Abstract: In a wireless network, a user equipment (UE) may support reflective quality of service (QoS), where QoS applied to uplink packets is implicitly derived from downlink packets. For example, when the UE receives a downlink packet that includes a reflective QoS (RQoS) indicator and a QoS flow identifier (QFI), the UE may apply the same QoS associated with the downlink packet to an uplink packet with one or more attributes that match the downlink packet. However, for a received downlink encapsulating security payload (ESP) packet that includes an RQoS indicator and a QFI, a modem cannot determine an uplink security parameters index (SPI) and downlink SPI pairing needed to enable RQoS because the uplink/downlink SPI pairing is known only by the upper layer. Accordingly, some aspects described herein enable the modem to learn uplink/downlink SPI pairings for ESP packets and thereby enable RQoS for ESP packets.

Abstract: Various aspects of the present disclosure generally relate to wireless communication. In some aspects, a user equipment (UE) may start, at a default data subscription (DDS) of the UE, a timer associated with a non-Third Generation Partnership Project (non-3GPP) tunnel over a cellular network based at least in part on a DDS switching at the UE. The UE may determine, at the DDS, that the non-3GPP tunnel over the cellular network is available prior to an expiry of the timer. The UE may perform a handover of a non-3GPP tunnel over data connection to the DDS based at least in part on the DDS switching at the UE and the non-3GPP tunnel over the cellular network being available prior to the expiry of the timer. Numerous other aspects are described.

Abstract: Aspects of the present disclosure provide apparatus, methods, processing systems, and computer readable mediums for updating QoS configurations at a user equipment (UE). An example method generally includes receiving, from a network entity, quality of service (QoS) information, a QoS identifier associated with the QoS information, and a bearer context associated with the QoS information in one of a modify bearer context request message, an activate default bearer context request message, or an activate dedicated bearer context request message; and updating a QoS configuration using the QoS information based on whether the UE is already configured with QoS information associated with the QoS identifier for a bearer context different from the bearer context associated with the QoS information received in the modify bearer context request message, activate default bearer context request message, or activate dedicated bearer context request message.

Abstract: Various aspects of the present disclosure generally relate to wireless communication. In some aspects, a user equipment (UE) may start, at a default data subscription (DDS) of the UE, a timer associated with a non-Third Generation Partnership Project (non-3GPP) tunnel over a cellular network based at least in part on a DDS switching at the UE. The UE may determine, at the DDS, that the non-3GPP tunnel over the cellular network is available prior to an expiry of the timer. The UE may perform a handover of a non-3GPP tunnel over data connection to the DDS based at least in part on the DDS switching at the UE and the non-3GPP tunnel over the cellular network being available prior to the expiry of the timer. Numerous other aspects are described.

Abstract: Disclosed techniques for image processing three-dimensional image data include: obtaining three-dimensional image data representing contiguous slices parallel to a plane, constructing training data from the image data by, for each of a plurality of angles: rotating the image data in the plane to produce rotated image data, blurring the rotated image data in a dimension parallel to the plane to produce low resolution rotated image data, and introducing aliasing into the low resolution rotated image data in the dimension parallel to the plane to produce aliased low resolution rotated image data, training an anti-aliasing neural network with the aliased low resolution image data and the low resolution image data, training a super-resolution neural network with the aliased low resolution image data and the rotated image data, and processing the image data using the trained anti-aliasing neural network and the trained super-resolution neural network to produce processed image data.

Abstract: A method for controlling a vehicle platoon includes determining whether a vehicle platoon is capable of safely passing through a weight-limited road section, generating segment information of the vehicle platoon when the vehicle platoon is incapable of safely passing through the weight-limited road section, and sending this information to a lead vehicle in the vehicle platoon. The lead vehicle can then segment the vehicle platoon based on the segment information.

Abstract: In a wireless network, a user equipment (UE) may support reflective quality of service (QoS), where QoS applied to uplink packets is implicitly derived from downlink packets. For example, when the UE receives a downlink packet that includes a reflective QoS (RQoS) indicator and a QoS flow identifier (QFI), the UE may apply the same QoS associated with the downlink packet to an uplink packet with one or more attributes that match the downlink packet. However, for a received downlink encapsulating security payload (ESP) packet that includes an RQoS indicator and a QFI, a modem cannot determine an uplink security parameters index (SPI) and downlink SPI pairing needed to enable RQoS because the uplink/downlink SPI pairing is known only by the upper layer. Accordingly, some aspects described herein enable the modem to learn uplink/downlink SPI pairings for ESP packets and thereby enable RQoS for ESP packets.

Abstract: The present disclosure relates to systems and methods for a multi-video stream transmission to a client terminal. The systems and methods may include obtaining a multi-video stream including a plurality of video streams, each video stream including multiple key frames characterized by a frame rate and a key frame interval. The systems and methods may include determining a delay time of an initial key frame for each video stream based on a plurality of frame rates and a plurality of key frame intervals of the plurality of video streams. The systems and methods may further include processing the plurality of video streams to determine a desired sending time of the initial key frame in the corresponding video streams based on the delay time of the initial key frame in each video stream. The systems and methods may further include transmitting the plurality of processed video streams to the client terminal.

Abstract: A method of wireless communication performed by a user equipment (UE) includes: operating in a Dual SIM Dual Active (DSDA) mode or a Dual SIM Dual Standby (DSDS) mode in which a first subscriber identity module (SIM) is designated as a default data subscription (DDS); determining a recommendation to change the DDS from the first SIM to a second SIM at a modem; informing a user of the recommendation to change the DDS; changing the DDS in response to, at least in part, the recommendation an input from the user; updating a first state variable to indicate a state of the DDS; and routing internet data to the second SIM.

Abstract: A communications method includes determining, by a first platoon member, at least one second platoon member, where the first platoon member and the at least one second platoon member belong to a same platoon, and signal quality of a communication link from the first platoon member to each second platoon member is less than a first preset quality threshold, determining, by the first platoon member, a target communications node, where signal quality of a communication link from the target communications node to each second platoon member is greater than or equal to the first preset quality threshold, and sending, by the first platoon member, to-be-sent data to each second platoon member through the target communications node.

Abstract: Apparatuses, systems, and techniques are presented to predict annotations for objects in images. In at least one embodiment, boundaries of an object within an image can be identified based, at least in part, on a user-generated outline of only a portion of this object or information about a size of this object provided by a user.

Abstract: Apparatuses, systems, and techniques to generate one or more images of an object. In at least one embodiment, a technique includes training one or more neural networks to generate one or more images of an object from at least a first image of the object and a second lower-resolution image of the object, where the training includes a comparison of the one or more generated images of the object with the second lower-resolution image of the object.

Abstract: Aspects of the present disclosure provide apparatus, methods, processing systems, and computer readable mediums for updating QoS configurations at a user equipment (UE). An example method generally includes receiving, from a network entity, quality of service (QoS) information, a QoS identifier associated with the QoS information, and a bearer context associated with the QoS information in one of a modify bearer context request message, an activate default bearer context request message, or an activate dedicated bearer context request message; and updating a QoS configuration using the QoS information based on whether the UE is already configured with QoS information associated with the QoS identifier for a bearer context different from the bearer context associated with the QoS information received in the modify bearer context request message, activate default bearer context request message, or activate dedicated bearer context request message.

Abstract: Aspects of the present disclosure provide apparatus, methods, processing systems, and computer readable mediums for updating QoS configurations at a user equipment (UE). An example method generally includes receiving, from a network entity, quality of service (QoS) information, a QoS identifier associated with the QoS information, and a bearer context associated with the QoS information in one of a modify bearer context request message, an activate default bearer context request message, or an activate dedicated bearer context request message; and updating a QoS configuration using the QoS information based on whether the UE is already configured with QoS information associated with the QoS identifier for a bearer context different from the bearer context associated with the QoS information received in the modify bearer context request message, activate default bearer context request message, or activate dedicated bearer context request message.

Abstract: Disclosed are a peptide amide compound composition, a preparation method therefor and medical use thereof. Specifically, the composition contains a compound of formula (I) and pH regulators, and the pH of the solution thereof is 3-5.5. The composition is stable and requires few excipients, and is stable in clinical use.

Abstract: Various aspects of the present disclosure generally relate to wireless communication. In some aspects, a user equipment (UE) may establish a first communication connection associated with a first subscription or associated with a first network slice, wherein the first communication connection is a default connection for the UE for data traffic. The UE may establish a second communication connection associated with a second subscription or associated with a second network slice. The UE may receive, from a device via a wireless local area network provided by the UE or via a wired connection, a data traffic packet associated with one or more parameters. The UE may route the data traffic packet to the second communication connection based at least in part on the one or more parameters. The UE may transmit the data traffic packet using the second communication connection. Numerous other aspects are described.

Abstract: In some aspects, a user equipment (UE) may communicate using a first radio access technology (RAT) for a first subscription of the UE, wherein the first RAT is selected from a group that includes a first cellular RAT associated with the first subscription, a second cellular RAT associated with a second subscription of the UE, and a wireless local area network (WLAN) RAT. The UE may communicate using a second RAT for the second subscription of the UE, wherein the second RAT is selected from the group that includes the first cellular RAT associated with the first subscription, the second cellular RAT associated with the second subscription of the UE, and the WLAN RAT. The UE may transition, based at least in part on a condition, a communication link carrying a protocol data unit (PDU) session from the second subscription to the first subscription. Numerous other aspects are described.

Abstract: Apparatuses, systems, and techniques to select a neural network using an amount of memory to be used. In at least one embodiment, a processor includes one or more circuits to cause one or more neural networks to be selected from a plurality of neural networks based, at least in part, on an amount of memory to be used by the one oe more neural networks.

Abstract: Various aspects of the present disclosure generally relate to wireless communication. In some aspects, a user equipment (UE) may configure a first channel associated with a first subscriber identity module (SIM), the first SIM associated with data traffic. The UE may configure a second channel associated with a second SIM in a dual SIM dual active (DSDA) mode. The UE may detect, on the second channel, a subscription related data stream that includes voice call traffic. The UE may determine, based on detecting the subscription related data stream, to switch the data traffic from the first SIM to the second SIM based at least in part on a UE operation mode. The UE may switch the data traffic from the first SIM to the second SIM based at least in part on the determination to switch the data traffic. Numerous other aspects are described.

Abstract: Apparatuses, systems, and techniques to generate an optimized neural network architecture. In at least one embodiment, various neural network components are used to generate one or more neural network configurations, and each neural network configuration is trained in order to determine an optimal neural network architecture for a training dataset.