machine learning model using the training dataset. The model is trained to receive a specified location as input and generate predicted signal strength values as outputs. In addition, the method includes using the trained model to generate additional signal strength values. At least some additional signal strength values are to be used in place of at least a portion of the missing values.

Abstract: An electronic device may be provided to perform collision analysis. The electronic device may be configured to: receive sensor data from an inertial-measuring-unit (IMU) sensor; detect that a collision event has occurred based on the sensor data and detect collision data from the sensor data; input the collision data into a collision classification model that is trained to predict a collision material type and a collision intensity of the collision event; and determine an action to be performed by the electronic device based on the collision material type and the collision intensity of the collision event.

Abstract: A method for detecting a drop event of an electronic device, may include: obtaining an angular velocity and a proper acceleration of the electronic device based on sensor data received from an inertial measurement unit (IMU) sensor of the electronic device; obtaining centripetal acceleration of the electronic device based on the angular velocity, principal moments of inertia of the electronic device, and position of the IMU sensor within the electronic device; based on an acceleration difference between the centripetal acceleration and the proper acceleration, determining whether the electronic device is in a fall state; and based on the electronic device being determined to be in the fall state, providing an analysis result of the drop event.

Abstract: A method of performing visual question answering (VQA), including: obtaining an image and a question corresponding to the image; generating a plurality of feature predictions about at least one object included in the image by providing the image to an artificial intelligence (AI) scene perception model; generating a plurality of symbolic programs and a plurality of program confidence scores by providing the question to an AI question parsing model; selecting a symbolic program associated with a program confidence score which is highest among the plurality of program confidence scores; executing the selected symbolic program by performing a set of logic operations included in the selected symbolic program on the plurality of feature predictions; and determining a natural language answer to the question based on a result of the set of logic operations.

Abstract: A method includes receiving wireless fingerprint data identifying multiple locations within a specified area and, for each location, one or more signal strength values associated with wireless signals received from one or more of multiple wireless transmitters. The wireless fingerprint data is missing signal strength values for one or more transmitters at one or more specific locations. The method also includes generating a training dataset by adding filler signal strength values in place of at least some missing values. The method further includes training a machine learning model using the training dataset. The model is trained to receive a specified location as input and generate predicted signal strength values as outputs. In addition, the method includes using the trained model to generate additional signal strength values. At least some additional signal strength values are to be used in place of at least a portion of the missing values.