Search Results for author:
Found 68 papers, 25 papers with code
Approaching Sign Language Gloss Translation as a Low-Resource Machine Translation Task
A cascaded Sign Language Translation system first maps sign videos to gloss annotations and then translates glosses into a spoken languages.
The JHU/KyotoU Speech Translation System for IWSLT 2018
This paper describes the Johns Hopkins University (JHU) and Kyoto University submissions to the Speech Translation evaluation campaign at IWSLT2018.
SEMA: Text Simplification Evaluation through Semantic Alignment
Text simplification is an important branch of natural language processing.
Mitigating Pooling Bias in E-commerce Search via False Negative Estimation
Efficient and accurate product relevance assessment is critical for user experiences and business success.
Towards LLM-based Fact Verification on News Claims with a Hierarchical Step-by-Step Prompting Method
While large pre-trained language models (LLMs) have shown their impressive capabilities in various NLP tasks, they are still under-explored in the misinformation domain.
GNNHLS: Evaluating Graph Neural Network Inference via High-Level Synthesis
In this paper, we propose GNNHLS, an open-source framework to comprehensively evaluate GNN inference acceleration on FPGAs via HLS, containing a software stack for data generation and baseline deployment, and FPGA implementations of 6 well-tuned GNN HLS kernels.
Learning Minimalistic Tsetlin Machine Clauses with Markov Boundary-Guided Pruning
A set of variables is the Markov blanket of a random variable if it contains all the information needed for predicting the variable.
CktGNN: Circuit Graph Neural Network for Electronic Design Automation
The electronic design automation of analog circuits has been a longstanding challenge in the integrated circuit field due to the huge design space and complex design trade-offs among circuit specifications.
Artificial Intelligence for Science in Quantum, Atomistic, and Continuum Systems
Advances in artificial intelligence (AI) are fueling a new paradigm of discoveries in natural sciences.
Group Equivariant Fourier Neural Operators for Partial Differential Equations
We consider solving partial differential equations (PDEs) with Fourier neural operators (FNOs), which operate in the frequency domain.
A Score-Based Model for Learning Neural Wavefunctions
Existing optimization approaches compute the energy by sampling local energy from an explicit probability distribution given by the wavefunction.
BookGPT: A General Framework for Book Recommendation Empowered by Large Language Model
At the same time, based on different evaluation schemes for book recommendation tasks and the existing classic recommendation models, this paper discusses the advantages and disadvantages of the BookGPT in book recommendation scenarios and analyzes the opportunities and improvement directions for subsequent LLMs in these scenarios.
Cognition Guided Human-Object Relationship Detection
Human-object relationship detection reveals the fine-grained relationship between humans and objects, helping the comprehensive understanding of videos.
3D Molecular Geometry Analysis with 2D Graphs
Here, we propose a novel deep learning framework to predict 3D geometries from molecular graphs.
Interpretable Tsetlin Machine-based Premature Ventricular Contraction Identification
In this study, we develop a Tsetlin machine (TM) based architecture for premature ventricular contraction (PVC) identification by analysing long-term ECG signals.
Building Concise Logical Patterns by Constraining Tsetlin Machine Clause Size
This paper introduces a novel variant of TM learning - Clause Size Constrained TMs (CSC-TMs) - where one can set a soft constraint on the clause size.
DeSTSeg: Segmentation Guided Denoising Student-Teacher for Anomaly Detection
In this study, we propose an improved model called DeSTSeg, which integrates a pre-trained teacher network, a denoising student encoder-decoder, and a segmentation network into one framework.
Ranked #32 on
Anomaly Detection
on MVTec AD
VideoPipe 2022 Challenge: Real-World Video Understanding for Urban Pipe Inspection
For this reason, we propose to advance research areas of video understanding, with a shift from traditional action recognition to industrial anomaly analysis.
Lattice Convolutional Networks for Learning Ground States of Quantum Many-Body Systems
Based on the proposed lattice convolutions, we design lattice convolutional networks (LCN) that use self-gating and attention mechanisms.
Domain Knowledge-Infused Deep Learning for Automated Analog/Radio-Frequency Circuit Parameter Optimization
The design automation of analog circuits is a longstanding challenge.
Data-Driven Robust Control for Discrete Linear Time-Invariant Systems: A Descriptor System Approach
Given the recent surge of interest in data-driven control, this paper proposes a two-step method to study robust data-driven control for a parameter-unknown linear time-invariant (LTI) system that is affected by energy-bounded noises.
Domain Knowledge-Based Automated Analog Circuit Design with Deep Reinforcement Learning
The design automation of analog circuits is a longstanding challenge in the integrated circuit field.
Neural-PIM: Efficient Processing-In-Memory with Neural Approximation of Peripherals
This paper presents a new PIM architecture to efficiently accelerate deep learning tasks by minimizing the required A/D conversions with analog accumulation and neural approximated peripheral circuits.
A Fair and Efficient Hybrid Federated Learning Framework based on XGBoost for Distributed Power Prediction
In a modern power system, real-time data on power generation/consumption and its relevant features are stored in various distributed parties, including household meters, transformer stations and external organizations.
Data-Driven Controllability Analysis and Stabilization for Linear Descriptor Systems
For a parameter-unknown linear descriptor system, this paper proposes data-driven methods to testify the system's type and controllability and then to stabilize it.
Fairness-aware Online Price Discrimination with Nonparametric Demand Models
To handle this general class, we propose a soft fairness constraint and develop a dynamic pricing policy that achieves $\tilde{O}(T^{4/5})$ regret.
A Sequence to Sequence Model for Extracting Multiple Product Name Entities from Dialog
E-commerce voice ordering systems need to recognize multiple product name entities from ordering utterances.
Molecule3D: A Benchmark for Predicting 3D Geometries from Molecular Graphs
Here, we propose to predict the ground-state 3D geometries from molecular graphs using machine learning methods.
Ranked #1 on
3D Geometry Prediction
on Molecule3D val
On the Convergence of Tsetlin Machines for the AND and the OR Operators
The analyses on AND and OR operators, together with the previously analysed 1-bit and XOR operations, complete the convergence analyses on basic operators in Boolean algebra.
LeViT-UNet: Make Faster Encoders with Transformer for Medical Image Segmentation
Medical image segmentation plays an essential role in developing computer-assisted diagnosis and therapy systems, yet still faces many challenges.
Fast Quantum Property Prediction via Deeper 2D and 3D Graph Networks
We employ our methods to participate in the 2021 KDD Cup on OGB Large-Scale Challenge (OGB-LSC), which aims to predict the HOMO-LUMO energy gap of molecules.
An Integration and Operation Framework of Geothermal Heat Pumps in Distribution Networks
Besides, in the Virtual Power Plant (VPP) system, the demand response of clustered GHP systems can improve the operating flexibility of the power grid.
Self-Supervised Graph Neural Networks for Improved Electroencephalographic Seizure Analysis
Automated seizure detection and classification from electroencephalography (EEG) can greatly improve seizure diagnosis and treatment.
DIG: A Turnkey Library for Diving into Graph Deep Learning Research
Although there exist several libraries for deep learning on graphs, they are aiming at implementing basic operations for graph deep learning.
A Federated Learning Framework for Smart Grids: Securing Power Traces in Collaborative Learning
For example, power consumption data are stored in numerous transformer stations across cities; mobility data of the population, which are important indicators of power consumption, are held by mobile companies.
Sent2Matrix: Folding Character Sequences in Serpentine Manifolds for Two-Dimensional Sentence
We study text representation methods using deep models.
Spherical Message Passing for 3D Graph Networks
Based on such observations, we propose the spherical message passing (SMP) as a novel and powerful scheme for 3D molecular learning.
Ranked #3 on
Drug Discovery
on QM9
RTGPU: Real-Time GPU Scheduling of Hard Deadline Parallel Tasks with Fine-Grain Utilization
In this paper, we propose RTGPU, which can schedule the execution of multiple GPU applications in real-time to meet hard deadlines.
Disentangled Recurrent Wasserstein Autoencoder
Learning disentangled representations leads to interpretable models and facilitates data generation with style transfer, which has been extensively studied on static data such as images in an unsupervised learning framework.
On the Convergence of Tsetlin Machines for the XOR Operator
The Tsetlin Machine (TM) is a novel machine learning algorithm with several distinct properties, including transparent inference and learning using hardware-near building blocks.
Finding Physical Adversarial Examples for Autonomous Driving with Fast and Differentiable Image Compositing
We propose a scalable approach for finding adversarial modifications of a simulated autonomous driving environment using a differentiable approximation for the mapping from environmental modifications (rectangles on the road) to the corresponding video inputs to the controller neural network.
Boundary zonal flows in rapidly rotating turbulent thermal convection
The mode number of the BZF is 1 for $\Gamma \lesssim 1$ and $2 \Gamma$ for $\Gamma$ = {1, 2} independent of $Ra$ and $Pr$.
Fluid Dynamics
Generation of zonal flows in convective systems by travelling thermal waves
Our results confirm that the travelling thermal waves can cause zonal flows, i. e. strong mean horizontal flows.
Fluid Dynamics
On the Convergence of Tsetlin Machines for the IDENTITY- and NOT Operators
The analysis of the convergence of the two basic operators lays the foundation for analyzing other logical operators.
Reducing the Feeder Effect in Public School Admissions: A Bias-aware Analysis for Targeted Interventions
These scores are known to be impacted by socioeconomic status of students and test preparation received in "feeder" middle schools, leading to a massive filtering effect in the education pipeline.
Machine Translation System Selection from Bandit Feedback
Adapting machine translation systems in the real world is a difficult problem.
Reproducible and Efficient Benchmarks for Hyperparameter Optimization of Neural Machine Translation Systems
Hyperparameter selection is a crucial part of building neural machine translation (NMT) systems across both academia and industry.
Quaternion Product Units for Deep Learning on 3D Rotation Groups
We propose a novel quaternion product unit (QPU) to represent data on 3D rotation groups.
Balancing Efficiency and Fairness in On-Demand Ridesourcing
We investigate the problem of assigning trip requests to available vehicles in on-demand ridesourcing.
Neural Network-Inspired Analog-to-Digital Conversion to Achieve Super-Resolution with Low-Precision RRAM Devices
Recent works propose neural network- (NN-) inspired analog-to-digital converters (NNADCs) and demonstrate their great potentials in many emerging applications.
HABLex: Human Annotated Bilingual Lexicons for Experiments in Machine Translation
Bilingual lexicons are valuable resources used by professional human translators.
Attacking Vision-based Perception in End-to-End Autonomous Driving Models
One such example is autonomous driving, which often relies on deep learning for perception.
The Architectural Implications of Facebook's DNN-based Personalized Recommendation
The widespread application of deep learning has changed the landscape of computation in the data center.
Curriculum Learning for Domain Adaptation in Neural Machine Translation
We introduce a curriculum learning approach to adapt generic neural machine translation models to a specific domain.
A Scheme for Continuous Input to the Tsetlin Machine with Applications to Forecasting Disease Outbreaks
In this paper, we apply a new promising tool for pattern classification, namely, the Tsetlin Machine (TM), to the field of disease forecasting.
Simple Physical Adversarial Examples against End-to-End Autonomous Driving Models
Recent advances in machine learning, especially techniques such as deep neural networks, are promoting a range of high-stakes applications, including autonomous driving, which often relies on deep learning for perception.
A Hybrid Model for Role-related User Classification on Twitter
To aid a variety of research studies, we propose TWIROLE, a hybrid model for role-related user classification on Twitter, which detects male-related, female-related, and brand-related (i. e., organization or institution) users.
Social and Information Networks
An Empirical Exploration of Curriculum Learning for Neural Machine Translation
Machine translation systems based on deep neural networks are expensive to train.
SCPNet: Spatial-Channel Parallelism Network for Joint Holistic and Partial Person Re-Identification
Holistic person re-identification (ReID) has received extensive study in the past few years and achieves impressive progress.
Legal Assignments and fast EADAM with consent via classical theory of stable matchings
We prove that ${\cal L}$ is exactly the set of stable assignments in another instance, and that essentially any optimization problem over ${\cal L}$ can be solved within the same time bound needed for solving them over the set of stable assignments.
Data Structures and Algorithms
AxTrain: Hardware-Oriented Neural Network Training for Approximate Inference
The intrinsic error tolerance of neural network (NN) makes approximate computing a promising technique to improve the energy efficiency of NN inference.
Multi-Target, Multi-Camera Tracking by Hierarchical Clustering: Recent Progress on DukeMTMC Project
Although many methods perform well in single camera tracking, multi-camera tracking remains a challenging problem with less attention.
AlignedReID: Surpassing Human-Level Performance in Person Re-Identification
In this paper, we propose a novel method called AlignedReID that extracts a global feature which is jointly learned with local features.
Ranked #1 on
Person Re-Identification
on CUHK-SYSU
On the law of the iterated logarithm for continued fractions with sequentially restricted partial quotients
We establish a law of the iterated logarithm (LIL) for the set of real numbers whose $n$-th partial quotient is bigger than $\alpha_n$, where $(\alpha_n)$ is a sequence such that $\sum 1/\alpha_n$ is finite.
Dynamical Systems 11K50, 60F17, 37F35
Event extraction from Twitter using Non-Parametric Bayesian Mixture Model with Word Embeddings
To extract structured representations of newsworthy events from Twitter, unsupervised models typically assume that tweets involving the same named entities and expressed using similar words are likely to belong to the same event.
The Lindeberg theorem for Gibbs-Markov dynamics
A dynamical array consists of a family of functions $\{f_{n, i}: 1\le i\le k(n), n\ge 1\}$ and a family of initial times $\{\tau_{n, i}: 1\le i\le k(n), n\ge 1\}$.
Dynamical Systems 37A50, 60F05
