Abstract: A communications network system including antenna elements and a processor coupled with the antenna elements, the processor executing instructions to perform operations including establishing a first data communication link over a first frequency band between the CPU and the first AP of a first group of APs, causing the first AP to establish a second data communications link over a second frequency band between the first AP and a first UE, transmitting, via beamforming by the antenna elements, data to the first AP over the first data communications link, the data configured to be relayed via the first AP to the first UE over the second data communications link, obtaining an end-to-end data rate of the data communication between the CPU and the first UE, and achieving a higher end-to-end data rate than the obtained end-to-end data rate by adjusting beamforming vectors.

Abstract: Data associated with a coverage area of a base station is obtained. A model is trained based in part on the obtained data associated with the coverage area. The trained model is deployed to make inferences for one or more user equipment (UE) located in the coverage area. A corresponding recommended reference signal outputted by the trained model is utilized to decide on an approach for estimating corresponding channels associated with the one or more UE located in the coverage area.

Abstract: System and method for integrating sensing and communication (ISAC) systems with backscattering radio frequency identification (RFID) tags are disclosed. An access point employs a communication beam to serve a communications device while using a sensing beam to detect an RFID tag. Under the total transmit power constraint of the system, sensing and communication beams are designed by considering tag detection and communication specifications. Zero-forcing is used to design the beamforming vectors, and a convex optimization problem is solved to determine the power allocation between sensing and communication. Minimizing the total transmit power and satisfying tag detection and communication specifications are accomplished by joint beamforming design. To resolve this, we re-formulate the non-convex constraints into convex second-order cone constraints.

Abstract: System and method include a Large Wireless Model (LWM), a task-agnostic, Transformer-based, model pre-trained on large-scale wireless environment datasets. This self-supervised model generates contextualized wireless data embeddings in real time, enhancing the performance of a wide range of downstream tasks in wireless communication and sensing systems. LWM may learn from large-scale wireless data and adapt to diverse tasks with limited data.

Abstract: Wireless transmitter identification in visual scenes is provided. This technology enables important wireless communications and sensing applications such as (i) fast beam/blockage prediction in fifth generation (5G)/sixth generation (6G) systems using camera data, (ii) identifying cars and people in a surveillance camera feed using joint visual and wireless data processing, and (iii) enabling efficient autonomous vehicle communication relying on both the camera and wireless data. This is done by developing multimodal machine learning based frameworks that use the sensory data obtained by visual and wireless sensors. More specifically, given some visual data, an algorithm needs to perform the following: (i) predict whether an object responsible for a received radio signal is present or not, (ii) if it is present, detect which object it is out of the candidate transmitters, and (iii) predict what type of signal the detected object is transmitting.

Abstract: Relay-aided intelligent reconfigurable surfaces (IRSs) are provided. A novel relay-aided intelligent surface architecture is described herein that has the potential of achieving the promising gains of IRSs with a much smaller number of elements, opening the door for realizing these surfaces in practice. A half-duplex or full-duplex relay is connected to one or more IRSs. This merges the gains of relays and reconfigurable surfaces and splits the required signal-to-noise ratio (SNR) gain between them. This architecture can then significantly reduce the required number of reconfigurable elements in the IRS(s) while achieving the same spectral efficiencies. Consequently, the proposed relay-aided intelligent surface architecture needs far less channel estimation/beam training overhead and provides enhanced robustness compared to traditional IRS solutions.

Abstract: A system and method for identifying a communication user in a crowded scenario and support multi-user applications, and for identifying the target communication user from the other candidate objects (distractors) in the visual scene. Machine learning models process either one frame or a sequence of frames of sensor data from distributed nodes to identify the target communication user in the semantic environment. Large antenna arrays and narrow directive beams are used to ensure a receive signal power. Optimal beams for millimeter-wave (mmWave) and terahertz (THz) large antenna arrays are selected. Distributed nodes equipped with sensors to receive sensor data extract environment semantics from the captured sensor data. The semantic data are transmitted to the base station. A communication user identification and tracking process is executed at the base station.

Abstract: Data associated with a coverage area of a base station is obtained. A model is trained based in part on the obtained data associated with the coverage area. The trained model is deployed to make inferences for one or more user equipment (UE) located in the coverage area.

Abstract: Language learning through the utilization of advanced multi-modal sensing technologies, including cameras (RGB and RGB-D), LiDARs, radars, IMUs, IR, and mmWave/THz sensors includes integration of the sensing technologies, and enables the detection of both physical cues—such as lip movements, facial expressions, head movements, and gaze direction—and auditory data captured by microphones, providing information about the language acquisition process. This multi-modal strategy enables voice activity detection, identification of active speech moments by learners, and pronunciation error analysis. The error analysis enables feedback that can improve speaking proficiency and learner engagement.

Abstract: Reinforcement learning of interference-aware beam pattern design is provided. Employing large antenna arrays is a characteristic of millimeter wave (mmWave) and terahertz (THz) communication systems. Embodiments described herein provide an efficient deep reinforcement learning based beam pattern design algorithm that achieves interference awareness. This is done by not requiring the channel knowledge of both desired user and the interference users. Simulation results show that the developed solution is capable of finding a well-shaped beam pattern that significantly suppresses the interference while sacrificing only negligible beam-forming/combining gain from the desired user, based only on power measurements. Furthermore, a platform and results based on real measurements are also presented, which indicates the effectiveness and robustness of the disclosed interference-aware beam pattern design approach in a practical system.

Abstract: Relay-aided intelligent reconfigurable surfaces (IRSs) are provided. A novel relay-aided intelligent surface architecture is described herein that has the potential of achieving the promising gains of IRSs with a much smaller number of elements, opening the door for realizing these surfaces in practice. A half-duplex or full-duplex relay is connected to one or more IRSs. This merges the gains of relays and reconfigurable surfaces and splits the required signal-to-noise ratio (SNR) gain between them. This architecture can then significantly reduce the required number of reconfigurable elements in the IRS(s) while achieving the same spectral efficiencies. Consequently, the proposed relay-aided intelligent surface architecture needs far less channel estimation/beam training overhead and provides enhanced robustness compared to traditional IRS solutions.

Abstract: A system and method using a digital replica to populate large fingerprinting databases. A digital twin map is created ray-tracing simulations on a digital replica of the environment across several frequency bands and beamforming configurations. Online user equipment fingerprints are matched against this spatial database. A user equipment position measured in real-time and the digital twin map are used to compute the most probable location of the user equipment.

Abstract: A system and method for training the machine learning models of the multiple-input multiple-output (MIMO) communication systems. The system and method cluster the training data based on the device position. Then, separate models are trained based on the data for each position. The system and method can be applied to the design of machine learning-based beamforming, precoding, channel compression, channel estimation, and codebook design among other applications. The system uses the implicit or explicit user position information to select the right zone-specific model and its parameters.

Abstract: The invention provides compositions and methods for treating a patient with cancer with an immune cell, e.g., a T-cell, e.g., an engineered T-cell, with increased sialidase activity. The invention also provides compositions and methods for treating a patient with cancer with an immune cell, e.g., a T-cell, e.g., an engineered T-cell, in combination with a sialidase. The invention also provides compositions and methods for treating a patient with cancer with an immune cell, e.g., a T-cell, e.g., an engineered T-cell, pretreated with a sialidase.

Abstract: Reinforcement learning of beam codebooks for millimeter wave and terahertz multiple-input-multiple-output (MIMO) systems is provided. Millimeter wave (mmWave) and terahertz (THz) MIMO systems rely on predefined beamforming codebooks for both initial access and data transmission. These predefined codebooks, however, are commonly not optimized for specific environments, user distributions, and/or possible hardware impairments. To overcome these limitations, this disclosure develops a deep reinforcement learning framework that learns how to optimize the codebook beam patterns relying only on receive power measurements. The developed model learns how to adapt the beam patterns based on the surrounding environment, user distribution, hardware impairments, and array geometry. Further, this approach does not require any knowledge about the channel, radio frequency (RF) hardware, or user positions.

Abstract: A communications network system including antenna elements and a processor coupled with the antenna elements, the processor executing instructions to perform operations including establishing a first data communication link over a first frequency band between the CPU and the first AP of a first group of APs, causing the first AP to establish a second data communications link over a second frequency band between the first AP and a first UE, transmitting, via beamforming by the antenna elements, data to the first AP over the first data communications link, the data configured to be relayed via the first AP to the first UE over the second data communications link, obtaining an end-to-end data rate of the data communication between the CPU and the first UE, and achieving a higher end-to-end data rate than the obtained end-to-end data rate by adjusting beamforming vectors.

Abstract: A communications network system is disclosed. The system may include a central processing unit (CPU) in data communication with a first access point (AP) configured to enable a data communication between the CPU and a first user equipment (UE). The CPU may include a processor configured to select a first group of APs including the first AP, establish a first data communications link over a first frequency band between the CPU- and the first AP, cause the first AP to establish a second data communications link over a second frequency band between the first AP and the first UE, and transmit a portion of data to the first AP over the first data communications link. The first data communications link may be a wireless data communications link. The first frequency band may include higher frequency levels than those of the second frequency band.

Abstract: A computer system is disclosed that is configured to perform a method that includes receiving one or more radar data frames from one or more antennas of a base station or a user equipment device in an environment; processing the one or more radar data frames to identify one or more attributes of one or more static objects and one or more dynamic objects in the environment; and estimating one or more channels for the user equipment device and the base station based on the one or more attributes of the one or more static objects and the one or more dynamic objects.

Abstract: Large intelligent surfaces (LISs) with sparse channel sensors are provided. Embodiments described herein provide efficient solutions for these problems by leveraging tools from compressive sensing and deep learning. Consequently, an LIS architecture based on sparse channel sensors is provided where all LIS elements are passive reconfigurable elements except for a few elements that are active (e.g., connected to baseband). Two solutions are developed that design LIS reflection matrices with negligible training overhead. First, compressive sensing tools are leveraged to construct channels at all the LIS elements from the channels seen only at the active elements. These full channels can then be used to design the LIS reflection matrices with no training overhead.

Abstract: A communications network system is disclosed. The system may include a central processing unit (CPU) in data communication with a first access point (AP) configured to enable a data communication between the CPU and a first user equipment (UE). The CPU may include a processor configured to select a first group of APs including the first AP, establish a first data communications link over a first frequency band between the CPU- and the first AP, cause the first AP to establish a second data communications link over a second frequency band between the first AP and the first UE, and transmit a portion of data to the first AP over the first data communications link. The first data communications link may be a wireless data communications link. The first frequency band may include higher frequency levels than those of the second frequency band.