activity
20172023
most citedA Dual-Stage Attention-Based Recurrent Neural Network for Time Series Prediction

373 citations · 1.3k across the 51 of their papers we have counts for

collaborators
Showing 2023Show all

19 papers · 1 filter

hep-ex2023★ 5 cited

Measurements of the absolute branching fractions of decays and test of the rule

BESIII Collaboration, M. Ablikim, M. N. Achasov +610

Based on a data set of events collected at the BESIII experiment, the absolute branching fractions of the three dominant decays are meas…

cs.LG2023★ 1 cited

GLAD: Content-aware Dynamic Graphs For Log Anomaly Detection

Yufei Li, Yanchi Liu, Haoyu Wang +6

Logs play a crucial role in system monitoring and debugging by recording valuable system information, including events and states. Although various methods have been proposed to de…

cs.CL2023★ 2 cited

Improving Open Information Extraction with Large Language Models: A Study on Demonstration Uncertainty

Chen Ling, Xujiang Zhao, Xuchao Zhang +8

Open Information Extraction (OIE) task aims at extracting structured facts from unstructured text, typically in the form of (subject, relation, object) triples. Despite the potenti…

hep-ex2023★ 3 cited

A coupled-channel analysis of the lineshape with BESIII data

BESIII Collaboration, M. Ablikim, M. N. Achasov +611

We perform a study of the lineshape using the data samples of , and collected with the BESIII detector. The…

hep-ex2023

Investigation of the rule and test of CP violation through the measurement of decay asymmetry parameters in decays

BESIII Collaboration, M. Ablikim, M. N. Achasov +615

Using events collected with the BESIII detector, numerous and decay asymmetry parameters are simultaneously determined from the process…

hep-ex2023★ 3 cited

Measurement of the cross sections from 2.000 to 3.080 GeV

BESIII Collaboration, M. Ablikim, M. N. Achasov +615

Based on collision data collected at center-of-mass energies from 2.000 to 3.080 GeV by the BESIII detector at the BEPCII collider, a partial wave analysis is performe…

cs.CL2023★ 127 cited

Baichuan 2: Open Large-scale Language Models

Aiyuan Yang, Bin Xiao, Bingning Wang +52

Large language models (LLMs) have demonstrated remarkable performance on a variety of natural language tasks based on just a few examples of natural language instructions, reducing…

cs.LG2023★ 1 cited

From SMOTE to Mixup for Deep Imbalanced Classification

Wei-Chao Cheng, Tan-Ha Mai, Hsuan-Tien Lin

Given imbalanced data, it is hard to train a good classifier using deep learning because of the poor generalization of minority classes. Traditionally, the well-known synthetic min…

hep-ex2023

Measurement of cross sections at center-of-mass energies from 3.508 to 4.951 GeV and search for the decay

BESIII Collaboration, M. Ablikim, M. N. Achasov +611

The cross sections of the process at center-of-mass energies from 3.508 to 4.951 GeV are measured with high precision using 26.1 fb data collected with th…

hep-ex2023★ 10 cited

Measurement of the branching fractions of the singly Cabibbo-suppressed decays and

BESIII Collaboration, M. Ablikim, M. N. Achasov +618

Based on 4.5 $\mbox{fb$^{-1}$}$ collision data collected with BESIII detector at seven energy points between 4.600 and 4.699 GeV, the branching fractions for $Λ_{c}^{+…

cs.LG2023★ 6 cited

Skill Disentanglement for Imitation Learning from Suboptimal Demonstrations

Tianxiang Zhao, Wenchao Yu, Suhang Wang +6

Imitation learning has achieved great success in many sequential decision-making tasks, in which a neural agent is learned by imitating collected human demonstrations. However, exi…

cs.IT2023

Maximal Leakage of Masked Implementations Using Mrs. Gerber's Lemma for Min-Entropy

Julien Béguinot, Yi Liu, Olivier Rioul +2

A common countermeasure against side-channel attacks on secret key cryptographic implementations is th-order masking, which splits each sensitive variable into random shar…

cs.CL2023★ 74 cited

Domain Specialization as the Key to Make Large Language Models Disruptive: A Comprehensive Survey

Chen Ling, Xujiang Zhao, Jiaying Lu +21

Large language models (LLMs) have significantly advanced the field of natural language processing (NLP), providing a highly useful, task-agnostic foundation for a wide range of app…

cs.CL2023★ 20 cited

DNA-GPT: Divergent N-Gram Analysis for Training-Free Detection of GPT-Generated Text

Xianjun Yang, Wei Cheng, Yue Wu +3

Large language models (LLMs) have notably enhanced the fluency and diversity of machine-generated text. However, this progress also presents a significant challenge in detecting th…

cs.IT2023★ 61 cited

Integrated Sensing and Communication based Outdoor Multi-Target Detection, Tracking and Localization in Practical 5G Networks

Ruiqi Liu, Mengnan Jian, Dawei Chen +4

The 6th generation (6G) wireless networks will likely to support a variety of capabilities beyond communication, such as sensing and localization, through the use of communication…

cs.LG2023★ 6 cited

Personalized Federated Learning under Mixture of Distributions

Yue Wu, Shuaicheng Zhang, Wenchao Yu +5

The recent trend towards Personalized Federated Learning (PFL) has garnered significant attention as it allows for the training of models that are tailored to each client while mai…

cs.LG2023★ 1 cited

Time Series Contrastive Learning with Information-Aware Augmentations

Dongsheng Luo, Wei Cheng, Yingheng Wang +8

Various contrastive learning approaches have been proposed in recent years and achieve significant empirical success. While effective and prevalent, contrastive learning has been l…

cs.CL2023★ 3 cited

Dynamic Prompting: A Unified Framework for Prompt Tuning

Xianjun Yang, Wei Cheng, Xujiang Zhao +3

It has been demonstrated that the art of prompt tuning is highly effective in efficiently extracting knowledge from pretrained foundation models, encompassing pretrained language m…

cs.CL2023★ 89 cited

Exploring the Limits of ChatGPT for Query or Aspect-based Text Summarization

Xianjun Yang, Yan Li, Xinlu Zhang +2

Text summarization has been a crucial problem in natural language processing (NLP) for several decades. It aims to condense lengthy documents into shorter versions while retaining…