Search Results for author:
Found 100 papers, 23 papers with code
Multi-View Wireless Sensing via Conditional Generative Learning: Framework and Model Design
In this paper, we incorporate physical knowledge into learning-based high-precision target sensing using the multi-view channel state information (CSI) between multiple base stations (BSs) and user equipment (UEs).
Computational Imaging-Based ISAC Method with Large Pixel Division
In this paper, a novel method is proposed to address such a problem in environment sensing in millimeter-wave wireless cellular networks, which effectively cancels the severe errors caused by large pixel division as in conventional computational imaging algorithms.
FlexiAct: Towards Flexible Action Control in Heterogeneous Scenarios
Unlike existing methods, FlexiAct allows for variations in layout, viewpoint, and skeletal structure between the subject of the reference video and the target image, while maintaining identity consistency.
Communication-Efficient Personalized Distributed Learning with Data and Node Heterogeneity
In the proposed method, each local model is represented as the Hadamard product of global real-valued parameters and a personalized binary mask for pruning.
Cobra: Efficient Line Art COlorization with BRoAder References
The comic production industry requires reference-based line art colorization with high accuracy, efficiency, contextual consistency, and flexible control.
Analogical Learning for Cross-Scenario Generalization: Framework and Application to Intelligent Localization
Existing learning models often exhibit poor generalization when deployed across diverse scenarios.
Fair Resource Allocation in UAV-based Semantic Communication System with Fluid Antenna
In this paper, the problem of maximization of the minimum equivalent rate in a unmanned-aerial-vehicle (UAV)-based multi-user semantic communication system is investigated.
WorldPrompter: Traversable Text-to-Scene Generation
Scene-level 3D generation is a challenging research topic, with most existing methods generating only partial scenes and offering limited navigational freedom.
BlobCtrl: A Unified and Flexible Framework for Element-level Image Generation and Editing
Element-level visual manipulation is essential in digital content creation, but current diffusion-based methods lack the precision and flexibility of traditional tools.
VideoPainter: Any-length Video Inpainting and Editing with Plug-and-Play Context Control
Video inpainting, which aims to restore corrupted video content, has experienced substantial progress.
Large-Scale AI in Telecom: Charting the Roadmap for Innovation, Scalability, and Enhanced Digital Experiences
This white paper discusses the role of large-scale AI in the telecommunications industry, with a specific focus on the potential of generative AI to revolutionize network functions and user experiences, especially in the context of 6G systems.
Semantic Communication with Entropy-and-Channel-Adaptive Rate Control over Multi-User MIMO Fading Channels
Although significant improvements in transmission efficiency have been achieved, existing semantic communication (SemCom) methods typically use a fixed transmission rate for varying channel conditions and transmission contents, leading to performance degradation under harsh channel conditions.
Comprehensive Subjective and Objective Evaluation Method for Text-generated Video
Recent text-to-video (T2V) technology advancements, as demonstrated by models such as Gen3, Pika, and Sora, have significantly broadened its applicability and popularity.
Generative AI Empowered Semantic Feature Multiple Access (SFMA) Over Wireless Networks
Second, we optimize inter-group power allocation by formulating an optimization problem that allocates proper transmit power across all user groups to maximize system sum rates while satisfying each user's minimum rate requirement.
DiTCtrl: Exploring Attention Control in Multi-Modal Diffusion Transformer for Tuning-Free Multi-Prompt Longer Video Generation
Based on our careful design, the video generated by DiTCtrl achieves smooth transitions and consistent object motion given multiple sequential prompts without additional training.
DTSGAN: Learning Dynamic Textures via Spatiotemporal Generative Adversarial Network
Dynamic texture synthesis aims to generate sequences that are visually similar to a reference video texture and exhibit specific stationary properties in time.
Consistent Human Image and Video Generation with Spatially Conditioned Diffusion
By fine-tuning existing base diffusion models on human video data, our method demonstrates strong generalization to unseen human identities and poses without requiring additional per-instance fine-tuning.
ColorFlow: Retrieval-Augmented Image Sequence Colorization
Automatic black-and-white image sequence colorization while preserving character and object identity (ID) is a complex task with significant market demand, such as in cartoon or comic series colorization.
BrushEdit: All-In-One Image Inpainting and Editing
Image editing has advanced significantly with the development of diffusion models using both inversion-based and instruction-based methods.
Towards Wireless-Native Big AI Model: Insights into Its Ambitions, Peculiarities and Methodologies
Researches on leveraging big artificial intelligence model (BAIM) technology to drive the intelligent evolution of wireless networks are emerging.
Implicit Neural Compression of Point Clouds
Our approach employs two coordinate-based neural networks to implicitly represent a voxelized point cloud: the first determines the occupancy status of a voxel, while the second predicts the attributes of occupied voxels.
NVComposer: Boosting Generative Novel View Synthesis with Multiple Sparse and Unposed Images
Recent advancements in generative models have significantly improved novel view synthesis (NVS) from multi-view data.
Mitigating Knowledge Conflicts in Language Model-Driven Question Answering
In the context of knowledge-driven seq-to-seq generation tasks, such as document-based question answering and document summarization systems, two fundamental knowledge sources play crucial roles: the inherent knowledge embedded within model parameters and the external knowledge obtained through context.
Artistic Neural Style Transfer Algorithms with Activation Smoothing
The works of Gatys et al. demonstrated the capability of Convolutional Neural Networks (CNNs) in creating artistic style images.
Sampling-guided Heterogeneous Graph Neural Network with Temporal Smoothing for Scalable Longitudinal Data Imputation
In this paper, we propose a novel framework, the Sampling-guided Heterogeneous Graph Neural Network (SHT-GNN), to effectively tackle the challenge of missing data imputation in longitudinal studies.
Enhancing Missing Data Imputation through Combined Bipartite Graph and Complete Directed Graph
In this paper, we aim to address a significant challenge in the field of missing data imputation: identifying and leveraging the interdependencies among features to enhance missing data imputation for tabular data.
Analysis of Financial Risk Behavior Prediction Using Deep Learning and Big Data Algorithms
First, the application and advantages of deep learning and big data algorithms in the financial field are analyzed.
Research on Key Technologies for Cross-Cloud Federated Training of Large Language Models
With the rapid development of natural language processing technology, large language models have demonstrated exceptional performance in various application scenarios.
E-Healthcare Systems: Integrated Sensing, Computing, and Semantic Communication with Physical Layer Security
This paper introduces an integrated sensing, computing, and semantic communication (ISCSC) framework tailored for smart healthcare systems.
MotionCraft: Crafting Whole-Body Motion with Plug-and-Play Multimodal Controls
However, employing a unified model to achieve various generation tasks with different condition modalities presents two main challenges: motion distribution drifts across different tasks (e. g., co-speech gestures and text-driven daily actions) and the complex optimization of mixed conditions with varying granularities (e. g., text and audio).
ChipExpert: The Open-Source Integrated-Circuit-Design-Specific Large Language Model
Finally, to mitigate the hallucinations of ChipExpert, we have developed a Retrieval-Augmented Generation (RAG) system, based on the IC design knowledge base.
Image Inpainting Models are Effective Tools for Instruction-guided Image Editing
The most advanced methods, such as SmartEdit and MGIE, usually combine large language models with diffusion models through joint training, where the former provides text understanding ability, and the latter provides image generation ability.
FedsLLM: Federated Split Learning for Large Language Models over Communication Networks
This paper models the minimization of the training delay by integrating computation and communication optimization, simplifying the optimization problem into a convex problem to find the optimal solution.
MiraData: A Large-Scale Video Dataset with Long Durations and Structured Captions
Sora's high-motion intensity and long consistent videos have significantly impacted the field of video generation, attracting unprecedented attention.
Joint Beamforming and Antenna Design for Near-Field Fluid Antenna System
In this letter, we study the energy efficiency maximization problem for a fluid antenna system (FAS) in near field communications.
Image Conductor: Precision Control for Interactive Video Synthesis
To this end, we propose Image Conductor, a method for precise control of camera transitions and object movements to generate video assets from a single image.
Exploring Channel Estimation and Signal Detection for ODDM-based ISAC Systems
Inspired by providing reliable communications for high-mobility scenarios, in this letter, we investigate the channel estimation and signal detection in integrated sensing and communication~(ISAC) systems based on the orthogonal delay-Doppler multiplexing~(ODDM) modulation, which consists of a pulse-train that can achieve the orthogonality with respect to the resolution of the delay-Doppler~(DD) plane.
VBIM-Net: Variational Born Iterative Network for Inverse Scattering Problems
In this article, we propose a novel Variational Born Iterative Network, namely, VBIM-Net, to solve the full-wave ISPs with significantly improved structural rationality and inversion quality.
All-day Depth Completion
In poorly illuminated regions where photometric intensities do not afford the inference of local shape, the coarse approximation of scene depth serves as a prior; the uncertainty map is then used with the image to guide refinement through an uncertainty-driven residual learning (URL) scheme.
ReVideo: Remake a Video with Motion and Content Control
In this paper, we present a novel attempt to Remake a Video (ReVideo) which stands out from existing methods by allowing precise video editing in specific areas through the specification of both content and motion.
Evolving Semantic Communication with Generative Model
In this paper, we explore an evolving semantic communication system for image transmission, referred to as ESemCom, with the capability to continuously enhance transmission efficiency.
Channel Deduction: A New Learning Framework to Acquire Channel from Outdated Samples and Coarse Estimate
How to reduce the pilot overhead required for channel estimation?
Homogeneous Tokenizer Matters: Homogeneous Visual Tokenizer for Remote Sensing Image Understanding
Compared to Patch Embed, which requires more than one hundred tokens for one image, HOOK requires only 6 and 8 tokens for sparse and dense tasks, respectively, resulting in efficiency improvements of 1. 5 to 2. 8 times.
TernaryVote: Differentially Private, Communication Efficient, and Byzantine Resilient Distributed Optimization on Heterogeneous Data
In this paper, we propose TernaryVote, which combines a ternary compressor and the majority vote mechanism to realize differential privacy, gradient compression, and Byzantine resilience simultaneously.
Channel Mapping Based on Interleaved Learning with Complex-Domain MLP-Mixer
For such a channel mapping task, inspired by the intrinsic coupling across the space and frequency domains, this letter proposes to use interleaved learning with partial antenna and subcarrier characteristics to represent the whole MIMO-OFDM channel.
Point Cloud in the Air
Acquisition and processing of point clouds (PCs) is a crucial enabler for many emerging applications reliant on 3D spatial data, such as robot navigation, autonomous vehicles, and augmented reality.
Cached Transformers: Improving Transformers with Differentiable Memory Cache
This work introduces a new Transformer model called Cached Transformer, which uses Gated Recurrent Cached (GRC) attention to extend the self-attention mechanism with a differentiable memory cache of tokens.
Robust Target Detection of Intelligent Integrated Optical Camera and mmWave Radar System
To improve the target detection performance under complex real-world scenarios, this paper proposes an intelligent integrated optical camera and millimeter-wave (mmWave) radar system.
AutoDIR: Automatic All-in-One Image Restoration with Latent Diffusion
Specifically, AutoDIR consists of two key stages: a Blind Image Quality Assessment (BIQA) stage based on a semantic-agnostic vision-language model which automatically detects unknown image degradations for input images, an All-in-One Image Restoration (AIR) stage utilizes structural-corrected latent diffusion which handles multiple types of image degradations.
Online Resource Allocation for Semantic-Aware Edge Computing Systems
To solve this problem, an online low-complexity algorithm is proposed.
Resource Allocation for Semantic-Aware Mobile Edge Computing Systems
Moreover, the closed-form optimal solution of the semantic extraction factor is derived.
Semantic Information Extraction for Text Data with Probability Graph
In this paper, the problem of semantic information extraction for resource constrained text data transmission is studied.
Mean Field Game-based Waveform Precoding Design for Mobile Crowd Integrated Sensing, Communication, and Computation Systems
In this paper, we consider the environment sensing problem in the large-scale mobile crowd ISCC systems and propose an efficient waveform precoding design algorithm based on the mean field game~(MFG).
OmniQuant: Omnidirectionally Calibrated Quantization for Large Language Models
LWC modulates the extreme values of weights by optimizing the clipping threshold.
GraSS: Contrastive Learning with Gradient Guided Sampling Strategy for Remote Sensing Image Semantic Segmentation
Based on this, we propose contrastive learning with Gradient guided Sampling Strategy (GraSS) for RSI semantic segmentation.
Deep Joint Source-Channel Coding for Wireless Image Transmission with Entropy-Aware Adaptive Rate Control
Adaptive rate control for deep joint source and channel coding (JSCC) is considered as an effective approach to transmit sufficient information in scenarios with limited communication resources.
MIMO Precoding Design with QoS and Per-Antenna Power Constraints
Precoding design for the downlink of multiuser multiple-input multiple-output (MU-MIMO) systems is a fundamental problem.
Distributed Learning over Networks with Graph-Attention-Based Personalization
In conventional distributed learning over a network, multiple agents collaboratively build a common machine learning model.
Semantic-aware Digital Twin for Metaverse: A Comprehensive Review
To facilitate the deployment of digital twins in Metaverse, the paradigm with semantic awareness has been proposed as a means for enabling accurate and task-oriented information extraction with inherent intelligence.
Musketeer: Joint Training for Multi-task Vision Language Model with Task Explanation Prompts
We present a vision-language model whose parameters are jointly trained on all tasks and fully shared among multiple heterogeneous tasks which may interfere with each other, resulting in a single model which we named Musketeer.
Revenue Management without Demand Forecasting: A Data-Driven Approach for Bid Price Generation
We develop a methodology to generate bid prices using historical booking data only.
From Data-driven Learning to Physics-inspired Inferring: A Novel Mobile MIMO Channel Prediction Scheme Based on Neural ODE
Then, we design a novel physics-inspired spatial channel gradient network (SCGnet), which represents the derivative process of channel varying as a special neural network and can obtain the gradients at any relative displacement needed for the ODE solving.
Real-time Controllable Denoising for Image and Video
Controllable image denoising aims to generate clean samples with human perceptual priors and balance sharpness and smoothness.
Robust Millimeter Beamforming via Self-Supervised Hybrid Deep Learning
Beamforming with large-scale antenna arrays has been widely used in recent years, which is acknowledged as an important part in 5G and incoming 6G.
Breaking the Communication-Privacy-Accuracy Tradeoff with $f$-Differential Privacy
We consider a federated data analytics problem in which a server coordinates the collaborative data analysis of multiple users with privacy concerns and limited communication capability.
Magnitude Matters: Fixing SIGNSGD Through Magnitude-Aware Sparsification in the Presence of Data Heterogeneity
Communication overhead has become one of the major bottlenecks in the distributed training of deep neural networks.
Distributed Machine Learning for UAV Swarms: Computing, Sensing, and Semantics
In this survey, we first introduce several popular DL algorithms such as federated learning (FL), multi-agent Reinforcement Learning (MARL), distributed inference, and split learning, and present a comprehensive overview of their applications for UAV swarms, such as trajectory design, power control, wireless resource allocation, user assignment, perception, and satellite communications.
WAIR-D: Wireless AI Research Dataset
The statistical data hinder the trained AI models from further fine-tuning for a specific scenario, and ray-tracing data with limited environments lower down the generalization capability of the trained AI models.
Holographic MIMO Communications: Theoretical Foundations, Enabling Technologies, and Future Directions
In this survey, we present a comprehensive overview of the latest advances in the HMIMO communications paradigm, with a special focus on their physical aspects, their theoretical foundations, as well as the enabling technologies for HMIMO systems.
Generative Model Based Highly Efficient Semantic Communication Approach for Image Transmission
Deep learning (DL) based semantic communication methods have been explored to transmit images efficiently in recent years.
False: False Negative Samples Aware Contrastive Learning for Semantic Segmentation of High-Resolution Remote Sensing Image
This indicates that the SSCL model has the ability to self-differentiate FNS and that the FALSE effectively mitigates the SCI in self-supervised contrastive learning.
Explainable AI over the Internet of Things (IoT): Overview, State-of-the-Art and Future Directions
Explainable Artificial Intelligence (XAI) is transforming the field of Artificial Intelligence (AI) by enhancing the trust of end-users in machines.
Explainable artificial intelligence
Explainable Artificial Intelligence (XAI)
Model Compression for DNN-based Speaker Verification Using Weight Quantization
Experimental results on VoxCeleb show that weight quantization is effective for compressing SV models.
Over-the-Air Split Learning with MIMO-Based Neural Network and Constellation-Based Activation
The precoding and combining matrices are trainable parameters in such a system, whereas the MIMO channel is implicit.
Over-the-Air Split Machine Learning in Wireless MIMO Networks
In such a split ML system, the precoding and combining matrices are regarded as trainable parameters, while MIMO channel matrix is regarded as unknown (implicit) parameters.
Deep Learning-Based Rate-Splitting Multiple Access for Reconfigurable Intelligent Surface-Aided Tera-Hertz Massive MIMO
Then, to acquire accurate CSI at the BS for the investigated RSMA precoding scheme to achieve higher spectral efficiency, we propose a CSI acquisition network (CAN) with low pilot and feedback signaling overhead, where the downlink pilot transmission, CSI feedback at the user equipments (UEs), and CSI reconstruction at the BS are modeled as an end-to-end neural network based on Transformer.
Mobile MIMO Channel Prediction with ODE-RNN: a Physics-Inspired Adaptive Approach
Through exploring the intrinsic correlation among a set of historical CSI instances randomly obtained in a certain communication environment, channel prediction can significantly increase CSI accuracy and save signaling overhead.
Not All Models Are Equal: Predicting Model Transferability in a Self-challenging Fisher Space
It is challenging because the ground-truth model ranking for each task can only be generated by fine-tuning the pre-trained models on the target dataset, which is brute-force and computationally expensive.
Ranked #2 on
Transferability
on classification benchmark
Environment Sensing Considering the Occlusion Effect: A Multi-View Approach
In this paper, we consider the problem of sensing the environment within a wireless cellular framework.
Semantic-preserved Communication System for Highly Efficient Speech Transmission
Deep learning (DL) based semantic communication methods have been explored for the efficient transmission of images, text, and speech in recent years.
Semantic-aware Speech to Text Transmission with Redundancy Removal
We also propose a two-stage training scheme, which speeds up the training of the proposed DL model.
Sufficient-Statistic Memory AMP
Given an arbitrary MAMP, we can construct an SS-MAMP by damping, which not only ensures the convergence of the state evolution, but also preserves the orthogonality, i. e., its dynamics can be correctly described by state evolution.
C-GRBFnet: A Physics-Inspired Generative Deep Neural Network for Channel Representation and Prediction
Specifically, we first use a forward deep neural network to infer the positions of all possible images of the source reflected by the surrounding scatterers within that environment, and then use the well-known Gaussian Radial Basis Function network (GRBF) to approximate the amplitudes of all possible propagation paths.
Dynamic Token Normalization Improves Vision Transformers
It is difficult for Transformers to capture inductive bias such as the positional context in an image with LN.
JMSNAS: Joint Model Split and Neural Architecture Search for Learning over Mobile Edge Networks
In this paper, a joint model split and neural architecture search (JMSNAS) framework is proposed to automatically generate and deploy a DNN model over a mobile edge network.
Blind Channel Estimation for MIMO Systems via Variational Inference
In this paper, we investigate the blind channel estimation problem for MIMO systems under Rayleigh fading channel.
Communication-Efficient Federated Learning with Binary Neural Networks
{ Numerical results show that the proposed FL framework significantly reduces the communication cost compared to the conventional neural networks with typical real-valued parameters, and the performance loss incurred by the binarization can be further compensated by a hybrid method.
Joint Multi-User Communication and Sensing Exploiting Both Signal and Environment Sparsity
As a potential technology feature for 6G wireless networks, the idea of sensing-communication integration requires the system not only to complete reliable multi-user communication but also to achieve accurate environment sensing.
BWCP: Probabilistic Learning-to-Prune Channels for ConvNets via Batch Whitening
To address this problem, we develop a probability-based pruning algorithm, called batch whitening channel pruning (BWCP), which can stochastically discard unimportant channels by modeling the probability of a channel being activated.
FAT: Learning Low-Bitwidth Parametric Representation via Frequency-Aware Transformation
Prior arts often discretize the network weights by carefully tuning hyper-parameters of quantization (e. g. non-uniform stepsize and layer-wise bitwidths), which are complicated and sub-optimal because the full-precision and low-precision models have a large discrepancy.
Multi-hop RIS-Empowered Terahertz Communications: A DRL-based Hybrid Beamforming Design
We investigate the joint design of digital beamforming matrix at the BS and analog beamforming matrices at the RISs, by leveraging the recent advances in deep reinforcement learning (DRL) to combat the propagation loss.
STAR: A Structure-Aware Lightweight Transformer for Real-Time Image Enhancement
STAR is a general architecture that can be easily adapted to different image enhancement tasks.
Distributed ADMM with Synergetic Communication and Computation
In this paper, we propose a novel distributed alternating direction method of multipliers (ADMM) algorithm with synergetic communication and computation, called SCCD-ADMM, to reduce the total communication and computation cost of the system.
Hybrid Beamforming for RIS-Empowered Multi-hop Terahertz Communications: A DRL-based Method
Wireless communication in the TeraHertz band (0. 1--10 THz) is envisioned as one of the key enabling technologies for the future six generation (6G) wireless communication systems.
Channel Estimation for RIS-Empowered Multi-User MISO Wireless Communications
We also discuss the downlink achievable sum rate computation with estimated channels and different precoding schemes for the base station.
AdaX: Adaptive Gradient Descent with Exponential Long Term Memory
Although adaptive optimization algorithms such as Adam show fast convergence in many machine learning tasks, this paper identifies a problem of Adam by analyzing its performance in a simple non-convex synthetic problem, showing that Adam's fast convergence would possibly lead the algorithm to local minimums.
Differentiable Learning-to-Group Channels via Groupable Convolutional Neural Networks
ResNeXt, still suffers from the sub-optimal performance due to manually defining the number of groups as a constant over all of the layers.
Temporal Sequence Distillation: Towards Few-Frame Action Recognition in Videos
Secondly, TSD significantly reduces the computations to run video action recognition with compressed frames on the cloud, while maintaining high recognition accuracies.
Boosting up Scene Text Detectors with Guided CNN
Deep CNNs have achieved great success in text detection.
Performance Evaluation of Channel Decoding With Deep Neural Networks
With the demand of high data rate and low latency in fifth generation (5G), deep neural network decoder (NND) has become a promising candidate due to its capability of one-shot decoding and parallel computing.
