152 citations · 327 across the 34 of their papers we have counts for
35 papers
Neural Image Compression Using Masked Sparse Visual Representation
Wei Jiang, Wei Wang, Yue Chen
We study neural image compression based on the Sparse Visual Representation (SVR), where images are embedded into a discrete latent space spanned by learned visual codebooks. By sh…
Unveiling Invariances via Neural Network Pruning
Derek Xu, Yizhou Sun, Wei Wang
Invariance describes transformations that do not alter data's underlying semantics. Neural networks that preserve natural invariance capture good inductive biases and achieve super…
MathAttack: Attacking Large Language Models Towards Math Solving Ability
Zihao Zhou, Qiufeng Wang, Mingyu Jin +6
With the boom of Large Language Models (LLMs), the research of solving Math Word Problem (MWP) has recently made great progress. However, there are few studies to examine the secur…
Learning by Analogy: Diverse Questions Generation in Math Word Problem
Zihao Zhou, Maizhen Ning, Qiufeng Wang +4
Solving math word problem (MWP) with AI techniques has recently made great progress with the success of deep neural networks (DNN), but it is far from being solved. We argue that t…
Harnessing Trust in Directed Graphs: Redefining Robustness of Graph Learning
Zhichao Hou, Xitong Zhang, Wei Wang +2
Existing research on robust Graph Neural Networks (GNNs) focuses predominantly on undirected graphs, overlooking the trustworthiness inherent in the link directions of directed gra…
CAROM Air -- Vehicle Localization and Traffic Scene Reconstruction from Aerial Videos
Duo Lu, Eric Eaton, Matt Weg +5
Road traffic scene reconstruction from videos has been desirable by road safety regulators, city planners, researchers, and autonomous driving technology developers. However, it is…
STAR: Boosting Low-Resource Information Extraction by Structure-to-Text Data Generation with Large Language Models
Mingyu Derek Ma, Xiaoxuan Wang, Po-Nien Kung +3
Information extraction tasks such as event extraction require an in-depth understanding of the output structure and sub-task dependencies. They heavily rely on task-specific traini…
Dumpy: A Compact and Adaptive Index for Large Data Series Collections
Zeyu Wang, Qitong Wang, Peng Wang +2
Data series indexes are necessary for managing and analyzing the increasing amounts of data series collections that are nowadays available. These indexes support both exact and app…
AGO: Boosting Mobile AI Inference Performance by Removing Constraints on Graph Optimization
Zhiying Xu, Hongding Peng, Wei Wang
Traditional deep learning compilers rely on heuristics for subgraph generation, which impose extra constraints on graph optimization, e.g., each subgraph can only contain at most o…
Multi-level Adversarial Spatio-temporal Learning for Footstep Pressure based FoG Detection
Kun Hu, Shaohui Mei, Wei Wang +5
Freezing of gait (FoG) is one of the most common symptoms of Parkinson's disease, which is a neurodegenerative disorder of the central nervous system impacting millions of people a…
Dordis: Efficient Federated Learning with Dropout-Resilient Differential Privacy
Zhifeng Jiang, Wei Wang, Ruichuan Chen
Federated learning (FL) is increasingly deployed among multiple clients to train a shared model over decentralized data. To address privacy concerns, FL systems need to safeguard t…
Cross-Domain Cross-Set Few-Shot Learning via Learning Compact and Aligned Representations
Wentao Chen, Zhang Zhang, Wei Wang +3
Few-shot learning (FSL) aims to recognize novel queries with only a few support samples through leveraging prior knowledge from a base dataset. In this paper, we consider the domai…
Pisces: Efficient Federated Learning via Guided Asynchronous Training
Zhifeng Jiang, Wei Wang, Baochun Li +1
Federated learning (FL) is typically performed in a synchronous parallel manner, where the involvement of a slow client delays a training iteration. Current FL systems employ a par…
The Chinese Hα Solar Explorer (CHASE) mission: An overview
Chuan Li, Cheng Fang, Zhen Li +32
The Chinese Hα Solar Explorer (CHASE), dubbed "Xihe" - Goddess of the Sun, was launched on October 14, 2021 as the first solar space mission of China National Space Administration…
Wasserstein Adversarial Transformer for Cloud Workload Prediction
Shivani Arbat, Vinodh Kumaran Jayakumar, Jaewoo Lee +2
Predictive Virtual Machine (VM) auto-scaling is a promising technique to optimize cloud applications operating costs and performance. Understanding the job arrival rate is crucial…
Disentangle Saliency Detection into Cascaded Detail Modeling and Body Filling
Yue Song, Hao Tang, Nicu Sebe +1
Salient object detection has been long studied to identify the most visually attractive objects in images/videos. Recently, a growing amount of approaches have been proposed all of…
Machine Learning and Artificial Intelligence in Next-Generation Wireless Network
Wafeeq Iqbal, Wei Wang, Ting Zhu
Due to the advancement in technologies, the next-generation wireless network will be very diverse, complicated, and according to the changed demands of the consumers. The current n…
Fast Differentiable Matrix Square Root and Inverse Square Root
Yue Song, Nicu Sebe, Wei Wang
Computing the matrix square root and its inverse in a differentiable manner is important in a variety of computer vision tasks. Previous methods either adopt the Singular Value Dec…
Computer Vision Based Parking Optimization System
Siddharth Chandrasekaran, Jeffrey Matthew Reginald, Wei Wang +1
An improvement in technology is linearly related to time and time-relevant problems. It has been seen that as time progresses, the number of problems humans face also increases. Ho…
Towards Efficient Synchronous Federated Training: A Survey on System Optimization Strategies
Zhifeng Jiang, Wei Wang, Bo Li +1
The increasing demand for privacy-preserving collaborative learning has given rise to a new computing paradigm called federated learning (FL), in which clients collaboratively trai…
Smoothing the Disentangled Latent Style Space for Unsupervised Image-to-Image Translation
Yahui Liu, Enver Sangineto, Yajing Chen +6
Image-to-Image (I2I) multi-domain translation models are usually evaluated also using the quality of their semantic interpolation results. However, state-of-the-art models frequent…
Language Scaling for Universal Suggested Replies Model
Qianlan Ying, Payal Bajaj, Budhaditya Deb +7
We consider the problem of scaling automated suggested replies for Outlook email system to multiple languages. Faced with increased compute requirements and low resources for langu…
Representation and Correlation Enhanced Encoder-Decoder Framework for Scene Text Recognition
Mengmeng Cui, Wei Wang, Jinjin Zhang +1
Attention-based encoder-decoder framework is widely used in the scene text recognition task. However, for the current state-of-the-art(SOTA) methods, there is room for improvement…
Few-Shot Learning with Part Discovery and Augmentation from Unlabeled Images
Wentao Chen, Chenyang Si, Wei Wang +3
Few-shot learning is a challenging task since only few instances are given for recognizing an unseen class. One way to alleviate this problem is to acquire a strong inductive bias…