Search Results for author:
Found 96 papers, 29 papers with code
Initial Model Incorporation for Deep Learning FWI: Pretraining or Denormalization?
There are primarily two ways to embed the prior knowledge of the initial model into neural networks, that is, pretraining and denormalization.
Fog Intelligence for Network Anomaly Detection
However, the growing scale and complexity of the mobile communication networks, as well as the ever-increasing amount and dimensionality of the network surveillance data, make it extremely difficult to monitor a mobile network and discover abnormal network behaviors.
MetaSTNet: Multimodal Meta-learning for Cellular Traffic Conformal Prediction
Network traffic prediction techniques have attracted much attention since they are valuable for network congestion control and user experience improvement.
Cellular Traffic Prediction via Byzantine-robust Asynchronous Federated Learning
Developing a robust and privacy-preserving prediction model in the presence of Byzantine clients remains a significant challenge.
Exploration by Random Distribution Distillation
RDD facilitates a more extensive exploration by explicitly treating the difference between the prediction network and the target network as an intrinsic reward.
Argus: Federated Non-convex Bilevel Learning over 6G Space-Air-Ground Integrated Network
The space-air-ground integrated network (SAGIN) has recently emerged as a core element in the 6G networks.
Contextures: Representations from Contexts
Specifically, we show that many popular methods aim to approximate the top-d singular functions of the expectation operator induced by the context, in which case we say that the representation learns the contexture.
PR-Attack: Coordinated Prompt-RAG Attacks on Retrieval-Augmented Generation in Large Language Models via Bilevel Optimization
To address these issues, we propose coordinated Prompt-RAG attack (PR-attack), a novel optimization-driven attack that introduces a small number of poisoned texts into the knowledge database while embedding a backdoor trigger within the prompt.
Adaptive Group Policy Optimization: Towards Stable Training and Token-Efficient Reasoning
Since DeepSeek-R1 popularized, Group Relative Policy Optimization (GRPO) has become the core part of training Reasoning LLMs.
LMM-R1: Empowering 3B LMMs with Strong Reasoning Abilities Through Two-Stage Rule-Based RL
Enhancing reasoning in Large Multimodal Models (LMMs) faces unique challenges from the complex interplay between visual perception and logical reasoning, particularly in compact 3B-parameter architectures where architectural constraints limit reasoning capacity and modality alignment.
RGB-Phase Speckle: Cross-Scene Stereo 3D Reconstruction via Wrapped Pre-Normalization
3D reconstruction garners increasing attention alongside the advancement of high-level image applications, where dense stereo matching (DSM) serves as a pivotal technique.
An Algorithm Board in Neural Decoding
Understanding the mechanisms of neural encoding and decoding has always been a highly interesting research topic in fields such as neuroscience and cognitive intelligence.
Affine Frequency Division Multiplexing: Extending OFDM for Scenario-Flexibility and Resilience
Next-generation wireless networks are conceived to provide reliable and high-data-rate communication services for diverse scenarios, such as vehicle-to-vehicle, unmanned aerial vehicles, and satellite networks.
Learning to Synthesize Compatible Fashion Items Using Semantic Alignment and Collocation Classification: An Outfit Generation Framework
The field of fashion compatibility learning has attracted great attention from both the academic and industrial communities in recent years.
Novelty-Guided Data Reuse for Efficient and Diversified Multi-Agent Reinforcement Learning
Recently, deep Multi-Agent Reinforcement Learning (MARL) has demonstrated its potential to tackle complex cooperative tasks, pushing the boundaries of AI in collaborative environments.
Unlocking TriLevel Learning with Level-Wise Zeroth Order Constraints: Distributed Algorithms and Provable Non-Asymptotic Convergence
The proposed DTZO is versatile and can be adapted to a wide range of (grey-box) TLL problems with partial zeroth order constraints.
How Numerical Precision Affects Mathematical Reasoning Capabilities of LLMs
Despite the remarkable success of Transformer-based Large Language Models (LLMs) across various domains, understanding and enhancing their mathematical capabilities remains a significant challenge.
Novelty-based Sample Reuse for Continuous Robotics Control
In reinforcement learning, agents collect state information and rewards through environmental interactions, essential for policy refinement.
fastHDMI: Fast Mutual Information Estimation for High-Dimensional Data
Our results highlight the superiority of the FFTKDE-based mutual information estimation for feature screening in continuous nonlinear outcomes, while binning-based methods outperform others for binary outcomes with nonlinear probability preimages.
Tri-Level Navigator: LLM-Empowered Tri-Level Learning for Time Series OOD Generalization
Out-of-Distribution (OOD) generalization in machine learning is a burgeoning area of study.
SGFormer: Single-Layer Graph Transformers with Approximation-Free Linear Complexity
Learning representations on large graphs is a long-standing challenge due to the inter-dependence nature.
Distilling High Diagnostic Value Patches for Whole Slide Image Classification Using Attention Mechanism
However, a drawback of such methods is the incorporation of more redundant patches, leading to interference.
Contributions to Robust and Efficient Methods for Analysis of High-Dimensional Data
For correlated observations, this qGaussian model enhances the robustness and flexibility of statistical analyses, providing a more comprehensive tool for modeling the widely-correlated observations frequently encountered in biological and medical studies. Collectively, these contributions aim at addressing the multifaceted challenges of high–dimensional biological data analysis and paving the way for deeper insights into complex biological systems by seamlessly integrating solutions to nonlinearity, nonconvex nonsmooth optimization, and the need for more robust and adaptable models
A Two-stage Reinforcement Learning-based Approach for Multi-entity Task Allocation
Compared to heuristic algorithms like genetic algorithms, our reinforcement learning approach better solves dynamic allocation problems and achieves zero-shot generalization to new tasks with good performance.
Learning Multi-view Molecular Representations with Structured and Unstructured Knowledge
To address these issues, we present MV-Mol, a molecular representation learning model that harvests multi-view molecular expertise from chemical structures, unstructured knowledge from biomedical texts, and structured knowledge from knowledge graphs.
CDSA: Conservative Denoising Score-based Algorithm for Offline Reinforcement Learning
Distribution shift is a major obstacle in offline reinforcement learning, which necessitates minimizing the discrepancy between the learned policy and the behavior policy to avoid overestimating rare or unseen actions.
Triadic-OCD: Asynchronous Online Change Detection with Provable Robustness, Optimality, and Convergence
The primary goal of online change detection (OCD) is to promptly identify changes in the data stream.
Do Efficient Transformers Really Save Computation?
Our results show that while these models are expressive enough to solve general DP tasks, contrary to expectations, they require a model size that scales with the problem size.
BATON: Aligning Text-to-Audio Model with Human Preference Feedback
With the development of AI-Generated Content (AIGC), text-to-audio models are gaining widespread attention.
Two Stones Hit One Bird: Bilevel Positional Encoding for Better Length Extrapolation
In this work, we leverage the intrinsic segmentation of language sequences and design a new positional encoding method called Bilevel Positional Encoding (BiPE).
Exploration and Anti-Exploration with Distributional Random Network Distillation
To address this issue, we introduce the Distributional RND (DRND), a derivative of the RND.
Provably Convergent Federated Trilevel Learning
To address the aforementioned challenges, this paper proposes an asynchronous federated trilevel optimization method to solve TLO problems.
Gemini: A Family of Highly Capable Multimodal Models
This report introduces a new family of multimodal models, Gemini, that exhibit remarkable capabilities across image, audio, video, and text understanding.
Ranked #1 on
Visual Question Answering (VQA)
on InfographicVQA
UTBoost: Gradient Boosted Decision Trees for Uplift Modeling
Uplift modeling comprises a collection of machine learning techniques designed for managers to predict the incremental impact of specific actions on customer outcomes.
Using Human Feedback to Fine-tune Diffusion Models without Any Reward Model
The direct preference optimization (DPO) method, effective in fine-tuning large language models, eliminates the necessity for a reward model.
Few-Shot Recognition and Classification Framework for Jamming Signal: A CGAN-Based Fusion CNN Approach
Subject to intricate environmental variables, the precise classification of jamming signals holds paramount significance in the effective implementation of anti-jamming strategies within communication systems.
When Automated Assessment Meets Automated Content Generation: Examining Text Quality in the Era of GPTs
Interestingly, we find that the transformer PLMs tend to score GPT-generated text 10-15\% higher on average, relative to human-authored documents.
Lightning-Fast Dual-Layer Lossless Coding for Radiance Format High Dynamic Range Images
To suppress the dynamic range of the residuals in the enhancement layer, the coding directly uses the mantissa and exponent information from the Radiance format.
Local Structure-aware Graph Contrastive Representation Learning
Traditional Graph Neural Network (GNN), as a graph representation learning method, is constrained by label information.
Federated Distributionally Robust Optimization with Non-Convex Objectives: Algorithm and Analysis
Distributionally Robust Optimization (DRO), which aims to find an optimal decision that minimizes the worst case cost over the ambiguity set of probability distribution, has been widely applied in diverse applications, e. g., network behavior analysis, risk management, etc.
MolFM: A Multimodal Molecular Foundation Model
In this study, we introduce MolFM, a multimodal molecular foundation model designed to facilitate joint representation learning from molecular structures, biomedical texts, and knowledge graphs.
Ranked #10 on
Text-based de novo Molecule Generation
on ChEBI-20
ASM: Adaptive Skinning Model for High-Quality 3D Face Modeling
The research fields of parametric face model and 3D face reconstruction have been extensively studied.
Ranked #1 on
Face Alignment
on FaceScape
Towards Unified AI Drug Discovery with Multiple Knowledge Modalities
In recent years, AI models that mine intrinsic patterns from molecular structures and protein sequences have shown promise in accelerating drug discovery.
Bayesian Beta-Bernoulli Process Sparse Coding with Deep Neural Networks
Several approximate inference methods have been proposed for deep discrete latent variable models.
Unsupervised Deep Learning for IoT Time Series
IoT time series analysis has found numerous applications in a wide variety of areas, ranging from health informatics to network security.
Asynchronous Distributed Bilevel Optimization
Bilevel optimization plays an essential role in many machine learning tasks, ranging from hyperparameter optimization to meta-learning.
AI Empowered Net-RCA for 6G
6G is envisioned to offer higher data rate, improved reliability, ubiquitous AI services, and support massive scale of connected devices.
SOTIF Entropy: Online SOTIF Risk Quantification and Mitigation for Autonomous Driving
Therefore, this paper proposes the "Self-Surveillance and Self-Adaption System" as a systematic approach to online minimize the SOTIF risk, which aims to provide a systematic solution for monitoring, quantification, and mitigation of inherent and external risks.
Distributed Distributionally Robust Optimization with Non-Convex Objectives
Distributionally Robust Optimization (DRO), which aims to find an optimal decision that minimizes the worst case cost over the ambiguity set of probability distribution, has been widely applied in diverse applications, e. g., network behavior analysis, risk management, etc.
SIND: A Drone Dataset at Signalized Intersection in China
Then, the behaviors of traffic light violations in SIND are recorded.
ADTR: Anomaly Detection Transformer with Feature Reconstruction
Second, CNN tends to reconstruct both normal samples and anomalies well, making them still hard to distinguish.
Trustworthy Federated Learning via Blockchain
In this paper, we shall propose a decentralized blockchain based FL (B-FL) architecture by using a secure global aggregation algorithm to resist malicious devices, and deploying practical Byzantine fault tolerance consensus protocol with high effectiveness and low energy consumption among multiple edge servers to prevent model tampering from the malicious server.
Task-aware Similarity Learning for Event-triggered Time Series
The proposed framework aspires to offer a stepping stone that gives rise to a systematic approach to model and learn similarities among a multitude of event-triggered time series.
A Holistic Robust Motion Controller Framework for Autonomous Platooning
The output from UCL will be delivered to the lower-level motion-planning layer (LML) as reference signals.
A Unified Model for Multi-class Anomaly Detection
For example, when learning a unified model for 15 categories in MVTec-AD, we surpass the second competitor on the tasks of both anomaly detection (from 88. 1% to 96. 5%) and anomaly localization (from 89. 5% to 96. 8%).
Ranked #13 on
Multi-class Anomaly Detection
on MVTec AD
Heterogeneous Ultra-Dense Networks with Traffic Hotspots: A Unified Handover Analysis
By combining the PCP and MRWP model, the distributions of distances from a typical terminal to the BSs in different tiers are derived.
FedGBF: An efficient vertical federated learning framework via gradient boosting and bagging
With the aim of obtaining an outstanding performance with less time cost, we propose a novel model in a vertically federated setting termed as Federated Gradient Boosting Forest (FedGBF).
Few-shot Object Counting with Similarity-Aware Feature Enhancement
This work studies the problem of few-shot object counting, which counts the number of exemplar objects (i. e., described by one or several support images) occurring in the query image.
Ranked #2 on
Object Counting
on CARPK
Arbitrary Handwriting Image Style Transfer
This paper proposed a method to imitate handwriting style by style transfer.
Efficient Batch Homomorphic Encryption for Vertically Federated XGBoost
In this paper, we studied the efficiency problem of adapting widely used XGBoost model in real-world applications to vertical federated learning setting.
Fed-EINI: An Efficient and Interpretable Inference Framework for Decision Tree Ensembles in Federated Learning
With this key observation, we protect data privacy and allow the disclosure of feature meaning by concealing decision paths and adapt a communication-efficient secure computation method for inference outputs.
SiamCorners: Siamese Corner Networks for Visual Tracking
By tracking a target as a pair of corners, we avoid the need to design the anchor boxes.
A High-fidelity, Machine-learning Enhanced Queueing Network Simulation Model for Hospital Ultrasound Operations
To address the issue, we propose a novel two-level routing component to the queueing network model.
Interaction with an obstacle in the 2d focusing nonlinear Schrödinger equation
Moreover, we show that the sharp threshold for global existence vs. finite time blow-up solutions in the mass critical case in the presence of the obstacle is the same as the one given by Weinstein for {\rm{NLS}} in the whole Euclidean space $\R^d$.
Analysis of PDEs Numerical Analysis Numerical Analysis
Waveform Optimization with Multiple Performance Metrics for Broadband Joint Communication and Radar Sensing
For radar sensing, we consider optimizing one of two metrics, the mutual information or the Cramer-Rao bound.
Uplink Sensing in Perceptive Mobile Networks with Asynchronous Transceivers
We first adopt a cross-antenna cross-correlation (CACC) operation to remove the sensing ambiguity associated with both TOs and CFOs.
TimeAutoML: Autonomous Representation Learning for Multivariate Irregularly Sampled Time Series
To this end, we propose an autonomous representation learning approach for multivariate time series (TimeAutoML) with irregular sampling rates and variable lengths.
Accelerated Gradient Methods for Sparse Statistical Learning with Nonconvex Penalties
A recent proposal generalizes Nesterov's AG method to the nonconvex setting.
LSOTB-TIR:A Large-Scale High-Diversity Thermal Infrared Object Tracking Benchmark
We evaluate and analyze more than 30 trackers on LSOTB-TIR to provide a series of baselines, and the results show that deep trackers achieve promising performance.
A Semantics-Guided Graph Convolutional Network for Skeleton-Based Action Recognition
Action recognition with skeleton data is a challenging task in computer vision.
Ranked #87 on
Skeleton Based Action Recognition
on NTU RGB+D
Communication-Efficient Edge AI Inference Over Wireless Networks
Given the fast growth of intelligent devices, it is expected that a large number of high-stake artificial intelligence (AI) applications, e. g., drones, autonomous cars, tactile robots, will be deployed at the edge of wireless networks in the near future.
Federated Machine Learning for Intelligent IoT via Reconfigurable Intelligent Surface
Intelligent Internet-of-Things (IoT) will be transformative with the advancement of artificial intelligence and high-dimensional data analysis, shifting from "connected things" to "connected intelligence".
Weak Radio Frequency Signal Detection Based on Piezo-Opto-Electro-Mechanical System: Architecture Design and Sensitivity Prediction
We propose a novel radio-frequency (RF) receiving architecture based on micro-electro-mechanical system (MEMS) and optical coherent detection module.
Communication-Efficient Edge AI: Algorithms and Systems
By pushing inference and training processes of AI models to edge nodes, edge AI has emerged as a promising alternative.
A Quasi-Newton Method Based Vertical Federated Learning Framework for Logistic Regression
Our approach can considerably reduce the number of communication rounds with a little additional communication cost per round.
An Attention-Enhanced Recurrent Graph Convolutional Network for Skeleton-Based Action Recognition
Dynamic movements of human skeleton have attracted more and more attention as a robust modality for action recognition.
Inexact Primal-Dual Gradient Projection Methods for Nonlinear Optimization on Convex Set
In this paper, we propose a novel primal-dual inexact gradient projection method for nonlinear optimization problems with convex-set constraint.
Hybrid Beamforming for Terahertz Multi-Carrier Systems over Frequency Selective Fading
We consider a three-dimensional wideband THz channel by incorporating the joint effect of molecular absorption, high sparsity, and multi-path fading, and consider the carrier frequency offset in multi-carrier systems.
Energy-Efficient Processing and Robust Wireless Cooperative Transmission for Edge Inference
Edge machine learning can deliver low-latency and private artificial intelligent (AI) services for mobile devices by leveraging computation and storage resources at the network edge.
Group-wise Correlation Stereo Network
Previous works built cost volumes with cross-correlation or concatenation of left and right features across all disparity levels, and then a 2D or 3D convolutional neural network is utilized to regress the disparity maps.
Federated Learning via Over-the-Air Computation
Instead, edge machine learning becomes increasingly attractive for performing training and inference directly at network edges without sending data to a centralized data center.
Multi-task Prediction of Patient Workload
This issue becomes more critical for the healthcare facilities that provide service for chronic disease treatment because of the need for continuous treatments over the time.
Effective Feature Learning with Unsupervised Learning for Improving the Predictive Models in Massive Open Online Courses
A major challenge that has to be addressed when building such models is to design handcrafted features that are effective for the prediction task at hand.
SyntaxSQLNet: Syntax Tree Networks for Complex and Cross-DomainText-to-SQL Task
In this paper we propose SyntaxSQLNet, a syntax tree network to address the complex and cross-domain text-to-SQL generation task.
Ranked #7 on
Text-To-SQL
on SParC
SyntaxSQLNet: Syntax Tree Networks for Complex and Cross-Domain Text-to-SQL Task
In this paper we propose SyntaxSQLNet, a syntax tree network to address the complex and cross-domain text-to-SQL generation task.
Spider: A Large-Scale Human-Labeled Dataset for Complex and Cross-Domain Semantic Parsing and Text-to-SQL Task
We define a new complex and cross-domain semantic parsing and text-to-SQL task where different complex SQL queries and databases appear in train and test sets.
Ranked #10 on
Semantic Parsing
on spider
Active Learning for Wireless IoT Intrusion Detection
This paper discusses the human-in-the-loop active learning approach for wireless intrusion detection.
Incorporating Features Learned by an Enhanced Deep Knowledge Tracing Model for STEM/Non-STEM Job Prediction
The 2017 ASSISTments Data Mining competition aims to use data from a longitudinal study for predicting a brand-new outcome of students which had never been studied before by the educational data mining research community.
A Deep Active Survival Analysis Approach for Precision Treatment Recommendations: Application of Prostate Cancer
Survival analysis has been developed and applied in the number of areas including manufacturing, finance, economics and healthcare.
SUBIC: A Supervised Bi-Clustering Approach for Precision Medicine
Traditional medicine typically applies one-size-fits-all treatment for the entire patient population whereas precision medicine develops tailored treatment schemes for different patient subgroups.
Deep Stock Representation Learning: From Candlestick Charts to Investment Decisions
We propose a novel investment decision strategy (IDS) based on deep learning.
Computational Finance
SAFS: A Deep Feature Selection Approach for Precision Medicine
In this paper, we propose a new deep feature selection method based on deep architecture.
Autoencoder Regularized Network For Driving Style Representation Learning
In this paper, we study learning generalized driving style representations from automobile GPS trip data.
Exploring Topic Discriminating Power of Words in Latent Dirichlet Allocation
Latent Dirichlet Allocation (LDA) and its variants have been widely used to discover latent topics in textual documents.
Predicting patient risk of readmission with frailty models in the Department of Veteran Affairs
Reducing potentially preventable readmissions has been identified as an important issue for decreasing Medicare costs and improving quality of care provided by hospitals.
Applications 62N01, 62N02, 62P10
A predictive analytics approach to reducing avoidable hospital readmission
We further propose a tree based classification method to estimate the predicted probability of readmission that can directly incorporate patient's history of readmission and risk factors changes over time.
