Abstract: Some embodiments of the present disclosure relate to the selection of a waveform for an integrated communications and sensing (ICS) signal, where the waveform is suitable for both communication applications and sensing applications. In view of the sensing applications, the waveform selection can be, at least in part, adapted based on capabilities of hardware of nodes involved in the sensing applications. In view of the communication applications, the waveform selection can be, at least in part, adapted based on the extent to which data is to be embedded.

Abstract: Aspects of the present application provide a system with a RIS panel with a unique geometrical shape surface, two RIS panels, also referred to as an RIS-pair, or a group of more than two RIS panels that are jointly controlled to aid wireless communication coverage holes.

Abstract: Aspects of the present disclosure relate to a reference signal assignment, in which reference signals for a first apparatus may be assigned based on second channel estimates for one or more second apparatus having a same location and network resource configuration as the first apparatus.

Abstract: This application provides a model training method and apparatus. The method includes: A first processing node obtains at least one first model; the first processing node processes the at least one first model to generate a first common model; and the first processing node determines a second processing node, where the second processing node is a processing node for a next round of model processing, and the first common model is obtained by the second processing node before the next round of model processing. In technical solutions provided in this application, before the next round of model processing, a processing node for the next round of model processing may be determined based on an actual requirement, to adapt to a change of an application scenario.

Abstract: Aspects of the present disclosure relate to inference and, in particular, to distributed inference representative of a machine learning process. It is expected that inferencing will be a service in wireless networks. Aspects of the present application relate to applying aspects of coding theory to distributed inference to introduce redundancy. Methods of decoding outputs from a distributed inference process are also provided.

Abstract: Embodiments of this application relate to the field of communications technologies, and provide an encoding and decoding method and apparatus, to reduce encoding/decoding complexity and improve encoding/decoding performance. In the method, a transmit device may obtain N to-be-encoded vectors. The transmit device may encode the N to-be-encoded vectors based on a polar code kernel matrix, to obtain N temporary code blocks. The transmit device may respectively perform a mask operation on target bit sequences in an (n+1)th temporary code block to an (n+M)th temporary code block and a source bit sequence segment of an nth temporary code block, to obtain M mask bit sequences. The transmit device may respectively encode the M mask bit sequences based on the polar kernel matrix, to obtain M encoded mask bit sequences. The transmit device may sum the M encoded mask bit sequences and M temporary code blocks, to obtain M first code blocks.

Abstract: Some embodiments of the present disclosure provide certification for the handling of an inference request that is transmitted to a DNN hosted on a remote computing system. Output data, received responsive to the inference request, may be certified as being appropriately generated by the DNN, rather than being tampered with or generated by a malicious DNN. Output data from the DNN may be also certified as appropriately corresponding to input data included in the inference request. Linear block coding may be used on transmissions to guard against eavesdropping and tampering. Through the use of a certification DNN, a degree of comfort may be gained that given output data appropriately corresponds to input data included in a given inference request.

Abstract: Some embodiments of the present application provide a forward-propagation-only (FP-only) method of training a DNN model. Such methods result in a trained DNN model whose performance comparable to a DNN model trained using bidirectional training methods. The FP-only method for training a DNN model may operate without employing the known chain rule. The chain rule is employed when computing gradients for a backward propagation in a bidirectional method. The FP-only method may allow for the computations and updates to the parameters for each layer of the DNN model to be performed in parallel. The FP-only methods for training a DNN model use stochastic gradient descent and the FP-only method for training a DNN model still involves computing gradients. However, the FP-only methods of training a DNN model allow for computing of gradients without the chain rule.

Abstract: Methods and devices utilizing artificial intelligence (AI) or machine learning (ML) for customization of a device specific air interface configuration in a wireless communication network are provided. An over the air information exchange to facilitate the training of one or more AI/ML modules involves the exchange of AI/ML capability information identifying whether a device supports AI/ML for optimization of the air interface.

Abstract: This application provides example communication methods and a related apparatuses. An example communication method may be used for a first processing entity of a first communication device. The example method includes the first processing entity sending a first registration request to a second entity, where the first registration request includes a first identifier which indicates one or more of the following information of the first processing entity: model information or data information. A model parameter of the second entity can be adjusted based on a real-time environment parameter. The first processing entity receives a first registration response sent by the second entity, where the first registration response indicates an input parameter of the second entity. The first processing entity sends a first response acknowledgment, where the first response acknowledgment indicates whether an output parameter of the first processing entity matches the input parameter of the second entity.

Abstract: Some embodiments of the present disclosure provide a scheme for multiplexing of sensing pilot signals and data content signals. For example, some embodiments include obtaining, at a sensing pilot signal transmitting node, a time-frequency pattern specific to the sensing pilot signal transmitting node. The time-frequency pattern indicates, for a first plurality of resource blocks, a second plurality of resource blocks that are to be used for transmitting a plurality of sensing pilot signals, and a sensing pilot signal parameter for each sensing pilot signal among the plurality of sensing pilot signals. Some embodiments further include transmitting, to a sensing pilot signal receiving node and in accordance with the time-frequency pattern, a particular sensing pilot signal among the plurality of sensing pilot signals.

Abstract: A low density parity check (LDPC) channel encoding method is used in a wireless communications system. A communication device encodes an input bit sequence by using an LDPC matrix, to obtain an encoded bit sequence for transmission. The LDPC matrix is obtained based on a lifting factor Z and a base matrix. The base matrix may be one of eight exemplary designs. The encoding method can be used in various communications systems including fifth generation (5G) telecommunication systems, and can support various encoding requirements for information bit sequences with different code lengths.

Abstract: Current online training procedures for artificial intelligence/machine learning (AI/ML) models for wireless communication generally suffer from high communication overhead and/or significant delays in training, particularly when training data is exchanged over an unreliable/hostile communication channel. An example method includes communicating, in accordance with a first communication mode, data or control information with a second device in the wireless communication network. The first communication mode is one of a plurality of communication modes comprising at least the first communication mode and a second communication mode, the second communication mode differing from the first communication mode in terms of at least one of a quantization level used to quantize values of variables in the data or control information, or a Hybrid Automatic Repeat reQuest (HARQ) feedback and retransmission mode for selective retransmission of one or more portions of the data or control information.

Abstract: A sending device may obtain a first to-be-encoded vector. The sending device may perform first encoding on the first to-be-encoded vector, to obtain a second to-be-encoded vector. The sending device may encode the second to-be-encoded vector based on a first generator matrix, to obtain an encoded codeword. The first generator matrix may include at least N+1 submatrices a, and N of the submatrices a may be located on a main diagonal of the first generator matrix. The first generator matrix may be a block upper triangular matrix, or the first generator matrix may be a block lower triangular matrix. The submatrix a is a polar kernel matrix with a size of 2m*2m, m is a natural number, and N is a natural number. The sending device may send the encoded codeword.

Abstract: A wireless network can generate candidate signal configurations for physical transmissions to or from a user equipment (UE) in a radio environment. The generation of candidate signal configurations can be performed using a first neural network that is associated with the UE. These signal configurations can then be evaluated using a second neural network that is associated with the radio environment. The second neural network can be trained using measurements from previous physical transmissions in the radio environment. The trained second neural network generates a reward value that is associated with the candidate signal configurations. The first neural network is then trained using the reward values from the second neural network to produce improved candidate signal configurations. When a signal configuration that produces a suitable reward value is generated, this signal configuration can be used for the physical transmission in the radio environment.

Abstract: Embodiments of this application disclose a communication method and a communication apparatus. The method includes: A transmit end performs first encoding processing on first data by using an encoder neural network, to obtain a first sent feature, where the first sent feature is related to a channel distribution dimension of an environment in which the transmit end is located. The transmit end performs second encoding processing on the first sent feature by using a matching layer, to obtain a first feature, where the encoder neural network and the matching layer are obtained through independent training. The transmit end sends the first feature to a receive end, where the first feature is used by the receive end to obtain the first data.

Abstract: The present disclosure relates, in part, to non-terrestrial communication systems, and in some embodiments to the integration of terrestrial and non-terrestrial communication systems. Non-terrestrial communication systems can provide a more flexible communication system with extended wireless coverage range and enhanced service quality compared to conventional communication systems.

Abstract: Systems and methods are provided that deliver unequal error protection for multiple payloads in a single forward error correction codeword at the air interface layer of wireless communication networks. To simultaneously solve the two problems of (i) providing differential treatment for high and low priority payloads (e.g. higher QoS for payload with higher priority), and (ii) enhancing the overall coding gain, a joint coding scheme is provided in which a high-priority payload is combined with a low priority payload, and a combined payload is jointly encoded to generate a single long codeword. For example, one or more small URLLC messages (e.g. from sensors) can be combined with a video payload or an eMBB payload.

Abstract: Some embodiments of the present disclosure relate to inferencing using a trained deep neural network. Inferencing may, reasonably, be expected to be a mainstream application of 6G wireless networks. Agile, robust and accurate inferencing is important for the success of AI applications. Aspects of the present application relate to introducing coding theory into inferencing in a distributed manner. It may be shown that redundant wireless bandwidths and edge units help to ensure agility, robustness and accuracy in coded inferencing networks.

Abstract: Aspects of the present disclosure enable the determination of beamforming information and channel information for communication between a transmitter and receiver by using a propagation path map. The propagation path map may provide an association between a location of the receiver and channel characteristics between the transmitter and the receiver via a direct propagation path and possible reflection propagation paths. The propagation path map may be used to obtain a more accurate location of the receiver, AoA at the transmitter and/or receiver, AoD at the transmitter, and/or receiver and other sensing information for beamforming and improving the RF propagation map. The association between a location of the receiver and channel characteristics between the transmitter and the receiver may then aid in performing beam measurements and/or channel measurements.