87 citations · 634 across the 83 of their papers we have counts for
21 papers · 1 filter
Simultaneous Location of Rail Vehicles and Mapping of Environment with Multiple LiDARs
Yusheng Wang, Weiwei Song, Yidong Lou +3
Precise and real-time rail vehicle localization as well as railway environment monitoring is crucial for railroad safety. In this letter, we propose a multi-LiDAR based simultaneou…
Rail Vehicle Localization and Mapping with LiDAR-Vision-Inertial-GNSS Fusion
Yusheng Wang, Weiwei Song, Yidong Lou +4
In this paper, we present a global navigation satellite system (GNSS) aided LiDAR-visual-inertial scheme, RailLoMer-V, for accurate and robust rail vehicle localization and mapping…
From Dense to Sparse: Contrastive Pruning for Better Pre-trained Language Model Compression
Runxin Xu, Fuli Luo, Chengyu Wang +4
Pre-trained Language Models (PLMs) have achieved great success in various Natural Language Processing (NLP) tasks under the pre-training and fine-tuning paradigm. With large quanti…
A global analysis of charmless two body hadronic decays for anti-triplet charmed baryons
Fei Huang, Zhi-Peng Xing, Xiao-Gang He
Recently Belle collaboration reported new measurements for the branching fractions with the first observing two processes of , $\mathcal{B}(Ξ_c^0\toΣ^0…
LOGEN: Few-shot Logical Knowledge-Conditioned Text Generation with Self-training
Shumin Deng, Jiacheng Yang, Hongbin Ye +6
Natural language generation from structured data mainly focuses on surface-level descriptions, suffering from uncontrollable content selection and low fidelity. Previous works leve…
RailLoMer: Rail Vehicle Localization and Mapping with LiDAR-IMU-Odometer-GNSS Data Fusion
Yusheng Wang, Yidong Lou, Yi Zhang +4
We present RailLoMer in this article, to achieve real-time accurate and robust odometry and mapping for rail vehicles. RailLoMer receives measurements from two LiDARs, an IMU, trai…
Photoproduction reaction in an effective Lagrangian approach
Neng-Chang Wei, Yi-Ming Zhu, Fei Huang
In our previous work [Phys. Rev. C 101, 014003 (2020)], the photoproduction reaction has been investigated within an effective Lagrangian approach. There, the…
Revisiting Dark Matter Freeze-in and Freeze-out through Phase-Space Distribution
Yong Du, Fei Huang, Hao-Lin Li +2
We revisit dark-matter production through freeze-in and freeze-out by solving the Boltzmann equations at the level of the phase-space distribution . Using the annih…
MetroLoc: Metro Vehicle Mapping and Localization with LiDAR-Camera-Inertial Integration
Yusheng Wang, Weiwei Song, Yi Zhang +3
We propose an accurate and robust multi-modal sensor fusion framework, MetroLoc, towards one of the most extreme scenarios, the large-scale metro vehicle localization and mapping.…
Fusing Heterogeneous Factors with Triaffine Mechanism for Nested Named Entity Recognition
Zheng Yuan, Chuanqi Tan, Songfang Huang +1
Nested entities are observed in many domains due to their compositionality, which cannot be easily recognized by the widely-used sequence labeling framework. A natural solution is…
Learning to Ask for Data-Efficient Event Argument Extraction
Hongbin Ye, Ningyu Zhang, Zhen Bi +5
Event argument extraction (EAE) is an important task for information extraction to discover specific argument roles. In this study, we cast EAE as a question-based cloze task and e…
Raise a Child in Large Language Model: Towards Effective and Generalizable Fine-tuning
Runxin Xu, Fuli Luo, Zhiyuan Zhang +4
Recent pretrained language models extend from millions to billions of parameters. Thus the need to fine-tune an extremely large pretrained model with a limited training corpus aris…
Differentiable Prompt Makes Pre-trained Language Models Better Few-shot Learners
Ningyu Zhang, Luoqiu Li, Xiang Chen +5
Large-scale pre-trained language models have contributed significantly to natural language processing by demonstrating remarkable abilities as few-shot learners. However, their eff…
Stochastic Gravitational Wave Background from PBH-ABH Mergers
Wenfeng Cui, Fei Huang, Jing Shu +1
The measurement of gravitational waves produced by binary black-hole mergers at the Advanced LIGO has encouraged extensive studies on the stochastic gravitational wave background.…
Real-time Multi-Messenger Analysis Framework for KM3NeT
William Assal, Damien Dornic, Feifei Huang +3
KM3NeT is a multi-purpose cubic-kilometer neutrino observatory under construction in the Mediterranean Sea. It consists of ORCA and ARCA (for Oscillation and Astroparticle Research…
StructuralLM: Structural Pre-training for Form Understanding
Chenliang Li, Bin Bi, Ming Yan +4
Large pre-trained language models achieve state-of-the-art results when fine-tuned on downstream NLP tasks. However, they almost exclusively focus on text-only representation, whil…
Improving Named Entity Recognition by External Context Retrieving and Cooperative Learning
Xinyu Wang, Yong Jiang, Nguyen Bach +4
Recent advances in Named Entity Recognition (NER) show that document-level contexts can significantly improve model performance. In many application scenarios, however, such contex…
Improving Biomedical Pretrained Language Models with Knowledge
Zheng Yuan, Yijia Liu, Chuanqi Tan +2
Pretrained language models have shown success in many natural language processing tasks. Many works explore incorporating knowledge into language models. In the biomedical domain,…
Resurrecting Low-Mass Axion Dark Matter Via a Dynamical QCD Scale
Lucien Heurtier, Fei Huang, Tim M. P. Tait
In the framework where the strong coupling is dynamical, the QCD sector may confine at a much higher temperature than it would in the Standard Model, and the temperature-dependent…
Prototypical Representation Learning for Relation Extraction
Ning Ding, Xiaobin Wang, Yao Fu +7
Recognizing relations between entities is a pivotal task of relational learning. Learning relation representations from distantly-labeled datasets is difficult because of the abund…
Dynamic Hybrid Relation Network for Cross-Domain Context-Dependent Semantic Parsing
Binyuan Hui, Ruiying Geng, Qiyu Ren +7
Semantic parsing has long been a fundamental problem in natural language processing. Recently, cross-domain context-dependent semantic parsing has become a new focus of research. C…