activity
20182022
most citedHigh thermal conductivity of high-quality monolayer boron nitride and its thermal expansion

603 citations · 664 across the 16 of their papers we have counts for

collaborators

24 papers

cs.CV20225 cited

Masked Vision-Language Transformers for Scene Text Recognition

Jie Wu, Ying Peng, Shengming Zhang +2

Scene text recognition (STR) enables computers to recognize and read the text in various real-world scenes. Recent STR models benefit from taking linguistic information in addition…

cs.NI20222 cited

Client Selection and Bandwidth Allocation for Federated Learning: An Online Optimization Perspective

Yun Ji, Zhoubin Kou, Xiaoxiong Zhong +3

Federated learning (FL) can train a global model from clients' local data set, which can make full use of the computing resources of clients and performs more extensive and efficie…

cs.CL2022

Locally Aggregated Feature Attribution on Natural Language Model Understanding

Sheng Zhang, Jin Wang, Haitao Jiang +1

With the growing popularity of deep-learning models, model understanding becomes more important. Much effort has been devoted to demystify deep neural networks for better interpret…

physics.ins-det20222 cited

An auto-locking ultra-stable laser with sub-hertz linewidth

D. Jiao, G. Xu, J. Gao +7

We report in detail the design process and performance of an auto-locking ultra-stable laser with sub-hertz linewidth at the first time. The laser frequency is automatically stabil…

cs.CL2022

Zero-Shot Dependency Parsing with Worst-Case Aware Automated Curriculum Learning

Miryam de Lhoneux, Sheng Zhang, Anders Søgaard

Large multilingual pretrained language models such as mBERT and XLM-RoBERTa have been found to be surprisingly effective for cross-lingual transfer of syntactic parsing models (Wu…

cs.CL2022

FairLex: A Multilingual Benchmark for Evaluating Fairness in Legal Text Processing

Ilias Chalkidis, Tommaso Pasini, Sheng Zhang +3

We present a benchmark suite of four datasets for evaluating the fairness of pre-trained language models and the techniques used to fine-tune them for downstream tasks. Our benchma…