
SelfSupervised Learning with Swin Transformers
We are witnessing a modeling shift from CNN to Transformers in computer ...
read it

Metatuning Language Models to Answer Prompts Better
Large pretrained language models like GPT3 have acquired a surprising a...
read it

OnFPGA Training with Ultra Memory Reduction: A LowPrecision Tensor Method
Various hardware accelerators have been developed for energyefficient a...
read it

HighDimensional Uncertainty Quantification via Rank and SampleAdaptive Tensor Regression
Fabrication process variations can significantly influence the performan...
read it

Swin Transformer: Hierarchical Vision Transformer using Shifted Windows
This paper presents a new vision Transformer, called Swin Transformer, t...
read it

Graph Neural Networks Inspired by Classical Iterative Algorithms
Despite the recent success of graph neural networks (GNN), common archit...
read it

Bayesian Inference with Certifiable Adversarial Robustness
We consider adversarial training of deep neural networks through the len...
read it

Towards Robust Neural Networks via Closeloop Control
Despite their success in massive engineering applications, deep neural n...
read it

Semantic Disentangling Generalized ZeroShot Learning
Generalized ZeroShot Learning (GZSL) aims to recognize images from both...
read it

EntropyBased Uncertainty Calibration for Generalized ZeroShot Learning
Compared to conventional zeroshot learning (ZSL) where recognising unse...
read it

Active Sampling for Accelerated MRI with LowRank Tensors
Magnetic resonance imaging (MRI) is a powerful imaging modality that rev...
read it

TROJANZOO: Everything you ever wanted to know about neural backdoors (but were afraid to ask)
Neural backdoors represent one primary threat to the security of deep le...
read it

Fork or Fail: CycleConsistent Training with ManytoOne Mappings
Cycleconsistent training is widely used for jointly learning a forward ...
read it

Propagate Yourself: Exploring PixelLevel Consistency for Unsupervised Visual Representation Learning
Contrastive learning methods for unsupervised visual representation lear...
read it

Overview of the Ninth Dialog System Technology Challenge: DSTC9
This paper introduces the Ninth Dialog System Technology Challenge (DSTC...
read it

Sparse Tucker Tensor Decomposition on a Hybrid FPGACPU Platform
Recommendation systems, social network analysis, medical imaging, and da...
read it

EndtoEnd Variational Bayesian Training of Tensorized Neural Networks with Automatic Rank Determination
Lowrank tensor decomposition is one of the most effective approaches to...
read it

DistDGL: Distributed Graph Neural Network Training for BillionScale Graphs
Graph neural networks (GNN) have shown great success in learning from gr...
read it

CoLAKE: Contextualized Language and Knowledge Embedding
With the emerging branch of incorporating factual knowledge into pretra...
read it

Efficient Estimation of General Treatment Effects using Neural Networks with A Diverging Number of Confounders
The estimation of causal effects is a primary goal of behavioral, social...
read it

Dualconstrained Deep SemiSupervised Coupled Factorization Network with Enriched Prior
Nonnegative matrix factorization is usually powerful for learning the "s...
read it

HighDimensional Uncertainty Quantification via Active and RankAdaptive Tensor Regression
Uncertainty quantification based on stochastic spectral methods suffers ...
read it

Robust and Secure Communications in Intelligent Reflecting Surface Assisted NOMA networks
This letter investigates secure transmission in an intelligent reflectin...
read it

FeatGraph: A Flexible and Efficient Backend for Graph Neural Network Systems
Graph neural networks (GNNs) are gaining increasing popularity as a prom...
read it

Trojaning Language Models for Fun and Profit
Recent years have witnessed a new paradigm of building natural language ...
read it

Adversarial Bipartite Graph Learning for Video Domain Adaptation
Domain adaptation techniques, which focus on adapting models between dis...
read it

RepPoints V2: Verification Meets Regression for Object Detection
Verification and regression are two general methodologies for prediction...
read it

Parametric Instance Classification for Unsupervised Visual Feature Learning
This paper presents parametric instance classification (PIC) for unsuper...
read it

Disentangled NonLocal Neural Networks
The nonlocal block is a popular module for strengthening the context mo...
read it

Duallevel Semantic Transfer Deep Hashing for Efficient Social Image Retrieval
Social network stores and disseminates a tremendous amount of user share...
read it

CycleGT: Unsupervised GraphtoText and TexttoGraph Generation via Cycle Training
Two important tasks at the intersection of knowledge graphs and natural ...
read it

Relation of the Relations: A New Paradigm of the Relation Extraction Problem
In natural language, often multiple entities appear in the same text. Ho...
read it

Repurpose Open Data to Discover Therapeutics for COVID19 using Deep Learning
There have been more than 850,000 confirmed cases and over 48,000 deaths...
read it

Learning Goaloriented Dialogue Policy with Opposite Agent Awareness
Most existing approaches for goaloriented dialogue policy learning used...
read it

DGLKE: Training Knowledge Graph Embeddings at Scale
Knowledge graphs have emerged as a key abstraction for organizing inform...
read it

Negative Margin Matters: Understanding Margin in Fewshot Classification
This paper introduces a negative margin loss to metric learning based fe...
read it

Spatially Adaptive Inference with Stochastic Feature Sampling and Interpolation
In the feature maps of CNNs, there commonly exists considerable spatial ...
read it

Recent Advances and Challenges in Taskoriented Dialog System
Due to the significance and value in humancomputer interaction and natu...
read it

CrossWOZ: A LargeScale Chinese CrossDomain TaskOriented Dialogue Dataset
To advance multidomain (crossdomain) dialogue modeling as well as alle...
read it

Transformer on a Diet
Transformer has been widely used thanks to its ability to capture sequen...
read it

Race, Gender and Beauty: The Effect of Information Provision on Online Hiring Biases
We conduct a study of hiring bias on a simulation platform where we ask ...
read it

Dense RepPoints: Representing Visual Objects with Dense Point Sets
We present an object representation, called Dense RepPoints, for flexibl...
read it

Fast DenseNet: Towards Efficient and Accurate Text Recognition with Fast Dense Networks
Convolutional Recurrent Neural Network (CRNN) is a popular network for r...
read it

FullyConvolutional Intensive Feature Flow Neural Network for Text Recognition
The Deep Convolutional Neural Networks (CNNs) have obtained a great succ...
read it

Deep Selfrepresentative Concept Factorization Network for Representation Learning
In this paper, we investigate the unsupervised deep representation learn...
read it

QuantumInspired Hamiltonian Monte Carlo for Bayesian Sampling
Hamiltonian Monte Carlo (HMC) is an efficient Bayesian sampling method t...
read it

MultiScale SelfAttention for Text Classification
In this paper, we introduce the prior knowledge, multiscale structure, ...
read it

Discriminative Local Sparse Representation by Robust Adaptive Dictionary Pair Learning
In this paper, we propose a structured Robust Adaptive Dictionary Pair ...
read it

Transductive ZeroShot Hashing for MultiLabel Image Retrieval
Hash coding has been widely used in approximate nearest neighbor search ...
read it

Learning from the Past: Continual MetaLearning via Bayesian Graph Modeling
Metalearning for fewshot learning allows a machine to leverage previou...
read it
Zheng Zhang
is this you? claim profile
Professor of Computer Science, NYU Shanghai; Global Network Professor, NYU