Abstract: Systems and methods for active speaker detection for videoconferencing are provided. For example, an audio recording system can record a set of raw audio signals. The set of raw audio signals include audio signals recorded by a set of microphones at different distances from an audio source with different orientations. An audio dataset generation system can access a virtual meeting room setup which specifies microphones used in a virtual meeting room, locations of speakers and the microphones, and orientations of the speakers. The audio dataset generation system generates a synthetic audio signal for each of the speakers specified in the virtual meeting room setup by combining audio signals selected from the set of raw audio signals according to the virtual meeting room setup.

Abstract: An AI image processing system is provided. The system is configured to receive latent parameters defining representations of attributes of an object in an image. The latent parameters include subsets of latent parameters, and each latent parameter subset corresponds to one attribute. The system is configured to produce a joint encoding of the latent parameters and produce an implicit 3D model of the object based on the joint encoding. The implicit 3D model defines a volumetric representation for each 3D location in the scene with respect to an input viewing direction. The volumetric representation defines a signed distance value and/or an optical density, and a color and/or a feature vector. The system is configured to render a 2D image of the scene including the object viewed from the input viewing direction based on the produced volumetric representations for different 3D locations in the scene.

Abstract: A method for moderating an anonymous discussion is described. The method includes hosting the anonymous discussion among a plurality of participants and a moderator. During the anonymous discussion, the moderator is provided with contribution analysis for each of the plurality of participants, the contribution analysis indicating a participation level for the associated participant. After the anonymous discussion, each participant's contribution is analyzed to determine whether the participant has met contribution criteria. The discussion is stored as anonymized text data and can be evaluated to find topics of interest and participant sentiment.

Abstract: The present disclosure provides a feedback control system for optimizing performance of a grid-interactive building (GIB) system that is configured to condition an indoor environment of a building. The feedback control system comprises a time-series foundation model configured to predict disturbances affecting energy consumption of the building; and a stochastic feedback controller configured to: determine control inputs for the GIB system by evaluating multiple control actions for the GIB system based on the predicted disturbances, wherein the control inputs maximize a likelihood of achieving desired indoor environmental conditions while minimizing the energy consumption.

Abstract: Embodiments of the present disclosure disclose a method and a system for training a neural network for generating universal adversarial perturbations. The method includes collecting a plurality of data samples. Each of the plurality of data samples is identified by a label from a finite set of labels. The method includes training a probabilistic neural network for transforming the plurality of data samples into a corresponding plurality of perturbed data samples having a bounded probability of deviation from the plurality of data samples by maximizing a conditional entropy of the finite set of labels of the plurality of data samples conditioned on the plurality of perturbed data samples. The conditional entropy is unknown. The probabilistic neural network is trained based on an iterative estimation of a gradient of the unknown conditional entropy of labels. The method further includes generating the universal adversarial perturbations based on the trained probabilistic neural network.

Abstract: A reconfigurable device is provided for splitting optical beams. The device includes an input port configured to receive an input beam including at least two primary wavelengths, a tunable splitter configured to separate the input beam into at least two beams via at least two routes corresponding to the at least two primary wavelengths, wherein each of the at least two routes is configured to propagate one of the at least two primary wavelengths of the input beam, wherein the tunable splitter includes a bottom electrode, a substrate on the bottom electrode, core segments arranged on the substrate, a top layer, support segments to connect the substrate and the top layer, a top electrode on the top layer, a controllable refractive index layer arranged to fill gaps between the substrate, the support segments, and the top layer; and at least two output ports configured to transmit the at least two beams propagated via the at least two routes.

Abstract: Communication-capable devices such as commercial Wi-Fi devices can be used for integrated sensing and communications (ISAC) systems to jointly exchange data and monitor environment. Such devices typically require diverse signal processing such as machine learning inference that demands high-power operations for real-time sensing and computing. The present invention provides a way to realize energy-efficient computing by exploiting the capability of data communications to access distributed computing resources including classical computers and quantum computers over networks. The system and method are based on the realization that computationally intensive processing is offloaded to networked hybrid classical-quantum computing to build dynamic computing graphs. Some embodiments use automated classical-quantum machine learning whose circuits and hyperparameters are automatically adjusted via gradient or heuristic optimization for Wi-Fi indoor monitoring and human tracking.

Abstract: A cavity filter includes a housing, an input resonator and an output resonator. The input resonator includes a first sheet resonant body, an input end extending outward from one side of the first sheet resonant body and a first branch extending outward from the first sheet resonant body and/or the input end, and the input end extends out of the housing through the input through hole. The output resonator includes a second sheet resonant body, an output end extending outward from one side of the second sheet resonant body, and a second branch extending outward from the second sheet resonant body and/or the output end, and the output end extends out of the housing through the output through hole. The lengths of the first branch and the second branch are both a quarter wavelength of a resonant frequency of the cavity filter.

Abstract: An antenna detection circuit and method, an in-vehicle device, and a vehicle are provided, relate to the field of communication technologies, and are used to improve antenna detection accuracy and device safety. The antenna detection circuit includes a controller (10), a switch circuit (20), and an in-position detection circuit (30).

Abstract: A system and a computer-implemented method using physics-informed neural network (PINN) are provided for data communications. At a transmitter, the method is configured to acquire source data to be transmitted, encode the source data to codewords based on forward error correction (FEC) codes, map the codewords to amplitude symbols, modify the mapped amplitude symbols to pre-equalized symbols including pre-distort channel impairments symbols based on a predetermined physical model, and transmit digital data of the pre-equalized symbols over a channel as channel data.

Abstract: Method and system for phase detecting of hybrid wye-connected and delta-connected loads in an unbalanced power distribution system. A data-driven event-triggered phase identification algorithm is presented in which the exceeding current fluctuation events are used to build the relationship between the feeder head and the undetermined phase load and mutual information index is used to assess the dependence level of the feeder head on the undetermined phase load. The connected and non-connected phase of wye-connected and delta-connected single-phase load are determined as the phase having highest and lowest dependences of the phases of feeder head on the load, respectively.

Abstract: A magnetic fluid micropump includes an annular flow channel, a fixed magnetic assembly and a driving magnetic assembly. A magnetic fluid is provided inside the annular flow channel. The fixed magnetic assembly is arranged outside the annular flow channel in a stationary manner so that a part of the magnetic fluid is attracted and fixated in the annular flow channel to form a magnetic fluid valve. An inlet tube and an outlet tube that are in communication with the annular flow channel are respectively provided on both sides of the fixed magnetic assembly along a path of the annular flow channel. The driving magnetic assembly is arranged outside the annular flow channel and configured to move along the path of the annular flow channel, so that another part of the magnetic fluid moves along the annular flow channel to form a magnetic fluid piston.

Abstract: The present disclosure provides a method and a system for training a neural network suitable for localization of a device within an environment based on signals received by the device. The method comprises training a bi-regressor neural network to identify locations from labeled data, wherein the bi-regressor neural network includes a feature extractor and a bi-regressor including two regressors; training parameters of the bi-regressor using the labeled data and unlabeled data, such that each of the two regressors identifies the same labeled locations while processing the labeled data and identifies different locations while processing the unlabeled data; and training parameters of the feature extractor using an adversarial discriminator to extract domain invariant features from the unlabeled data with statistical properties of the labeled data according to the adversarial discriminator such that each of the two regressors identifies the same locations while processing the domain invariant features.

Abstract: Various example embodiments described herein provide for systems, methods, devices, instructions, and the like for suffix-based speculative token decoding for an artificial intelligence model, such as a language model (e.g., large language model). In particular, some example embodiments provide an AI model system with hybrid speculative token decoding, which combines suffix-based speculative token decoding with a draft AI model approach to speculative token decoding. With this hybrid decoding approach, various example embodiments can accelerate inference throughput while adapting to different types of workloads, particularly agentic applications that exhibit repetitive token generation patterns.

Abstract: A method, computer program product, and computer system for finding outliers in multi-dimensional time series samples. Each time series sample is divided into at least 2 sub samples having equal time duration. At least one prediction model is pre-trained using the sub samples and a prediction result for each sub sample for each prediction model is obtained by executing the pre-trained prediction models with the time series samples as input. A Shapely value corresponding to each prediction result is sub samples for each prediction model to generate multiple clusters of Shapely values for each prediction model. Highest ranking Shapely value outliers are determined from analysis of the multiple clusters. Highest ranking outlier sub samples corresponding to the highest ranking Shapely value outliers are identified.

Abstract: A semiconductor structure and a method for forming same. The structure includes: a base substrate; a gate structure, located on the base substrate; a drift region, located in the base substrate on one side of the gate structure; a body region, located in the base substrate on the other side of the gate structure; a drain region, located in the drift region on one side of the gate structure; a source region, located in the body region on the other side of the gate structure; and a floating field plate, located on the drift region between the gate structure and the drain region, where the floating field plate has notches arranged at intervals along a width direction of the gate structure, and the floating field plate also has notches arranged at intervals along a length direction of the gate structure.

Abstract: A method, computer system, and program product facilitate identification of error image labels in training data. The method comprises: evenly dividing a training dataset into N subsets, where the training dataset includes M data items each comprising a pair of image and its original image label; training a prediction model to label images by respectively using each of the N subsets as training data to generate N respective trained prediction models; respectively using each of the N trained prediction models trained by using one of the N subsets as training data to label the images in other N?1 subsets of the N subsets to generate N?1 prediction labels for each of the M images in the training dataset. For each image in the M data items, whether the original image label of the image is a potential error image label is based on the N?1 prediction labels of the image.

Abstract: A cavity filter includes a housing, an input resonator and an output resonator. The input resonator includes a first sheet-like resonant body, an input end extending outward from one side of the first sheet-like resonance body and a first branch extending outward from the first sheet-like resonance body and/or the input end, and the input end extends out of the housing through the input through hole. The output resonator includes a second sheet-like resonant body, an output end extending outward from one side of the second sheet-like resonance body, and a second branch extending outward from the second sheet-like resonance body and/or the output end, and the output end extends out of the housing through the output through hole. The lengths of the first branch and the second branch are both a quarter wavelength of a resonant frequency of the cavity filter.

Abstract: Embodiments disclose a method and a system for robust transformation of input with a neural network. The method comprises processing the input data with a variational neural network (VNN) trained with ML to produce static parameters including noise level for the input data, injecting a set of random noises sampled on a probabilistic distribution according to the statistic parameters defined by the VNN to produce a set of perturbed input samples. The method comprises processing each of the set of perturbed input samples with a transformation neural network to produce a set of transformations and outputting a combination of the set of transformations as the robust transformation of the input data. Some embodiments consider training the variational neural network and transformation neural network by using adversarial examples from an attack model via alternating, explicit, and implicit gradient frameworks.

Abstract: A magnetic fluid micropump includes an annular flow channel, a fixed magnetic assembly and a driving magnetic assembly. A magnetic fluid is provided inside the annular flow channel. The fixed magnetic assembly is arranged outside the annular flow channel in a stationary manner so that a part of the magnetic fluid is attracted and fixated in the annular flow channel to form a magnetic fluid valve. An inlet tube and an outlet tube that are in communication with the annular flow channel are respectively provided on both sides of the fixed magnetic assembly along a path of the annular flow channel. The driving magnetic assembly is arranged outside the annular flow channel and configured to move along the path of the annular flow channel, so that another part of the magnetic fluid moves along the annular flow channel to form a magnetic fluid piston.