Search Results for author:
Found 54 papers, 14 papers with code
Anno-incomplete Multi-dataset Detection
Object detectors have shown outstanding performance on various public datasets.
VTON-HandFit: Virtual Try-on for Arbitrary Hand Pose Guided by Hand Priors Embedding
To tackle this issue widely existing in real-world scenarios, we propose VTON-HandFit, leveraging the power of hand priors to reconstruct the appearance and structure for hand occlusion cases.
The Llama 3 Herd of Models
This paper presents a new set of foundation models, called Llama 3.
Ranked #4 on
Multi-task Language Understanding
on MMLU
Wireless Communications in Doubly Selective Channels with Domain Adaptivity
Wireless communications are significantly impacted by the propagation environment, particularly in doubly selective channels with variations in both time and frequency domains.
Exploring Knowledge Transfer in Evolutionary Many-task Optimization: A Complex Network Perspective
The field of evolutionary many-task optimization (EMaTO) is increasingly recognized for its ability to streamline the resolution of optimization challenges with repetitive characteristics, thereby conserving computational resources.
AnyMaker: Zero-shot General Object Customization via Decoupled Dual-Level ID Injection
In addition, we propose an ID-aware decoupling module to disentangle ID-related information from non-ID elements in the extracted representations for high-fidelity generation of both identity and text descriptions.
NoiseBoost: Alleviating Hallucination with Noise Perturbation for Multimodal Large Language Models
Multimodal large language models (MLLMs) contribute a powerful mechanism to understanding visual information building on large language models.
Automated Loss function Search for Class-imbalanced Node Classification
Class-imbalanced node classification tasks are prevalent in real-world scenarios.
Efficient Multimodal Large Language Models: A Survey
In the past year, Multimodal Large Language Models (MLLMs) have demonstrated remarkable performance in tasks such as visual question answering, visual understanding and reasoning.
GLHF: General Learned Evolutionary Algorithm Via Hyper Functions
Pretrained Optimization Models (POMs) leverage knowledge gained from optimizing various tasks, providing efficient solutions for new optimization challenges through direct usage or fine-tuning.
HCPM: Hierarchical Candidates Pruning for Efficient Detector-Free Matching
Deep learning-based image matching methods play a crucial role in computer vision, yet they often suffer from substantial computational demands.
Sensing in Bi-Static ISAC Systems with Clock Asynchronism: A Signal Processing Perspective
Integrated Sensing and Communication (ISAC) has been identified as a pillar usage scenario for the impending 6G era.
UniM-OV3D: Uni-Modality Open-Vocabulary 3D Scene Understanding with Fine-Grained Feature Representation
3D open-vocabulary scene understanding aims to recognize arbitrary novel categories beyond the base label space.
Unsupervised Continual Anomaly Detection with Contrastively-learned Prompt
Unsupervised Anomaly Detection (UAD) with incremental training is crucial in industrial manufacturing, as unpredictable defects make obtaining sufficient labeled data infeasible.
Signed Graph Neural Ordinary Differential Equation for Modeling Continuous-time Dynamics
Modeling continuous-time dynamics constitutes a foundational challenge, and uncovering inter-component correlations within complex systems holds promise for enhancing the efficacy of dynamic modeling.
Active Noise Control Portable Device Design
Then the noise will be sent to an electronic control system to process the noise, which will generate a reverse phase frequency signal to counteract the disturbance.
EMOFM: Ensemble MLP mOdel with Feature-based Mixers for Click-Through Rate Prediction
WARNING: The comparison might not be fair enough since the proposed method is designed for this data in particular while compared methods are not.
SPELL: Semantic Prompt Evolution based on a LLM
Prompt engineering is a new paradigm for enhancing the performance of trained neural network models.
Machine learning of network inference enhancement from noisy measurements
Inferring networks from observed time series data presents a clear glimpse into the interconnections among nodes.
IIDM: Inter and Intra-domain Mixing for Semi-supervised Domain Adaptation in Semantic Segmentation
In this paper, we highlight the significance of exploiting the intra-domain information between the labeled target data and unlabeled target data.
A Unified Framework for Online Data-Driven Predictive Control with Robust Safety Guarantees
Despite great successes, model predictive control (MPC) relies on an accurate dynamical model and requires high onboard computational power, impeding its wider adoption in engineering systems, especially for nonlinear real-time systems with limited computation power.
Pre-trained transformer for adversarial purification
It is frightening that deep neural networks are vulnerable and sensitive to adversarial attacks, the most common one of which for the services is evasion-based.
B2Opt: Learning to Optimize Black-box Optimization with Little Budget
To achieve this, 1) drawing on the mechanism of genetic algorithm, we propose a deep neural network framework called B2Opt, which has a stronger representation of optimization strategies based on survival of the fittest; 2) B2Opt can utilize the cheap surrogate functions of the target task to guide the design of the efficient optimization strategies.
DECN: Automated Evolutionary Algorithms via Evolution Inspired Deep Convolution Network
Evolutionary algorithms (EAs) have emerged as a powerful framework for optimization, especially for black-box optimization.
A Self-attention Knowledge Domain Adaptation Network for Commercial Lithium-ion Batteries State-of-health Estimation under Shallow Cycles
Accurate state-of-health (SOH) estimation is critical to guarantee the safety, efficiency and reliability of battery-powered applications.
Transferable Deep Learning Power System Short-Term Voltage Stability Assessment with Physics-Informed Topological Feature Engineering
In particular, the highest accuracy reaches 99. 68\% in evaluation, which demonstrates a good knowledge transfer ability of the proposed model for power grid topology change.
Practical Frequency-Hopping MIMO Joint Radar Communications: Design and Experiment
Joint radar and communications (JRC) can realize two radio frequency (RF) functions using one set of resources, greatly saving hardware, energy and spectrum for wireless systems needing both functions.
Discover governing differential equations from evolving systems
Our proposal is competitive in identifying the change points and discovering governing differential equations in three hybrid systems and two switching linear systems.
Higher-order Knowledge Transfer for Dynamic Community Detection with Great Changes
In this way, our proposal can better keep the advantages of previous community detection results and transfer them to the next task.
Frequency and Amplitude Optimizations for Magnetic Particle Spectroscopy Applications
Nowadays, there is a growing interest in the field of magnetic particle spectroscopy (MPS)-based bioassays.
DIICAN: Dual Time-scale State-Coupled Co-estimation of SOC, SOH and RUL for Lithium-Ion Batteries
A state-coupled co-estimation method named Deep Inter and Intra-Cycle Attention Network (DIICAN) is proposed in this paper to estimate SOC, SOH, and RUL, which organizes battery measurement data into the intra-cycle and inter-cycle time scales.
Rethinking Dimensionality Reduction in Grid-based 3D Object Detection
In MDRNet, the Spatial-aware Dimensionality Reduction (SDR) is designed to dynamically focus on the valuable parts of the object during voxel-to-BEV feature transformation.
Green Joint Communications and Sensing Employing Analog Multi-Beam Antenna Arrays
Most existing JCAS designs are based on digital arrays, analog arrays with tunable phase shifters, or hybrid arrays, which are effective but are generally complicated to design and power inefficient.
Joint Communications and Sensing Employing Optimized MIMO-OFDM Signals
We establish an optimization problem that modifies data symbols on sub-carriers to enhance the above-mentioned signal orthogonality.
Simultaneous Beam and User Selection for the Beamspace mmWave/THz Massive MIMO Downlink
We then exploit its beneficial properties for substantially simplifying the joint user and beam selection problem.
A Multi-Transformation Evolutionary Framework for Influence Maximization in Social Networks
Influence maximization is a crucial issue for mining the deep information of social networks, which aims to select a seed set from the network to maximize the number of influenced nodes.
Integration of Radar Sensing into Communications with Asynchronous Transceivers
Clock asynchronism is a critical issue in integrating radar sensing into communication networks.
Fast and Accurate Linear Fitting for Incompletely Sampled Gaussian Function With a Long Tail
Fitting experiment data onto a curve is a common signal processing technique to extract data features and establish the relationship between variables.
Class-Aware Contrastive Semi-Supervised Learning
Pseudo-label-based semi-supervised learning (SSL) has achieved great success on raw data utilization.
Learning Multi-Task Gaussian Process Over Heterogeneous Input Domains
Multi-task Gaussian process (MTGP) is a well-known non-parametric Bayesian model for learning correlated tasks effectively by transferring knowledge across tasks.
Network Collaborator: Knowledge Transfer Between Network Reconstruction and Community Detection
Community detection (CD) from dynamics and network reconstruction (NR) from dynamics are natural synergistic tasks that motivate the proposed evolutionary multitasking NR and CD framework, called network collaborator (NC).
Evolutionary Multitasking AUC Optimization
Inspired by the characteristic of pairwise learning, the cheap AUC optimization task with a small-scale dataset sampled from the large-scale dataset is constructed to promote the AUC accuracy of the original, large-scale, and expensive AUC optimization task.
Boost Distribution System Restoration with Emergency Communication Vehicles Considering Cyber-Physical Interdependence
Enhancing restoration capabilities of distribution systems is one of the main strategies for resilient power systems to cope with extreme events.
OTFS-Based Joint Communication and Sensing for Future Industrial IoT
To meet the ever-increasing demands on better wireless communications for IIoT, we propose an orthogonal time-frequency space (OTFS) waveform-based joint communication and radio sensing (JCAS) scheme -- an energy-efficient solution for not only reliable communications but also high-accuracy sensing.
Integrating Low-Complexity and Flexible Sensing into Communication Systems
Extensive simulations validate the superiority of the proposed sensing framework over prior methods in terms of signal-to-IN ratios in RDMs, detecting performance and flexibility.
One-step, Wash-free, Nanoparticle Clustering-based Magnetic Particle Spectroscopy (MPS) Bioassay Method for Detection of SARS-CoV-2 Spike and Nucleocapsid Proteins in Liquid Phase
With the ongoing global pandemic of coronavirus disease 2019 (COVID-19), there is an increasing quest for more accessible, easy-to-use, rapid, inexpensive, and high accuracy diagnostic tools.
Accurate Frequency Estimation with Fewer DFT Interpolations based on Padé Approximation
Frequency estimation is a fundamental problem in many areas.
A Low-Complexity Method for FFT-based OFDM Sensing
OFDM sensing is gaining increasing popularity in wideband radar applications as well as in joint communication and radar/radio sensing (JCAS).
Frequency-Hopping MIMO Radar-Based Communications: An Overview
Enabled by the advancement in radio frequency technologies, the convergence of radar and communication systems becomes increasingly promising and is envisioned as a key feature of future 6G networks.
Waveform Design and Accurate Channel Estimation for Frequency-Hopping MIMO Radar-Based Communications
In this paper, we develop accurate methods for a single-antenna communication receiver to estimate timing offset and channel for FH-MIMO DFRC.
Integrating Secure and High-Speed Communications into Frequency Hopping MIMO Radar
How to enhance the physical layer security of FH-MIMO DFRC is vital yet unsolved.
Enabling Joint Communication and Radar Sensing in Mobile Networks -- A Survey
We then introduce a framework of PMN, including the system platform and infrastructure, three types of sensing operations, and signals usable for sensing.
Learning to Generate Time Series Conditioned Graphs with Generative Adversarial Nets
Differently, in this paper, we are interested in a novel problem named Time Series Conditioned Graph Generation: given an input multivariate time series, we aim to infer a target relation graph modeling the underlying interrelationships between time series with each node corresponding to each time series.
