24 citations · 83 across the 20 of their papers we have counts for
20 papers
Unified Demonstration Retriever for In-Context Learning
Xiaonan Li, Kai Lv, Hang Yan +6
In-context learning is a new learning paradigm where a language model conditions on a few input-output pairs (demonstrations) and a test input, and directly outputs the prediction.…
Filter Pruning via Filters Similarity in Consecutive Layers
Xiaorui Wang, Jun Wang, Xin Tang +3
Filter pruning is widely adopted to compress and accelerate the Convolutional Neural Networks (CNNs), but most previous works ignore the relationship between filters and channels i…
SFE-AI at SemEval-2022 Task 11: Low-Resource Named Entity Recognition using Large Pre-trained Language Models
Changyu Hou, Jun Wang, Yixuan Qiao +8
Large scale pre-training models have been widely used in named entity recognition (NER) tasks. However, model ensemble through parameter averaging or voting can not give full play…
PASH at TREC 2021 Deep Learning Track: Generative Enhanced Model for Multi-stage Ranking
Yixuan Qiao, Shanshan Zhao, Jun Wang +8
This paper describes the PASH participation in TREC 2021 Deep Learning Track. In the recall stage, we adopt a scheme combining sparse and dense retrieval method. In the multi-stage…
A Simple Hash-Based Early Exiting Approach For Language Understanding and Generation
Tianxiang Sun, Xiangyang Liu, Wei Zhu +7
Early exiting allows instances to exit at different layers according to the estimation of difficulty. Previous works usually adopt heuristic metrics such as the entropy of internal…
CandidateDrug4Cancer: An Open Molecular Graph Learning Benchmark on Drug Discovery for Cancer
Xianbin Ye, Ziliang Li, Fei Ma +6
Anti-cancer drug discoveries have been serendipitous, we sought to present the Open Molecular Graph Learning Benchmark, named CandidateDrug4Cancer, a challenging and realistic benc…
Multi-institutional Validation of Two-Streamed Deep Learning Method for Automated Delineation of Esophageal Gross Tumor Volume using planning-CT and FDG-PETCT
Xianghua Ye, Dazhou Guo, Chen-kan Tseng +22
Background: The current clinical workflow for esophageal gross tumor volume (GTV) contouring relies on manual delineation of high labor-costs and interuser variability. Purpose: To…
Pairwise Half-graph Discrimination: A Simple Graph-level Self-supervised Strategy for Pre-training Graph Neural Networks
Pengyong Li, Jun Wang, Ziliang Li +6
Self-supervised learning has gradually emerged as a powerful technique for graph representation learning. However, transferable, generalizable, and robust representation learning o…
DeepStationing: Thoracic Lymph Node Station Parsing in CT Scans using Anatomical Context Encoding and Key Organ Auto-Search
Dazhou Guo, Xianghua Ye, Jia Ge +9
Lymph node station (LNS) delineation from computed tomography (CT) scans is an indispensable step in radiation oncology workflow. High inter-user variabilities across oncologists a…
Winner Team Mia at TextVQA Challenge 2021: Vision-and-Language Representation Learning with Pre-trained Sequence-to-Sequence Model
Yixuan Qiao, Hao Chen, Jun Wang +7
TextVQA requires models to read and reason about text in images to answer questions about them. Specifically, models need to incorporate a new modality of text present in the image…
CBLUE: A Chinese Biomedical Language Understanding Evaluation Benchmark
Ningyu Zhang, Mosha Chen, Zhen Bi +20
Artificial Intelligence (AI), along with the recent progress in biomedical language understanding, is gradually changing medical practice. With the development of biomedical langua…
Lesion Segmentation and RECIST Diameter Prediction via Click-driven Attention and Dual-path Connection
Youbao Tang, Ke Yan, Jinzheng Cai +6
Measuring lesion size is an important step to assess tumor growth and monitor disease progression and therapy response in oncology image analysis. Although it is tedious and highly…
Weakly-Supervised Universal Lesion Segmentation with Regional Level Set Loss
Youbao Tang, Jinzheng Cai, Ke Yan +6
Accurately segmenting a variety of clinically significant lesions from whole body computed tomography (CT) scans is a critical task on precision oncology imaging, denoted as univer…
Scalable Semi-supervised Landmark Localization for X-ray Images using Few-shot Deep Adaptive Graph
Xiao-Yun Zhou, Bolin Lai, Weijian Li +12
Landmark localization plays an important role in medical image analysis. Learning based methods, including CNN and GCN, have demonstrated the state-of-the-art performance. However,…
Learning from Subjective Ratings Using Auto-Decoded Deep Latent Embeddings
Bowen Li, Xinping Ren, Ke Yan +6
Depending on the application, radiological diagnoses can be associated with high inter- and intra-rater variabilities. Most computer-aided diagnosis (CAD) solutions treat such data…
Semi-Supervised Learning for Bone Mineral Density Estimation in Hip X-ray Images
Kang Zheng, Yirui Wang, Xiaoyun Zhou +8
Bone mineral density (BMD) is a clinically critical indicator of osteoporosis, usually measured by dual-energy X-ray absorptiometry (DEXA). Due to the limited accessibility of DEXA…
Learn molecular representations from large-scale unlabeled molecules for drug discovery
Pengyong Li, Jun Wang, Yixuan Qiao +6
How to produce expressive molecular representations is a fundamental challenge in AI-driven drug discovery. Graph neural network (GNN) has emerged as a powerful technique for model…
Semi-supervised Active Learning for Instance Segmentation via Scoring Predictions
Jun Wang, Shaoguo Wen, Kaixing Chen +5
Active learning generally involves querying the most representative samples for human labeling, which has been widely studied in many fields such as image classification and object…
AutoRC: Improving BERT Based Relation Classification Models via Architecture Search
Wei Zhu, Xipeng Qiu, Yuan Ni +1
Although BERT based relation classification (RC) models have achieved significant improvements over the traditional deep learning models, it seems that no consensus can be reached…
AutoTrans: Automating Transformer Design via Reinforced Architecture Search
Wei Zhu, Xiaoling Wang, Xipeng Qiu +2
Though the transformer architectures have shown dominance in many natural language understanding tasks, there are still unsolved issues for the training of transformer models, espe…