Abstract: A device includes a memory configured to store images representing scenes associated with a vehicle. The device includes one or more processors configured to obtain a set of images representing a scene associated with the vehicle. The one or more processors are configured to generate, based on the set of images, language-grounded scene tokens. The one or more processors are configured to provide the language-grounded scene tokens to a planning transformer to generate a path plan prediction for the vehicle.

Abstract: Examples relate to item pick-ability scores, that is whether an item is available to be picked from the node. An example may involve receiving a recommendation request regarding an order for at least one item; determining, based on the recommendation request, feature data and at least one node in a retail fulfillment network of a retailer; computing, for each item in the order and each node of the at least one node, a pick-ability score using at least one machine learning model based on the feature data, wherein the pick-ability score indicates a probability that the item is available to be picked from the node in a future time period for fulfilling the order; generating, based on the pick-ability score, recommendation data for fulfilling the order; and transmitting the recommendation data to a computing device.

Abstract: Systems and techniques are provided for generating depth information from one or more images. For example, a process can include obtaining a first depth map corresponding to an input comprising an image of the one or more images and a sparse depth measurement. A three-dimensional (3D) point cloud can be generated based on the first depth map and multi-scale visual features of the input, wherein the 3D point cloud includes a plurality of 3D point features uplifted from the multi-scale visual features. At least a portion of the plurality of 3D point features can be processed using one or more self-attention layers to generate refined 3D point features. A two-dimensional (2D) projection of the refined 3D point features can be generated and a second depth map can be generated based on the 2D projection of the refined 3D point features.

Abstract: A method of question answering using enhanced retrieval-augmented generation according to an embodiment includes receiving, by a computing system, a user query, pre-processing, by the computing system, the user query to determine whether the user query is associated with malicious intent, retrieving, by the computing system, relevant data from a knowledge base by using a keyword index and a semantic index in response to determining that the user query is not associated with malicious intent, prompting, by the computing system, a large language model to generate an answer to the user query based on only the relevant data retrieved from the knowledge base, and receiving, by the computing system, the answer to the user query from the large language model in response to the prompt.

Abstract: A method for efficient identification of knowledge base data to support interactions in a contact center may include identifying a query associated with a contemporaneous interaction between a client and an agent of a contact center and performing a search of a knowledge base to determine a set of one or more relevant documents responsive to the identified query, including ranking a set of resultant documents from the knowledge base as a function of a vector-based similarity determination in which each resultant document and the identified query is represented with a corresponding embedding. Additionally, the method may include identifying, with a transformer-based artificial intelligence model, a subset of content within each relevant document as being most pertinent to the identified query and visually demarcating the identified subset of each relevant document from other content of the relevant document in a user interface as the interaction occurs.

Abstract: The present invention provides the sterilization of an ophthalmic composition comprising timolol or salt thereof optionally with pharmaceutically acceptable agent(s) wherein the sterilization is achieved through aseptic filtration technique. Further the present invention provides the sterilization process by optimising the process parameters by varying the heating time at a temperature to control the viscosity of the ophthalmic composition of present invention through aseptic filtration technique wherein the filtration is done under aseptic condition through 0.45 ?m clarification pre-filter followed by 0.2? sterilizing grade filter. The process is simple and economical.

Abstract: Certain aspects of the present disclosure provide techniques and apparatus for processing data using a transformer neural network. The method generally includes generating, via a first attention layer of a machine learning model, a first attention map based on an input into the machine learning model; identifying, using a token prediction model, a first subset of tokens in the first attention map more relevant to a second attention layer of the machine learning model and a second subset of tokens in the first attention map less relevant to the second attention layer of the machine learning model; generating, via the second attention layer of the machine learning model, a second attention map based on the first subset of tokens in the first attention map; and generating an inference based on the second attention map and the second subset of tokens in the first attention map.

Abstract: Certain aspects of the present disclosure provide techniques for implementing polynomial based transformer mechanisms for transforming an input tensor that includes storing the input tensor; inputting the input tensor into a transformer of a machine learning (ML) model; generating, by the transformer, one or more transformed matrices based on the input tensor; generating, by the transformer, a plurality of homogenous polynomials based on the one or more transformed matrices; generating, by the transformer, an output polynomial comprising a linear combination of the plurality of homogenous polynomials; and performing, by the ML model, one or more operations based on the output polynomial.

Abstract: A method includes adjusting a temperature of a liquid; after adjusting the temperature of the liquid, dispensing the liquid onto a backside of a wafer by progressively moving a dispensing position from a center of the wafer toward a peripheral edge of the wafer; etching a target layer on a front side of the wafer using an etchant.

Abstract: A multiplexed single-photon generator includes a plurality of single-photon sources, an optical switching network controllable to couple pump light into any one of the single-photon sources, and a bus waveguide optical coupled to all of the single-photon sources. Each single-photon source includes a quantum emitter coupled to an optical cavity. All of the single photons emitted by all of the single-photon sources propagate along the bus waveguide. The single-photon generator may be time-multiplexed in which only one of the single-photon sources is pumped at any time. In this case, the single photons form a temporal sequence with little or no temporal overlap. As an alternative to time multiplexing, the single-photon generator may be frequency-multiplexed such that each single-photon source emits single photons that are distinguishable from the other emitted single photons based on optical frequency.

Abstract: A method includes rotating a wafer, dispensing a liquid from a center of the wafer to a peripheral edge of the wafer to control a temperature of the wafer, and etching an etch layer of the wafer with an etchant during or after dispensing the liquid. The liquid is dispensed through a nozzle.

Abstract: Certain aspects of the present disclosure provide techniques and apparatus for efficient inferencing using machine learning models and learned normalizing constants. An example method generally includes receiving an input for processing using a machine learning model. The input is normalized based on one or more defined constants associated with characteristics learned from a training data set used in training the machine learning model. An inference is generated for the input based on the normalized input, and one or more actions are taken based on the generated inference.

Abstract: Systems and techniques are provided for generating depth information from one or more images. For example, a process can include obtaining a first depth map corresponding to an input comprising an image of the one or more images and a sparse depth measurement. A three-dimensional (3D) point cloud can be generated based on the first depth map and multi-scale visual features of the input, wherein the 3D point cloud includes a plurality of 3D point features uplifted from the multi-scale visual features. At least a portion of the plurality of 3D point features can be processed using one or more self-attention layers to generate refined 3D point features. A two-dimensional (2D) projection of the refined 3D point features can be generated and a second depth map can be generated based on the 2D projection of the refined 3D point features.

Abstract: Systems and techniques are provided for generating depth information. For example, a process can include obtaining a first feature volume including visual features corresponding to each respective frame included in a first set of frames. A first query generator network can generate reconstruction features associated with a reconstructed feature volume corresponding to the first feature volume. Based on the first feature volume, a second query generator network can generate motion features associated with predicted future motion corresponding to the first feature volume. An initial depth prediction can be generated for each respective frame based on cross-attention between features of a depth prediction decoder, the reconstruction features, and the motion features. A refined depth prediction can be generated for each respective based on cross-attention between the initial depth prediction, the reconstruction features, and the motion features.

Abstract: A processor-implemented method for image or text processing includes receiving, by an artificial neural network (ANN) model, a set of tokens corresponding to an input. A token interaction block of the ANN model processes the set of tokens according to each channel of the input to generate a spatial mixture of a set of features for each channel of the input. A feed forward network block of the ANN model generates a mixture of channel features based on the spatial mixture of the set of features for each channel of the input. An attention block of the ANN model determines a set of attended features of the mixture of channel features according to a set of attention weights. In turn, the ANN model generates an inference based on the set of attend features of the mixture of channel features.

Abstract: Certain aspects of the present disclosure provide techniques and apparatus for improved machine learning. A transformed version of image pixels is accessed as input to an attention layer of a machine learning model. A number of local attention operations to apply, in one transformer, to the transformed version of image pixels is selected based at least in part on a size of the transformed version of image pixels. A transformer output for the attention layer of the machine learning model is generated based on applying the number of local attention operations and at least one global attention operation to the transformed version of image pixels.

Abstract: Systems and techniques are provided for processing image data. According to some aspects, a computing device can generate a gradient (e.g., a classifier gradient using a trained classifier) associated with a current sample. The computing device can combine the gradient with an iterative model estimated score function or data associated with the current sample to generate a score function estimate. The computing device can predict, using the diffusion machine learning model and based on the score function estimate, a new sample.

Abstract: Techniques for ripple-type control of networked physical systems such as power systems, water systems, and others are provided. As one example, a device includes at least one processor configured to determine, for a first controllable device in a system, based on a measurement of an output parameter and a minimum output parameter value, an output violation value for the first device. The processor is further configured to determine, based on a present input value for the first device, the output violation value, and an assistance requisition value corresponding to a second device, a target input value for the first device. The processor is further configured to cause the first controllable device to modify operation based on the target input value and a maximum input value for the first controllable device.

Abstract: As described herein, a system, method, and computer program are provided for proactive 5G leg estimation. During an initial access procedure by a user equipment on a 4G leg of a 4G-LTE network, an eNodeB of the 4G-LTE network computes a parameter for the user equipment. Further, the eNodeB of the 4G-LTE network conditionally allows an addition of a 5G leg to the 4G-LTE network for the user equipment, based on the parameter computed for the user equipment.

Abstract: A device may calculate a reactive power setpoint associated with a distributed energy resource (DER) electrically coupled to a power distribution network, based on a local voltage value associated with the DER. The device may control a reactive power output of the DER in association with regulating voltage at the power distribution network, based on the reactive power setpoint.