Search Results for author:
Found 114 papers, 44 papers with code
Personalized Entity Resolution with Dynamic Heterogeneous KnowledgeGraph Representations
We first build a cross-source heterogeneous knowledge graph from customer purchase history and product knowledge graph to jointly learn customer and product embeddings.
Incorporating Instructional Prompts into a Unified Generative Framework for Joint Multiple Intent Detection and Slot Filling
Specifically, we design 5-type templates as instructional prompts, and each template includes a question that acts as the driver to teach UGEN to grasp the paradigm, options that list the candidate intents or slots to reduce the answer search space, and the context denotes original utterance.
Resistive Memory-based Neural Differential Equation Solver for Score-based Diffusion Model
Demonstrating equivalent generative quality to the software baseline, our system achieved remarkable enhancements in generative speed for both unconditional and conditional generation tasks, by factors of 64. 8 and 156. 5, respectively.
Integrating AI in NDE: Techniques, Trends, and Further Directions
Since we cannot discuss each NDE modality in one paper, we limit our attention to magnetic methods, ultrasound, thermography, as well as optical inspection.
Elysium: Exploring Object-level Perception in Videos via MLLM
Multi-modal Large Language Models (MLLMs) have demonstrated their ability to perceive objects in still images, but their application in video-related tasks, such as object tracking, remains understudied.
Ranked #1 on
Zero-Shot Single Object Tracking
on LaSOT
A Simple Mixture Policy Parameterization for Improving Sample Efficiency of CVaR Optimization
Reinforcement learning algorithms utilizing policy gradients (PG) to optimize Conditional Value at Risk (CVaR) face significant challenges with sample inefficiency, hindering their practical applications.
Efficient Convolutional Forward Modeling and Sparse Coding in Multichannel Imaging
This study considers the Block-Toeplitz structural properties inherent in traditional multichannel forward model matrices, using Full Matrix Capture (FMC) in ultrasonic testing as a case study.
A Multimodal Fusion Network For Student Emotion Recognition Based on Transformer and Tensor Product
In recent years, there have been frequent incidents of foreign objects intruding into railway and Airport runways.
Schema-Aware Multi-Task Learning for Complex Text-to-SQL
Conventional text-to-SQL parsers are not good at synthesizing complex SQL queries that involve multiple tables or columns, due to the challenges inherent in identifying the correct schema items and performing accurate alignment between question and schema items.
Emerging Synergies Between Large Language Models and Machine Learning in Ecommerce Recommendations
With the boom of e-commerce and web applications, recommender systems have become an important part of our daily lives, providing personalized recommendations based on the user's preferences.
Jointly Learning Selection Matrices For Transmitters, Receivers And Fourier Coefficients In Multichannel Imaging
Strategic subsampling has become a focal point due to its effectiveness in compressing data, particularly in the Full Matrix Capture (FMC) approach in ultrasonic imaging.
Beyond Accuracy: An Empirical Study on Unit Testing in Open-source Deep Learning Projects
Deep Learning (DL) models have rapidly advanced, focusing on achieving high performance through testing model accuracy and robustness.
Hierarchical Speed Planner for Automated Vehicles: A Framework for Lagrangian Variable Speed Limit in Mixed Autonomy Traffic
The Speed Planner comprises two modules: a TSE enhancement module and a target speed design module.
Traffic Control via Connected and Automated Vehicles: An Open-Road Field Experiment with 100 CAVs
The upper layer is called Speed Planner, and is a centralized optimal control algorithm.
MemeCraft: Contextual and Stance-Driven Multimodal Meme Generation
Online memes have emerged as powerful digital cultural artifacts in the age of social media, offering not only humor but also platforms for political discourse, social critique, and information dissemination.
Self-Distillation Bridges Distribution Gap in Language Model Fine-Tuning
The surge in Large Language Models (LLMs) has revolutionized natural language processing, but fine-tuning them for specific tasks often encounters challenges in balancing performance and preserving general instruction-following abilities.
Soft Self-Consistency Improves Language Model Agents
Current "sample and select" methods such as self-consistency (SC) rely on majority voting to score answers.
Chinese MentalBERT: Domain-Adaptive Pre-training on Social Media for Chinese Mental Health Text Analysis
To address this, we have collected a huge dataset from Chinese social media platforms and enriched it with publicly available datasets to create a comprehensive database encompassing 3. 36 million text entries.
Mesoscale Traffic Forecasting for Real-Time Bottleneck and Shockwave Prediction
Accurate real-time traffic state forecasting plays a pivotal role in traffic control research.
MMAUD: A Comprehensive Multi-Modal Anti-UAV Dataset for Modern Miniature Drone Threats
In response to the evolving challenges posed by small unmanned aerial vehicles (UAVs), which possess the potential to transport harmful payloads or independently cause damage, we introduce MMAUD: a comprehensive Multi-Modal Anti-UAV Dataset.
Finite-Time Analysis of On-Policy Heterogeneous Federated Reinforcement Learning
In response, we introduce FedSARSA, a novel federated on-policy reinforcement learning scheme, equipped with linear function approximation, to address these challenges and provide a comprehensive finite-time error analysis.
Meta-Learning Linear Quadratic Regulators: A Policy Gradient MAML Approach for the Model-free LQR
We investigate the problem of learning Linear Quadratic Regulators (LQR) in a multi-task, heterogeneous, and model-free setting.
GloTSFormer: Global Video Text Spotting Transformer
In this paper, we propose a novel Global Video Text Spotting Transformer GloTSFormer to model the tracking problem as global associations and utilize the Gaussian Wasserstein distance to guide the morphological correlation between frames.
Prompting Large Language Models for Topic Modeling
Topic modeling is a widely used technique for revealing underlying thematic structures within textual data.
PromptMTopic: Unsupervised Multimodal Topic Modeling of Memes using Large Language Models
The proliferation of social media has given rise to a new form of communication: memes.
TLM: Token-Level Masking for Transformers
Structured dropout approaches, such as attention dropout and DropHead, have been investigated to regularize the multi-head attention mechanism in Transformers.
Efficient Numerical Algorithm for Large-Scale Damped Natural Gradient Descent
We propose a new algorithm for efficiently solving the damped Fisher matrix in large-scale scenarios where the number of parameters significantly exceeds the number of available samples.
Oracle Complexity Reduction for Model-free LQR: A Stochastic Variance-Reduced Policy Gradient Approach
We investigate the problem of learning an $\epsilon$-approximate solution for the discrete-time Linear Quadratic Regulator (LQR) problem via a Stochastic Variance-Reduced Policy Gradient (SVRPG) approach.
Stochastic Optimization of Coupled Power Distribution-Urban Transportation Network Operations with Autonomous Mobility on Demand Systems
Then, a bi-level power-traffic flow (PTF) model is proposed to characterize the interaction of power distribution networks (PDNs) and urban transportation networks (UTNs).
Contracting with Heterogeneous Researchers
We study the design of contracts that incentivize a researcher to conduct a costly experiment, extending the work of Yoder (2022) from binary states to a general state space.
Measuring and Mitigating Interference in Reinforcement Learning
Lastly, we outline a class of algorithms which we call online-aware that are designed to mitigate interference, and show they do reduce interference according to our measure and that they improve stability and performance in several classic control environments.
CA-CentripetalNet: A novel anchor-free deep learning framework for hardhat wearing detection
Automatic hardhat wearing detection can strengthen the safety management in construction sites, which is still challenging due to complicated video surveillance scenes.
Clickbait Detection via Large Language Models
Clickbait, which aims to induce users with some surprising and even thrilling headlines for increasing click-through rates, permeates almost all online content publishers, such as news portals and social media.
MCPI: Integrating Multimodal Data for Enhanced Prediction of Compound Protein Interactions
The identification of compound-protein interactions (CPI) plays a critical role in drug screening, drug repurposing, and combination therapy studies.
Look Beneath the Surface: Exploiting Fundamental Symmetry for Sample-Efficient Offline RL
Based on extensive experiments, we find TSRL achieves great performance on small benchmark datasets with as few as 1% of the original samples, which significantly outperforms the recent offline RL algorithms in terms of data efficiency and generalizability. Code is available at: https://github. com/pcheng2/TSRL
Evaluating GPT-3 Generated Explanations for Hateful Content Moderation
A key concern is that these explanations, generated by LLMs, may lead to erroneous judgments about the nature of flagged content by both users and content moderators.
Hierarchical Game for Coupled Power System with Energy Sharing and Transportation System
This necessitates new business models in the power sector to hedge against uncertainties while imposing a strong coupling between the connected power and transportation networks.
Generation of 3D Molecules in Pockets via Language Model
Generative models for molecules based on sequential line notation (e. g.
Replay Memory as An Empirical MDP: Combining Conservative Estimation with Experience Replay
In this work, we further exploit the information in the replay memory by treating it as an empirical \emph{Replay Memory MDP (RM-MDP)}.
MMRDN: Consistent Representation for Multi-View Manipulation Relationship Detection in Object-Stacked Scenes
Manipulation relationship detection (MRD) aims to guide the robot to grasp objects in the right order, which is important to ensure the safety and reliability of grasping in object stacked scenes.
Side Channel-Assisted Inference Leakage from Machine Learning-based ECG Classification
In particular, we first identify the vulnerability of DTW for ECG classification, i. e., the correlation between warping path choice and prediction results.
Learning Personalized Models with Clustered System Identification
We address the problem of learning linear system models from observing multiple trajectories from different system dynamics.
Distributed Safe Control Design and Safety Verification for Multi-Agent Systems
Both the scenario sampling and safety verification procedures are fully distributed.
The In-Sample Softmax for Offline Reinforcement Learning
We highlight a simple fact: it is more straightforward to approximate an in-sample \emph{softmax} using only actions in the dataset.
Comparison and Analysis of Cognitive Load under 2D/3D Visual Stimuli
However, for videos that involve calculation tasks (P > 0. 05), the difference in cognitive load induced by 2D and 3D stimuli is not as pronounced.
Cooperative Driving for Speed Harmonization in Mixed-Traffic Environments
Autonomous driving systems present promising methods for congestion mitigation in mixed autonomy traffic control settings.
Federated Temporal Difference Learning with Linear Function Approximation under Environmental Heterogeneity
We initiate the study of federated reinforcement learning under environmental heterogeneity by considering a policy evaluation problem.
Robust Markov Decision Processes without Model Estimation
Moreover, we prove the alternative form still plays a similar role as the original form.
WINNER: Weakly-Supervised hIerarchical decompositioN and aligNment for Spatio-tEmporal Video gRounding
WINNER first builds the language decomposition tree in a bottom-up manner, upon which the structural attention mechanism and top-down feature backtracking jointly build a multi-modal decomposition tree, permitting a hierarchical understanding of unstructured videos.
GWRBoost:A geographically weighted gradient boosting method for explainable quantification of spatially-varying relationships
The geographically weighted regression (GWR) is an essential tool for estimating the spatial variation of relationships between dependent and independent variables in geographical contexts.
FedSysID: A Federated Approach to Sample-Efficient System Identification
We study the problem of learning a linear system model from the observations of $M$ clients.
Few-Shot Character Understanding in Movies as an Assessment to Meta-Learning of Theory-of-Mind
Our dataset consists of ~1, 000 parsed movie scripts, each corresponding to a few-shot character understanding task that requires models to mimic humans' ability of fast digesting characters with a few starting scenes in a new movie.
BLOOM: A 176B-Parameter Open-Access Multilingual Language Model
Large language models (LLMs) have been shown to be able to perform new tasks based on a few demonstrations or natural language instructions.
Language Model Pre-Training with Sparse Latent Typing
Modern large-scale Pre-trained Language Models (PLMs) have achieved tremendous success on a wide range of downstream tasks.
Ranked #6 on
Few-shot NER
on Few-NERD (INTRA)
(using extra training data)
Causal Inference via Nonlinear Variable Decorrelation for Healthcare Applications
Causal inference and model interpretability research are gaining increasing attention, especially in the domains of healthcare and bioinformatics.
Deep Variational Free Energy Approach to Dense Hydrogen
We developed a deep generative model-based variational free energy approach to the equations of state of dense hydrogen.
PTSEFormer: Progressive Temporal-Spatial Enhanced TransFormer Towards Video Object Detection
The temporal information is introduced by the temporal feature aggregation model (TFAM), by conducting an attention mechanism between the context frames and the target frame (i. e., the frame to be detected).
Ranked #5 on
Video Object Detection
on ImageNet VID
Ask Question First for Enhancing Lifelong Language Learning
Lifelong language learning aims to stream learning NLP tasks while retaining knowledge of previous tasks.
DPA-1: Pretraining of Attention-based Deep Potential Model for Molecular Simulation
Machine learning assisted modeling of the inter-atomic potential energy surface (PES) is revolutionizing the field of molecular simulation.
DPOAD: Differentially Private Outsourcing of Anomaly Detection through Iterative Sensitivity Learning
Outsourcing anomaly detection to third-parties can allow data owners to overcome resource constraints (e. g., in lightweight IoT devices), facilitate collaborative analysis (e. g., under distributed or multi-party scenarios), and benefit from lower costs and specialized expertise (e. g., of Managed Security Service Providers).
DeePKS+ABACUS as a Bridge between Expensive Quantum Mechanical Models and Machine Learning Potentials
However, for high-level QM methods, such as density functional theory (DFT) at the meta-GGA level and/or with exact exchange, quantum Monte Carlo, etc., generating a sufficient amount of data for training a ML potential has remained computationally challenging due to their high cost.
RVAE-LAMOL: Residual Variational Autoencoder to Enhance Lifelong Language Learning
In order to alleviate catastrophic forgetting, we propose the residual variational autoencoder (RVAE) to enhance LAMOL, a recent LLL model, by mapping different tasks into a limited unified semantic space.
No More Pesky Hyperparameters: Offline Hyperparameter Tuning for RL
The performance of reinforcement learning (RL) agents is sensitive to the choice of hyperparameters.
SVR-based Observer Design for Unknown Linear Systems: Complexity and Performance
The variances of the estimation error and the fluctuations in performance are smaller with a properly-designed parameter $\gamma$ compared with the OLS methods.
DouFu: A Double Fusion Joint Learning Method For Driving Trajectory Representation
The attention fusion module incorporates route features with movement features to create a better spatial-temporal embedding.
Safety-Aware Optimal Control for Motion Planning with Low Computing Complexity
Simulations demonstrates that BRSCA has a higher probability of finding feasible solutions, reduces the computation time by about 17. 4% and the energy cost by about four times compared to other methods in the literature.
Automatic Multi-Label Prompting: Simple and Interpretable Few-Shot Classification
Prompt-based learning (i. e., prompting) is an emerging paradigm for exploiting knowledge learned by a pretrained language model.
Investigating the Properties of Neural Network Representations in Reinforcement Learning
In this paper we investigate the properties of representations learned by deep reinforcement learning systems.
FedADMM: A Federated Primal-Dual Algorithm Allowing Partial Participation
Federated learning is a framework for distributed optimization that places emphasis on communication efficiency.
PromptSource: An Integrated Development Environment and Repository for Natural Language Prompts
PromptSource is a system for creating, sharing, and using natural language prompts.
Dynamic Flow Equilibrium of Transportation and Power Distribution Networks Considering Flexible Traveling Choices and Voltage Quality Improvement
The increasing global spread of electric vehicles (EVs) has introduced significant interdependence between transportation and power networks.
Learning Linear Models Using Distributed Iterative Hessian Sketching
This work considers the problem of learning the Markov parameters of a linear system from observed data.
Decomposing Complex Questions Makes Multi-Hop QA Easier and More Interpretable
The Relation Extractor decomposes the complex question, and then the Reader answers the sub-questions in turn, and finally the Comparator performs numerical comparison and summarizes all to get the final answer, where the entire process itself constitutes a complete reasoning evidence path.
Reminding the Incremental Language Model via Data-Free Self-Distillation
Incremental language learning with pseudo-data can alleviate catastrophic forgetting in neural networks.
Multitask Prompted Training Enables Zero-Shot Task Generalization
Large language models have recently been shown to attain reasonable zero-shot generalization on a diverse set of tasks (Brown et al., 2020).
Robust Glare Detection: Review, Analysis, and Dataset Release
The source of glare is not limited to the sun, and glare can be seen in the images captured during the nighttime and in indoor environments, which is due to the presence of different light sources; reflective surfaces also influence the generation of such artifacts.
Greedy-based Value Representation for Efficient Coordination in Multi-agent Reinforcement Learning
Due to the representation limitation of the joint Q value function, multi-agent reinforcement learning (MARL) methods with linear or monotonic value decomposition can not ensure the optimal consistency (i. e. the correspondence between the individual greedy actions and the maximal true Q value), leading to instability and poor coordination.
Multi-agent Reinforcement Learning
reinforcement-learning
+1
Large-Scale System Identification Using a Randomized SVD
Learning a dynamical system from input/output data is a fundamental task in the control design pipeline.
Visual Enhanced 3D Point Cloud Reconstruction from A Single Image
Solving the challenging problem of 3D object reconstruction from a single image appropriately gives existing technologies the ability to perform with a single monocular camera rather than requiring depth sensors.
3D Object Reconstruction From A Single Image
3D Point Cloud Reconstruction
+1
Optimizing NLU Reranking Using Entity Resolution Signals in Multi-domain Dialog Systems
In dialog systems, the Natural Language Understanding (NLU) component typically makes the interpretation decision (including domain, intent and slots) for an utterance before the mentioned entities are resolved.
Entity Resolution in Open-domain Conversations
In recent years, incorporating external knowledge for response generation in open-domain conversation systems has attracted great interest.
REGRAD: A Large-Scale Relational Grasp Dataset for Safe and Object-Specific Robotic Grasping in Clutter
In this paper, we present a new dataset named REGRAD for the learning of relationships among objects and grasps.
A Novel Binocular Eye-Tracking SystemWith Stereo Stimuli for 3D Gaze Estimation
However, most current eye trackers focus on 2D point of gaze (PoG) estimation and cannot provide accurate gaze depth. Concerning future applications such as HCI with 3D displays, we propose a novel binocular eye tracking device with stereo stimuli to provide highly accurate 3D PoG estimation.
Personalized Entity Resolution with Dynamic Heterogeneous Knowledge Graph Representations
For example, with "add milk to my cart", a customer may refer to a certain organic product, while some customers may want to re-order products they regularly purchase.
The Phase Diagram of a Deep Potential Water Model
Using the Deep Potential methodology, we construct a model that reproduces accurately the potential energy surface of the SCAN approximation of density functional theory for water, from low temperature and pressure to about 2400 K and 50 GPa, excluding the vapor stability region.
Chemical Physics
Identification of 27 abnormalities from multi-lead ECG signals: An ensembled Se-ResNet framework with Sign Loss function
Cardiovascular disease is a major threat to health and one of the primary causes of death globally.
Masked Face Image Classification with Sparse Representation based on Majority Voting Mechanism
Sparse approximation is the problem to find the sparsest linear combination for a signal from a redundant dictionary, which is widely applied in signal processing and compressed sensing.
Enhancing Generalization in Natural Language Inference by Syntax
Pre-trained language models such as BERT have achieved the state-of-the-art performance on natural language inference (NLI).
DeePKS: a comprehensive data-driven approach towards chemically accurate density functional theory
We propose a general machine learning-based framework for building an accurate and widely-applicable energy functional within the framework of generalized Kohn-Sham density functional theory.
Online Visual Place Recognition via Saliency Re-identification
As an essential component of visual simultaneous localization and mapping (SLAM), place recognition is crucial for robot navigation and autonomous driving.
Deep Potential generation scheme and simulation protocol for the Li10GeP2S12-type superionic conductors
It has been a challenge to accurately simulate Li-ion diffusion processes in battery materials at room temperature using {\it ab initio} molecular dynamics (AIMD) due to its high computational cost.
Computational Physics Materials Science Chemical Physics
SentPWNet: A Unified Sentence Pair Weighting Network for Task-specific Sentence Embedding
Our model, SentPWNet, exploits the neighboring spatial distribution of each sentence as locality weight to indicate the informative level of sentence pair.
Pushing the limit of molecular dynamics with ab initio accuracy to 100 million atoms with machine learning
For 35 years, {\it ab initio} molecular dynamics (AIMD) has been the method of choice for modeling complex atomistic phenomena from first principles.
Computational Physics
Intensity Scan Context: Coding Intensity and Geometry Relations for Loop Closure Detection
Loop closure detection is an essential and challenging problem in simultaneous localization and mapping (SLAM).
Deep Attention Aware Feature Learning for Person Re-Identification
Visual attention has proven to be effective in improving the performance of person re-identification.
Ranked #8 on
Person Re-Identification
on Market-1501
Fast Loop Closure Detection via Binary Content
Our method is compared with the state-of-the-art loop closure detection methods and the results show that it outperforms the traditional methods at both recall rate and speed.
DP-GEN: A concurrent learning platform for the generation of reliable deep learning based potential energy models
Materials 3, 023804] and is capable of generating uniformly accurate deep learning based PES models in a way that minimizes human intervention and the computational cost for data generation and model training.
Computational Physics
VideoDP: A Universal Platform for Video Analytics with Differential Privacy
In this paper, to the best of our knowledge, we propose the first differentially private video analytics platform (VideoDP) which flexibly supports different video analyses with rigorous privacy guarantee.
Deep neural network for Wannier function centers
We introduce a deep neural network (DNN) model that assigns the position of the centers of the electronic charge in each atomic configuration on a molecular dynamics trajectory.
Computational Physics Materials Science Chemical Physics
Machine learning-guided synthesis of advanced inorganic materials
Synthesis of advanced inorganic materials with minimum number of trials is of paramount importance towards the acceleration of inorganic materials development.
Learning to Decompose Compound Questions with Reinforcement Learning
Our model consists of two parts: (i) a novel learning-to-decompose agent that learns a policy to decompose a compound question into simple questions and (ii) three independent simple-question answerers that classify the corresponding relations for each simple question.
Active Learning of Uniformly Accurate Inter-atomic Potentials for Materials Simulation
An active learning procedure called Deep Potential Generator (DP-GEN) is proposed for the construction of accurate and transferable machine learning-based models of the potential energy surface (PES) for the molecular modeling of materials.
Learn to Steer through Deep Reinforcement Learning
It is worth noting that the developed system is readily transferable from virtual training scenarios to real-world deployment without any fine-tuning by utilizing depth images.
HashTran-DNN: A Framework for Enhancing Robustness of Deep Neural Networks against Adversarial Malware Samples
Adversarial machine learning in the context of image processing and related applications has received a large amount of attention.
End-to-end Symmetry Preserving Inter-atomic Potential Energy Model for Finite and Extended Systems
Machine learning models are changing the paradigm of molecular modeling, which is a fundamental tool for material science, chemistry, and computational biology.
Computational Physics Materials Science Chemical Physics
English Out-of-Vocabulary Lexical Evaluation Task
Unlike previous unknown nouns tagging task, this is the first attempt to focus on out-of-vocabulary (OOV) lexical evaluation tasks that do not require any prior knowledge.
DeePMD-kit: A deep learning package for many-body potential energy representation and molecular dynamics
Here we describe DeePMD-kit, a package written in Python/C++ that has been designed to minimize the effort required to build deep learning based representation of potential energy and force field and to perform molecular dynamics.
Reinforced dynamics for enhanced sampling in large atomic and molecular systems
Like metadynamics, it allows for an efficient exploration of the configuration space by adding an adaptively computed biasing potential to the original dynamics.
Deep Potential Molecular Dynamics: a scalable model with the accuracy of quantum mechanics
We introduce a scheme for molecular simulations, the Deep Potential Molecular Dynamics (DeePMD) method, based on a many-body potential and interatomic forces generated by a carefully crafted deep neural network trained with ab initio data.
Detecting facial landmarks in the video based on a hybrid framework
Finally, the facial landmarks in the current frame are exactly detected from the validated face bounding box via the landmark detector.
Time-domain multiscale shape identification in electro-sensing
This paper presents premier and innovative time-domain multi-scale method for shape identification in electro-sensing using pulse-type signals.
Wavelet methods for shape perception in electro-sensing
This paper aims at presenting a new approach to the electro-sensing problem using wavelets.
