Abstract: A method for predicting at least one property of a crystal of a material, with the crystal exhibiting at least one point defect. At least one module samples structures of materials and point defects of the crystal. The method comprises: providing a neural network. The neural network comprises: receiving as input a structure of the material and an ideal crystal unit cell structure. The neural network also comprises: outputting at least one target quantity and using a generated set of data and representing the point defect. The point defect represents a set of coordinates and a type of the point defect and a crystal unit cell structure. The neural network further comprises: receiving as input at least one of a cloud of defect points and a global state vector. The neural network additionally comprises outputting a vector.

Abstract: A multi-layer path-planning system and method calculates trajectories for autonomous vehicles using a global planner, a fast local planner, and an optimizing local planner. The calculated trajectories are used to guide the autonomous vehicle along a bounded path between a starting point and a destination.

Abstract: A system receives a user query requesting a testable hypothesis about a scientific topic. The system classifies the user query into a first theoretical framework of a plurality of theoretical frameworks each comprising of terms and principles related to a particular scientific topic. The system generates the testable hypothesis by a first machine learning (ML) model that is configured to: receive as inputs: the user query, the first theoretical framework, and information from a graph document database comprising data associated with scientific documents, generate, as an output, the testable hypothesis that can be evaluated using the first theoretical framework and that does not reiterate a hypothesis or findings from the scientific documents in the graph document database. The system outputs the testable hypothesis via a user interface in response to the user query.

Abstract: An orchestration platform manages overtaking by autonomous vehicles by way of dividing a course into decision zones and execution zones. Autonomous vehicles proposed overtaking trajectories in the decision zones, which are evaluated and accepted or rejected by the orchestration platform. The orchestration platform is implemented as a master path coordinator that communicates wireless with the autonomous vehicles or at the vehicle level by acting as an on-board mediator of proposed trajectories. Autonomous vehicles are permitted to execute overtaking trajectories that meet certain predetermined safety requirements.

Abstract: Systems and methods provide a multidimensional data structure to tailor data storage and corresponding user output. Tailored graph data structures reduce the level of hallucination in composing an answer to a user using a large language model. In response to a user query of documents, the user query is translated to a vector. From the vector, the most relevant pieces of documents that are as similar as possible in semantics to the question of a person can be determined and communicated to the user. In one aspect, using the vector base (vector query applied to the documents), a graph can be generated in the form of nodes and connections between data in the documents.

Abstract: Disclosed herein are systems and methods for ML-based assessment of a live presentation by a presenter and engagement of in-person and remote audience members. The method includes: obtaining a live presentation video stream, a live presenter audio stream, and presentation material; evaluating the live presentation using a prepared presentation evaluation MLM; obtaining, for each audience member, whether in-person or remote, participating in the live presentation as an in-person audience member or a remote audience member, a plurality of video streams capturing each respective audience member, a plurality of audio streams for each respective audience member, and a plurality of capture streams capturing an interaction of each audience member and a respective computing device; evaluating an engagement of at least one audience member using a prepared engagement evaluation MLM; and generating a comprehension score based on the presentation score and the individual engagement score for at least one audience member.

Abstract: Disclosed herein are systems and methods for updating a graphical user interface displaying content related to a topic based on user performance. A method may include: receiving, via a user interface (UI), a user selection of a topic; generating, using a machine learning algorithm, a course from reference materials describing a plurality of sub-topics associated with the topic, wherein the machine learning algorithm includes, in the course, a plurality of assessments that test comprehension of the plurality of sub-topics; outputting the course on the UI; monitoring user interaction with a first subset of the assessments within the course on the UI; in response to determining, based on the monitoring, that the user interaction does not meet a comprehension criteria, modifying, using the machine learning algorithm, a first subset of the sub-topics corresponding to the first subset of the assessments; and outputting the modified course on the UI.

Abstract: Disclosed herein are systems and method for generating animated avatars of users in real-time during a teleconference. The method includes training AI avatar generation models to create an avatar of a first user, deploying an AI avatar generation agent on a communication device, collecting sensor data from different sensors associated with the first user and sending the collected sensor data to the communication device of the second user, activating a data processing model and to identify the types of sensor data received from the communication device of the first user and activating the AI avatar generation agent of the second user to execute, on the communication device of the second user, the plurality of AI avatar generation models, and displaying, on the communication device of second user, the animated avatar of the first user synced with the real-time audio of the voice of the first user during the teleconference.

Abstract: Methods and systems for enhancing a student's comprehension of visually narrated lectures by automatically augmenting narration of textual lectures with automatically generated textual scenarios inserted into the lecture, including by automatically selecting the locations of the insertion, contents, voice, and avatar characteristics for the scenarios.

Abstract: Systems and methods include detecting obstacles and drivable areas by an autonomous vehicle by inputting image and map data into a neural network to extract feature vectors. A transformer encoder converts these vectors from camera space to Bird's Eye View (BEV) space. A detection head identifies objects, and a segmentation head generates a BEV map showing objects and drivable surfaces. Attributes from both heads are compared, and the segmentation head's weights are updated accordingly, resulting in an updated BEV segmentation map output by the updated segmentation head.

Abstract: Disclosed herein are systems and methods for providing LLM embeddings. The method also includes receiving a query to a LLM service. The method also includes determining if a first embedding of the input query is provided by a main embedding model. The method further includes, based on a determination that the first embedding is provided by the main embedding model, identifying an embeddings cluster similar to the input query, and computing a main centroid embedding for the embeddings cluster based on the first embedding. The method further includes based on a determination that the first embedding is not provided by the main embedding model, identifying an embeddings cluster similar to the input query, and transmitting the main centroid embedding of the embeddings cluster to the LLM service.

Abstract: A system determines whether a first operation performed by an MLM is compatible with one of a first encryption scheme and a second encryption scheme, wherein the MLM is distributed over at least one client device and at least one server. In response to determining that the first operation is compatible with the first encryption scheme, the system: encrypts data associated with the first operation using the first encryption scheme; and transmits the data encrypted by the first encryption scheme to the at least one server configured to apply the first operation. In response to determining that the first operation is incompatible with the first encryption scheme, the system: encrypts the data associated with the first operation using the second encryption scheme; and transmits the data encrypted by the second encryption scheme to the at least one server configured to apply the first operation.

Abstract: The invention relates to the field of computer engineering. The technical result consists in reducing the number of errors in the detection of breaches of remote examination regulations in automated proctoring systems. The technical result is achieved in that, if more than one breach is detected during an examination, a sum total of the weights of the detected breaches is determined and compared with at least one preset threshold value; a tip regarding the conduct of a student is returned, said tip indicating the extent to which said sum total of weights has reached the threshold value, wherein the weight of at least one breach is determined as the sum total of weights for said breach, detected in one or more modes from the following group: automatically detected, automatically detected and manually confirmed, and manually detected; wherein quantitatively differing weights are set for the same breach depending on which of the above-mentioned modes the breach was detected in.

Abstract: Disclosed herein are systems and methods for aggregating knowledge from a plurality specialized knowledge models (KMs). In one aspect, an exemplary method includes: receiving a query; analyzing the query to determine that the query is directed to different subject matter areas; selecting a plurality of specialized KMs each having respective expertise in one of the different subject matter areas of the query; generating a first sub-query directed to the first subject matter of the query and a second sub-query directed to the second subject matter of the query; transmitting the first sub-query for processing by the selected first specialized KM; obtaining a first response from the first specialized KM based on the first sub-query; transmitting the second sub-query and the first response from the first specialized KM for processing by the selected second specialized KM; and generating an aggregated response from the second specialized KM.

Abstract: Systems and methods for creating a training script on a virtual laboratory instance running in an e-learning infrastructure. The method comprises deploying a virtual laboratory instance from a template on e-learning infrastructure. The virtual laboratory instance includes preconfigured training software and an action interception tool. The method further comprises intercepting system events at the action interception tool corresponding to training software operation, pre-processing intercepted events by filtering and grouping events into an action-centric dataset, generating a training script using a machine learning model, based on an action-centric dataset, in a human-readable format, and storing the training script in a structured text-based format file.

Abstract: A system and method for performing brand detection in a video is disclosed herein. The method comprises receiving the video for performing the brand detection thereon; splitting the video for obtaining a plurality of video frames; performing an open set detection on each input video frame from the plurality of video frames, which comprises proposing one or more bounding boxes on the input video frames on regions of the video frame that potentially include brand media; cropping the one or more bounding boxes; providing the cropped bounding boxes to a classification module for obtaining embedding vectors corresponding to each of the cropped bounding boxes; and comparing the embedding vectors of the cropped bounding boxes with embedding vectors of one or more brand reference images provided by a user for computing instances of brand detection in each video frame of the plurality of video frames.

Abstract: Systems and methods for automatically enhancing the quality of images in the training set of a neural network NN. A method includes gaining access to a training set including a plurality of images. Using at least one image quality assessment method, at least one image is identified from a plurality of images in the training set, which matches a low-quality criterion as at least one low-quality image. At least one image enhancement method is used for enhancing the at least one low-quality image to obtain at least one enhanced image. The at least one low-quality image is replaced with the corresponding at least one enhanced image in the training set.

Abstract: System and method for administration of remote user activities interacting with critical data are used to detect violations of user activities, generate hints in response to each violation or a group of violations, that includes video-based violations, audio-based violation, and display-control-based violations, and to display hints to the administrator in a prioritized manner helping the administrator to react to most critical violations in a proper way. The invention solves a problem of simultaneous monitoring of multiple user interactions with critical data by ranking each violation, each session of interaction and each user.

Abstract: A system and a method for performing brand detection and brand analysis in a video are disclosed herein. The method comprises receiving the video for performing the brand detection thereon; splitting the video for obtaining input video frames; performing an open set detection on the input video frames to compute instances of detecting brand media; determining an exact square region in which the brand media is occupied within the input video frame; resolving a scene understanding task in the input video frame; detecting crucial moments in the video; identifying an area on the input frame where a user's attention is focused to provide user focus index; generating heat maps using the detection of crucial moments and user focus index; and combining above inputs from the brand detection and the scene understanding into the heat maps for all the input video frames of the video for computing a brand advertising rate.

Abstract: Systems and methods for generating video highlights with a certain label and a specific duration (SD) using a trained ranking neural network (RankNet). The system obtains a request for highlight generation, specific duration, and a specific label. The video is split into a set of fragments of pre-defined duration forming a sequence. Digital representation in a form of 3D spatio-temporal embedding is generated for each fragment by a spatio-temporal encoder. Using the embedding value, a rank of each fragment is identified by a trained Ranking Neural Network. Ranks are recorded into a data structure. A minimum number of fragments are selected to cover the SD using a criteria comprising comparing ranks of different fragments. A video highlight is generated from concatenated selected fragments with a truncation, if necessary.