Abstract: Disclosed are embodiments for facilitating generative artificial intelligence (AI) to pre-train and fine-tune models for multiple autonomous vehicle (AV) trajectories generation. In some aspects, an embodiment includes training a teacher generative AI model on a first set of training data; providing a student generative AI model with at least one distillation of the teacher generative AI model, the at least one distillation comprising transformer weights, embeddings, or predictions labels of the teacher generative AI model; training the student generative AI model that is initialized with the at least one distillation of the teacher generative AI model, wherein the student generative AI model is trained using a second set of training data that is smaller than the first set of training data; and deploying the student generative AI model to a resource-constrained environment.

Abstract: Disclosed are embodiments for facilitating right-of-way-based semantic coverage and automatic labeling for trajectory generation in autonomous systems. In some aspects, an embodiment includes receiving a set of trajectories generated by a trajectory generation source, the set of trajectories generated for an autonomous vehicle (AV) interaction with a road agent; labeling a ground truth trajectory from the set of trajectories with a ground truth label; classifying each remaining trajectory of the set of trajectories as at least one of an assert trajectory or a yield trajectory; for an assert group comprising the assert trajectories, assigning an auxiliary assert label to the assert trajectory having a highest selection score; for a yield group comprising the yield trajectories, assigning an auxiliary yield label to the yield trajectory having a highest selection score; and utilizing the ground truth label, the auxiliary assert label, and the auxiliary yield label to train a trajectory generation model.

Abstract: Techniques for improving a user video game experience are described. In an example, a computer system receives event data from a plurality of user devices. Each event data includes an identifier of an activity in a video game and data indicating completion of the activity. The identifier can be predefined in program code of the video game. The identifier and completion data can be received based on an execution of the program code. The event data is processed to determine a video game mechanic suggestion to help a player complete the activity.

Abstract: The disclosure relates to a grabbing detection method based on an RP-ResNet. The method comprises: inputting an image of a target; pre-processing data; performing data processing by an RP-ResNet model; and finally, generating a grabbing block diagram of a target to be grabbed. On the basis of a model ResNet 50, a region proposal network is used in the 30th layer of a network, fuzzy positioning is performed on the positions of grabbing points, feature information of high and low layers is fully fused to strengthen the utilization of information of low layers, and the 40th layer of the network is added to an SENet structure, thereby further increasing the detection accuracy of a grabbing points. By a grabbing detection framework based on ResNet-50, a residual network, a region proposal idea and SENet are combined, thereby ensuring rapid and accurate target detection.

Abstract: Techniques for improving a user video game experience are described. In an example, a computer system receives event data from a plurality of user devices. Each event data includes an identifier of an activity in a video game and data indicating completion of the activity. The identifier can be predefined in program code of the video game. The identifier and completion data can be received based on an execution of the program code. The event data is processed to determine a video game mechanic suggestion to help a player complete the activity.

Abstract: Disclosed are embodiments for facilitating right-of-way-based semantic coverage and automatic labeling for trajectory generation in autonomous systems. In some aspects, an embodiment includes receiving a set of trajectories generated by a trajectory generation source, the set of trajectories generated for an autonomous vehicle (AV) interaction with a road agent; labeling a ground truth trajectory from the set of trajectories with a ground truth label; classifying each remaining trajectory of the set of trajectories as at least one of an assert trajectory or a yield trajectory; for an assert group comprising the assert trajectories, assigning an auxiliary assert label to the assert trajectory having a highest selection score; for a yield group comprising the yield trajectories, assigning an auxiliary yield label to the yield trajectory having a highest selection score; and utilizing the ground truth label, the auxiliary assert label, and the auxiliary yield label to train a trajectory generation model.

Abstract: Disclosed are embodiments for facilitating generative artificial intelligence (AI) to pre-train and fine-tune models for multiple autonomous vehicle (AV) trajectories generation. In some aspects, an embodiment includes training a teacher generative AI model on a first set of training data; providing a student generative AI model with at least one distillation of the teacher generative AI model, the at least one distillation comprising transformer weights, embeddings, or predictions labels of the teacher generative AI model; training the student generative AI model that is initialized with the at least one distillation of the teacher generative AI model, wherein the student generative AI model is trained using a second set of training data that is smaller than the first set of training data; and deploying the student generative AI model to a resource-constrained environment.

Abstract: Disclosed is a microscopic comparison and experimental verification method for the wettability of similar surfactants on coal dust, comprising: collecting a coal sample on site from a mining area and analyzing the coal sample by infrared spectroscopy and nuclear magnetic resonance spectroscopy to obtain information on functional groups and carbon structure of coal molecules; S2: constructing a surfactant-coal molecule electrostatic interaction model and analyzing an orbital energy difference and an electrostatic potential difference between surfactant molecules and coal molecules, etc. S6. The invention provides a simple and effective idea for the selection of surfactants.

Abstract: A machine learning (ML) model is used to identify spam messages and spammers in computer game settings based on learned gamer behavior. An evaluator module receives score(s) from the ML model indicating whether a particular message is spam or other undesired message and when the scores satisfy a threshold, passes the message to a punishment module to determine whether the warn, suspend, or ban the sending account.

Abstract: A machine learning (ML) model is used to identify spam messages and spammers in computer game settings based on learned gamer behavior. Message text may also be used. An evaluator module receives the score(s) from the ML model(s) indicating whether a particular message is spam and when the score(s) satisfy a threshold, passes the message to a punishment module to determine whether the warn, suspend, or ban the sending account.

Abstract: An RGB-T (Thermal) multispectral pedestrian detection method based on a target aware fusion strategy, which aims to accurately determine the position of pedestrians from a pair of RGB and thermal infrared images. Given a pair of RGB and thermal infrared image to be detected, this method firstly extracts multispectral features from the RGB and thermal infrared images; then the extracted multispectral features are fused by using a target aware fusion strategy; finally, the fused features are sent to a detection head for pedestrian detection, and the pedestrian position box and confidence are output. The method can effectively fuse the deep features of multispectral images, enhance the feature expression of pedestrian areas and suppress irrelevant background noise features during the fusion process, and can realize accurate pedestrian detection.

Abstract: A machine learning (ML) model is used to identify spam messages and spammers in computer game settings based on learned gamer behavior. An evaluator module receives score(s) from the ML model indicating whether a particular message is spam or other undesired message and when the scores satisfy a threshold, passes the message to a punishment module to determine whether the warn, suspend, or ban the sending account.

Abstract: A method, electronic device and storage medium for generating information are disclosed. The method includes: acquiring a plurality of tag entity words from a target video, the tag entity words including a person entity word, a work entity word, a video category entity word, and a video core entity word, the video core entity word including an entity word for characterizing a content related to the target video; linking, for a tag entity word among the plurality of tag entity words, the tag entity word to a node of a preset knowledge graph; determining semantic information of the target video based on a linking result of each of the tag entity words; and structuring the semantic information of the target video based on a relationship between the node and an edge of the knowledge graph, to obtain structured semantic information of the target video.

Abstract: A machine learning (ML) model is used to identify spam messages and spammers in computer game settings based on learned gamer behavior. Message text may also be used. An evaluator module receives the score(s) from the ML model(s) indicating whether a particular message is spam and when the score(s) satisfy a threshold, passes the message to a punishment module to determine whether the warn, suspend, or ban the sending account.

Abstract: A method for mining an entity focus in a text may include: performing word and phrase feature extraction on an input text; inputting an extracted word and phrase feature into a text coding network for coding, to obtain a coding sequence of the input text; processing the coding sequence of the input text using a core entity labeling network to predict a position of a core entity in the input text; extracting a subsequence corresponding to the core entity in the input text from the coding sequence of the input text, based on the position of the core entity in the input text; and predicting a position of a focus corresponding to the core entity in the input text using a focus labeling network, based on the coding sequence of the input text and the subsequence corresponding to the core entity in the input text.

Abstract: A machine learning (ML) model is used to identify spam messages and spammers in computer game settings based on learned gamer behavior. An evaluator module receives score(s) from the ML model indicating whether a particular message is spam or other undesired message and when the scores satisfy a threshold, passes the message to a punishment module to determine whether the warn, suspend, or ban the sending account.

Abstract: A system and method for providing personalized assistance in a virtual environment is disclosed. A plurality of trigger events is stored in memory, each trigger event based on a user interaction in the virtual environment. Data sent over a communication network regarding gameplay of a user associated with a media title engaged in the virtual environment is received. Play characteristics exhibited by the user based on the received data are identified. One or more user generated content streams that meet conditions of an identified one or more trigger events are identified. Identified streams are ranked based on a match between the play characteristics exhibited by the user and metadata of each of the identified streams. A display of the ranked streams is provided, wherein the display includes an analysis of the match.