Qualcomm Incorporated

June Namgoong

Tingfang Ji

Krishna Kiran Mukkavilli

Taesang Yoo

Naga Bhushan

Alexandros Manolakos

Pavan Kumar Vitthaladevuni

Jing Jiang

Jay Kumar Sundararajan

Joseph Binamira Soriaga

Hung Dinh Ly

Yang Yang

Saeid Sahraei

Tao Luo

Peter S Gaal

Hwan Joon Kwon

Shimman Arvind Patel

Gokul Sridharan

Muhammad Sayed Khairy Abdelghaffar

Srikant Jayaraman

Huilin Xu

Wanshi Chen

Hao Xu

Hyojin Lee

Peter Pui Lok Ang

Makesh Pravin John Wilson

Peter J Black

Weimin Duan

Yu Zhang

Heechoon Lee

Bilal Sadiq

Wei Jennifer Yang

Xiaoxia Zhang

Sony Akkarakaran

Wei Zeng

Gabi Sarkis

Bin Tian

Renqiu Wang

Sumeeth Nagaraja

Ahmad Jalali

Raghuraman Krishnamoorthi

Weiliang Zeng

Ruoheng Liu

Jae Won Yoo

Wenjun Li

Jing X Sun

Juan Montojo

Kapil Gulati

Haitong Sun

Wooseok Nam

Alexei Yurievitch Gorokhov

Xiao Feng Wang

Ahmed Attia Abotabl

Chih-Hao Liu

Jun Ma

Seyong Park

Siddhartha Mallik

Brian Clarke Banister

Kaushik Chakraborty

Danlu Zhang

Hari Sankar

Amir Aminzadeh Gohari

Yeliz Tokgoz

Joseph Patrick Burke

Shengbo Chen

Bo Chen

Ruifeng Ma

Mingxi Fan

Michael Alexander Howard

Jae Ho Ryu

Thomas Wilborn

Eren Balevi

Huang Lou

Michael John Mangan

Lu Zhao

Hanfang Pan

Sooryanarayanan Gopalakrishnan

Venkatraman Rajagopalan

Akash Sandeep Doshi

Rajakumar Ebenezar Devairakkam

Aaron Klein

Sunil Kumar Kamavaram

Hai Truong Le

Kirty Prabhakar Vedula

Gokul Sridaran

Krishna Kiran Mukkavili

Krisha Kiran Mukkavilli

Sunil Kamavaram

Hai Le

Methods, systems, and devices for wireless communications are described. A user equipment (UE) may transmit a request for sets of neural network weights, each set corresponding to a neural network, to one or more network entities. The one or more network entities may transmit multiple sets of neural network weights to the UE in response to the request. The UE may run a classifier neural network on the sets of neural network weights to select a set of neural network weights corresponding to a neural network. The UE may transmit a neural network identifier to the one or more network entities that transmitted neural network weights.

Online training and augmentation of neural networks for channel state feedback

Systems and techniques are described herein for wireless communication. For example, a computing device (e.g., a user equipment or component thereof) can obtain channel estimation of at least one channel for communication with a network device. The computing device can obtain a location parameter associated with the computing device. The computing device can determine, based at least on the channel estimation, one or more large scale parameters (LSPs). The computing device can further generate an LSP vector associated with the one or more LSPs. The computing device can transmit, to the network device, the LSP vector and the location parameter of the computing device.

Generation of complete large scale parameter maps

Various aspects of the present disclosure relate to wireless communication. In some aspects, a client may receive an observed environmental vector feedback configuration associated with a reporting procedure for reporting updates corresponding to at least one observed environmental vector that is based at least in part on one or more features associated with an environment of the client, wherein the observed environmental vector comprises input for a first machine learning component that determines client specific parameters for use by a second machine learning component. The client may transmit an update corresponding to the at least one observed environmental vector based at least in part on the observed environmental vector feedback configuration. Numerous other aspects are provided.

Observed environmental vector feedback for wireless communication

A method of wireless communication by a user equipment (UE) includes receiving different sets of parameters from different sources as input to a receiver neural network. The method also includes receiving, from a base station, a set of target long-term energy values associated with the receiver neural network. The method further includes calculating a scaling factor for each of the different sets of parameters based on the set of target long-term energy values, and separately scaling each of the different sets of parameters based on the scaling factor calculated for that set in order to generate multiple sets of scaled parameters. The method still further includes transmitting the multiple sets of scaled parameters to the receiver neural network.

Gain scaling of input to neural network for end-to-end learning in wireless communication system

Methods, systems, and devices for wireless communications are described. A user equipment (UE) may receive an indication of one or more encoding operations to use for encoding a compressed dataset, the one or more encoding operations including a differential encoding operation, or an entropy encoding operation, or both. In some examples, using a neural network, the UE may first encode a dataset based on an additional encoding operation to generate a compressed dataset and then quantize the compressed dataset encoded based on the additional encoding operation. Subsequently, after the dataset has been initially encoded and then quantized, the UE may use the indication of the one or more encoding operations to further encode and compress the dataset. The UE may then transmit the dataset to a second device based on the one or more encoding operations.

Encoding techniques for neural network architectures

Certain aspects of the present disclosure provide techniques for joint communication and radar sensing. A method is provided for wireless communications by a network entity. The method generally includes communicating one or more radar signals in a first set of slots. Each of the first set of slots comprises an extended cyclic prefix have a first length. The method generally includes communicating one or more signals in a second set of slots, each of the second set of slots comprising a normal cyclic prefix having a second length that is shorter than the first length.

Sensing instances for radar sensing and communication

Disclosed are techniques for wireless communication. In an aspect, a user equipment (UE) applies a plurality of positioning reference signal (PRS) processing windows to a PRS resource received from a network node over a multipath channel, determines a plurality of channel estimates for the PRS resource based on the plurality of PRS processing windows, and determines a plurality of positioning measurements of the PRS resource based on the plurality of channel estimates.

User equipment (UE) positioning with frequency domain windowing

Aspects described herein relate to determining whether full duplex (FD) communications are configured during resources for communicating one or more messages of a random access procedure, where the FD communications comprising uplink communications and downlink communications occurring in a same frequency band, and responsive to the determining whether the FD communications are configured during the resources, transmitting the one or more messages of the random access procedure using the resources.

Techniques for performing random access in full duplex wireless communications

Aspects relate to measuring downlink beam quality in the presence of self-interference when operating in a full duplex mode configured for concurrent transmission and reception within an overlapping bandwidth. A user equipment (UE) may communicate with a base station over one or more of a plurality of uplink beams and downlink beams. For each uplink beam, the UE may obtain beam quality measurements associated with each of the downlink beams to identify a set of usable downlink beams. The UE may further transmit a report to the base station indicating the set of usable downlink beams for at least one uplink beam.

Beam quality measurements in wireless networks

Certain aspects of the present disclosure generally relate to techniques for selecting a base graph to be used for wireless communications. Selection can be based on a variety of factors. Abase graph can be used to derive a low-density parity-check (LDPC) code used for encoding a retransmission of an original transmission. An exemplary method generally includes selecting, based on a modulation and coding scheme (MCS) and a resource allocation (RA) for transmitting a codeword, a base graph (BG), from which to derive a low density parity check (LDPC) code for use in encoding data bits in the codeword (e.g., encoding data bits of a bitstream such that some redundant bits are included in the codeword), encoding the data bits to generate the codeword using the LDPC code derived from the selected BG, and transmitting the codeword using the MCS via resources of the

Communication techniques applying low-density parity-check code base graph selection

Methods, systems, and devices for wireless communications are described. A user equipment (UE) may encode channel state feedback (CSF) information to compress the CSF information to a first encoding output associated with a first dimensional space, and apply entropy coding to the first encoding output of the channel state feedback information. The entropy coding may transform the first encoding output to a second encoding output associated with a second dimensional space that is smaller than the first dimensional space of the first encoding output. The UE may transmit a CSF message comprising the second encoding output. A network device may receive the CSF message and apply entropy decoding to the compressed CSF information to partially decompress the compressed CSF information to a first decoding output. The network device may decode the first decoding output to completely decompress the compressed CSF information to a second decoding output.

Techniques for encoding and decoding a channel between wireless communication devices

Methods, systems, and devices for wireless communications are described. A first device and a second device may communicate via a channel. The first device may generate and transmit a reference signal, which may be a distortion probing reference signal with a high peak to average power ratio. In one implementation, the first device may use the reference signal as an input for a neural network model to learn a nonlinear response of the second device transmission components. In another implementation, the second device may sample the generated reference signal, and use the samples as inputs for a neural network model to learn the nonlinear response. The first device and the second device may exchange signaling based on learning the nonlinear response, and each device may compensate for the nonlinear response when communicating via the channel.

Distortion probing reference signals

Various aspects of the present disclosure generally relate to wireless communication. In some aspects, a client may select, based at least in part on a classifier, an autoencoder of a set of autoencoders to be used for encoding an observed wireless communication vector to generate a latent vector. The client may transmit the latent vector and an indication of the autoencoder. Numerous other aspects are provided.

Federated learning for classifiers and autoencoders for wireless communication

Radio frequency (RF) sensing by a sensing entity with an oscillator that introduces frequency errors is supported using dual direction bistatic sensing. The sensing entity transmits a sensing signal that is reflected by an object and received by a second sensing entity, which measures a first frequency offset that includes an oscillator error from the transmission of the sensing signal and a Doppler shift from the object. The sensing entity also receives and measures a second frequency offset of a sensing signal transmitted by the second sensing entity and reflected by the object, which includes a second frequency offset that includes an oscillator error from the reception of the sensing signal and a Doppler shift from the target object. The velocity of the object may be estimated based on a combination of the first and second frequency offsets, which cancels the oscillator error caused by the sensing entity.

Mitigation of impact of oscillator error on doppler estimation for radio frequency sensing

A second base station may allocate a set of downlink resources for a downlink transmission. The set of downlink resources may include a subset of null resources, which may serve as a signature for the second base station. The second base station may transmit downlink data or reference signals on the set of downlink resources including the subset of null resources. A first UE may experience the downlink transmission from the second base station as interference. The first UE may identify the set of downlink resources. The first UE may identify the subset of null resources. The first UE may transmit, to a first base station, an indication of the subset of null resources. The first base station may identify the second base station based on the indication of the subset of null resources. The first base station may transmit, to the second base station, an interference coordination message.

Interferer identification using null resource pattern

Growing community of inventors

San Diego, CA, United States of America

June Namgoong