Abstract: Disclosed are mechanisms for selecting a recommended item for a current item being viewed by a user account based on a view history of the user account with reduced bias. For a current item being viewed by the user account represented by a current node of a co-watch graph, embodiments can select a recommended item represented by an associated node in the co-watch graph likely being viewed by the user account, and determine a probability of the recommended item likely being viewed. The co-watch graph can be generated based on a view history of the user account. An edge between a first node and a second node of the co-watch graph can have a weight representing a number of co-occurrence times when the first item represented by the first node and the second item represented by the second node are viewed in sequence within a predetermined time interval.

Abstract: A packet cache system includes a cache memory allocator for receiving a memory address corresponding to a non-cache memory and allocated to a packet, and associating the memory address with a cache memory address; a hash table for storing the memory address and the cache memory address, with the memory address as a key and the cache memory address as a value; a cache memory for storing the packet at a location indicated by the cache memory address; and an eviction engine for determining one or more cached packets to remove from the cache memory and place in the non-cache memory when occupancy of the cache memory is high.

Abstract: A method includes obtaining statistical information of incoming network traffic. The method also includes using a state machine to classify the incoming network traffic as a traffic pattern based on the statistical information. The method further includes using the traffic pattern to adapt one or more Target Wakeup Time (TWT) parameters to optimize power consumption of a Wi-Fi station. The traffic pattern includes at least one of bursty traffic, random traffic, and stable traffic.

Abstract: This disclosure provides systems, methods, and apparatuses for associating a wireless communication device such as a wireless station (STA) of a STA multi-link device (MLD) with an access point (AP) MLD that includes a first AP associated with a first communication link of the AP MLD and includes one or more secondary APs associated with one or more respective secondary communication links of the first AP MLD. The first AP includes one or more virtual APs, and the first AP and the one or more virtual APs of the first AP belong to a first multiple basic service set identifier (BSSID) set associated with the first communication link.

Abstract: One embodiment provides for a graphics processing unit to accelerate machine-learning operations, the graphics processing unit comprising a multiprocessor having a single instruction, multiple thread (SIMT) architecture, the multiprocessor to execute at least one single instruction; and a first compute unit included within the multiprocessor, the at least one single instruction to cause the first compute unit to perform a two-dimensional matrix multiply and accumulate operation, wherein to perform the two-dimensional matrix multiply and accumulate operation includes to compute an intermediate product of 16-bit operands and to compute a 32-bit sum based on the intermediate product.

Abstract: A correlation engine and policy manager (CPE) system includes: a persistent database, a cache database, an event gate, an event enricher, an event transformer, and an event dispatcher. The event gate obtains event data from at least one event source, and forwards the event data to the event enricher. The event enricher enriches the event data with additional data in the cached business layer data of the cache database, and forwards the enriched event data to the event transformer. The event transformer applies one or more policies in a cached business layer data of the cache database to the enriched event data to obtain transformed event data, and outputs the transformed event data to be stored in the persistent database. The event dispatcher dispatches output data to cause or prompt an action responsive to the transformed event data satisfying the at least one policy.

Abstract: A gate driver circuit includes first through third transistors, a first voltage clamp, and control logic. The first transistor has a first control input and first and second current terminals. The first current terminal couples to a first voltage terminal. The first voltage clamp couples between the first voltage terminal and the first control input. The second transistor couples between the first control input and the second voltage terminal. The third transistor couples between the first control input and the second voltage terminal. The third transistor is smaller than the second transistor. The control logic is configured to turn on both the second and third transistors to thereby turn on the first transistor, and the first control logic configured to turn off the second transistor after the first transistor turns on while maintaining in an on-state the third transistor to maintain the first transistor in the on-state.

Abstract: An autonomous vehicle computing system can include a primary perception system configured to receive a plurality of sensor data points as input generate primary perception data representing a plurality of classifiable objects and a plurality of paths representing tracked motion of the plurality of classifiable objects. The autonomous vehicle computing system can include a secondary perception system configured to receive the plurality of sensor data points as input, cluster a subset of the plurality of sensor data points of the sensor data to generate one or more sensor data point clusters representing one or more unclassifiable objects that are not classifiable by the primary perception system, and generate secondary path data representing tracked motion of the one or more unclassifiable objects. The autonomous vehicle computing system can generate fused perception data based on the primary perception data and the one or more unclassifiable objects.

Abstract: This disclosure provides systems, methods, and apparatuses for wireless communication that can be used to establish a restricted target wake time (TWT) session on a wireless medium. In some implementations, an access point (AP) establishes a restricted TWT session for one or more wireless stations (STAs) associated with latency sensitive traffic, the restricted TWT session including restricted TWT service periods (SPs) during which the AP reserves access to the wireless medium for only the one or more STAs associated with the latency sensitive traffic. The AP transmits a clear-to-send (CTS) frame at a start of each restricted TWT SP, the CTS frame indicating to other STAs that the wireless medium is unavailable for a duration of the respective restricted TWT SP. The AP transmits latency sensitive data to or receives latency sensitive data from the one or more STAs during at least one of the restricted TWT SPs.

Abstract: A semiconductor device and a method for manufacturing thereof. A substrate is provided. One or more groups of layers are formed on top of the substrate. A compensation layer is formed on top of at least one group of layers. At least one silicon layer is formed on top of the compensation layer. At least a portion of one or more layers in the one or more groups of layers is etched. The semiconductor device is formed.

Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media, for training a generative neural network. One of the methods includes training a generative neural network by performing a sequence of a plurality training stages each generating an expanded training data set. The method also involves performing a sequence of improve steps, each comprising training the generative neural network on the training examples in a corresponding subset of the expanded training data set.

Abstract: A method and device for reducing measurement error/s is provided. The method receives a file by an engineering tool from a system configurator tool and parses the file to identify a value associated with a transformer setting for a process bus device. The method fetches information from installation data to identify the value when the value is not identified in the file and stores the value in the engineering tool when the value is identified in the file or in the information. The method marks the value as a missing value to visually notify a technician when the value is not identified in the information or the file. The method publishes the value at a remote database for process bus subscriber device/s.

Abstract: A method for providing a personalized shopping experience using an AI-guided omnichannel shopping application is provided. The method includes presenting a user app interface on a user device associated with a user to receive user data comprising user styling preferences, shopping habits, and images of the user's personal wardrobe inventory. The method also includes providing a virtual closet for the user, wherein the virtual closet comprises processed images of the personal wardrobe inventory of the user. The method further includes providing a personalized product feed source by filtering product data. The method additionally includes providing a personal stylist interface that allows stylists to access the virtual closet of the user. The method includes analyzing using an AI model, the user preferences and shopping habits, sales history, browsing history, and the selected items, wherein the AI model continuously learns and generating personalized product recommendations to the user.

Abstract: Embodiments are generally directed to compression for compression for sparse data structures utilizing mode search approximation. An embodiment of an apparatus includes one or more processors including a graphics processor to process data; and a memory for storage of data, including compressed data. The one or more processors are to provide for compression of a data structure, including identification of a mode in the data structure, the data structure including a plurality of values and the mode being a most repeated value in a data structure, wherein identification of the mode includes application of a mode approximation operation, and encoding of an output vector to include the identified mode, a significance map to indicate locations at which the mode is present in the data structure, and remaining uncompressed data from the data structure.

Abstract: A system for utilizing media content reference point information to perform media content encoding, and supplemental content stitching and/or insertion. Media content can be encoded and packaged based on boundaries of the media content. The boundaries can be received from a third-party and/or generated via an automated process. Target boundaries can be selected based on accuracy levels associated with the received and/or generated boundaries. Supplemental content can be stitched and/or inserted into packaged media content based on audio and video content of the packaged media content being aligned.

Abstract: Systems, apparatuses and methods may provide for technology that selects an anti-aliasing mode for a vertex of a primitive based on a parameter associated with the vertex and generates a coverage mask based on the selected anti-aliasing mode. Additionally, one or more pixels corresponding to the vertex may be shaded based at least partly on the coverage mask, wherein the selected anti-aliasing mode varies across a plurality of vertices in the primitive.

Abstract: In some implementations, an access point (AP) establishes a restricted target wake time (TWT) session including at least one restricted TWT service period (SP) for peer-to-peer (P2P) communications. The AP admits a group of wireless stations (STAs) associated with P2P communications as members of the restricted TWT session, obtains a transmission opportunity (TXOP) on the wireless channel during the at least one restricted TWT SP, and transmits, on the wireless channel, a protection frame identifying one or more STAs of the group of STAs belonging to the restricted TWT session that are permitted to transmit or receive P2P communications on the wireless channel during the TXOP. The protection frame may also indicate to receiving devices other than the one or more identified STAs that the wireless channel is unavailable for at least a portion of the TXOP.

Abstract: An apparatus to facilitate thread scheduling is disclosed. The apparatus includes logic to store barrier usage data based on a magnitude of barrier messages in an application kernel and a scheduler to schedule execution of threads across a plurality of multiprocessors based on the barrier usage data.

Abstract: Systems and methods for training a generative neural radiance field model can include geometric regularization. Geometric regularization can involve the utilization of reference geometry data and/or an output of a surface prediction model. The geometry regularization can train the generative neural radiance field model to mitigate artifact generation by limiting a distribution considered for color value prediction and density value prediction to a range associated with a realistic geometry range.

Abstract: This disclosure describes systems, methods, and devices for remotely controlling device settings for collaboration sessions. A device may identify an alphanumeric handle based on a location identifier of a first location associated with the device and a collaboration session identifier for a collaboration session of a collaboration application executed by the device; generate a Bluetooth Low Energy (BLE) advertising packet including a header and a payload, the header including the alphanumeric handle and a hardware identifier that identifies the device; transmit the BLE advertising packet; identify an authentication request received from a second device in the collaboration session, the authentication request including the alphanumeric handle; authenticate the second device based on the alphanumeric handle; and transmit a BLE notification packet including an indication of a volume at which the second device is to set a speaker for the collaboration session.