XS
Xu Sun
cs.CLcs.LGcs.CVcs.AIstat.MLcs.MMcs.SIq-fin.TRAdversarial parameter defenseAlgorithms
On Valency
published · living versionsW_umajp7yy·v1 · currentpublished
When Requirements Interact: Scaling Long-Horizon Coding via Interdependent Specifications
with Yishuo Cai, Minzheng Wang, Liang Zhao, Linghao Zhang +3
1 version
W_ax2cmvsd·v1published
Preprints & journals
106 papers in the corpus · 2014–2025Spatial-Temporal Human-Object Interaction Detection2508.17270v1 · Xu Sun, Yunqing He, Tongwei Ren et al.2025 · 6 citationsarXiv
RICO: Improving Accuracy and Completeness in Image Recaptioning via Visual Reconstruction2505.22613v1 · Yuchi Wang, Yishuo Cai, Shuhuai Ren et al.2025 · 1 citationarXiv
TimeChat-Online: 80% Visual Tokens are Naturally Redundant in Streaming Videos2504.17343v1 · Linli Yao, Yicheng Li, Yuancheng Wei et al.2025 · 15 citationsarXiv
UVE: Are MLLMs Unified Evaluators for AI-Generated Videos?2503.09949v4 · Yuanxin Liu, Rui Zhu, Shuhuai Ren et al.2025 · 0 citationsarXiv
VidTwin: Video VAE with Decoupled Structure and Dynamics2412.17726v2 · Yuchi Wang, Junliang Guo, Xinyi Xie et al.2024 · 3 citationsarXiv
Temporal Reasoning Transfer from Text to Video2410.06166v1 · Lei Li, Yuanxin Liu, Linli Yao et al.2024 · 0 citationsarXiv
Enhancing Data Quality through Self-learning on Imbalanced Financial Risk Data2409.09792v1 · Xu Sun, Zixuan Qin, Shun Zhang et al.2024 · 0 citationsarXiv
TimeChat: A Time-sensitive Multimodal Large Language Model for Long Video Understanding2312.02051v2 · Shuhuai Ren, Linli Yao, Shicheng Li et al.2023 · 145 citationsarXiv
Edit As You Wish: Video Caption Editing with Multi-grained User Control2305.08389v3 · Linli Yao, Yuanmeng Zhang, Ziheng Wang et al.2023 · 5 citationsarXiv
DiMBERT: Learning Vision-Language Grounded Representations with Disentangled Multimodal-Attention2210.16431v1 · Fenglin Liu, Xian Wu, Shen Ge et al.2022 · 8 citationsarXiv
Stock Trading Volume Prediction with Dual-Process Meta-Learning2211.01762v1 · Ruibo Chen, Wei Li, Zhiyuan Zhang et al.2022 · 8 citationsarXiv
Distributional Correlation--Aware Knowledge Distillation for Stock Trading Volume Prediction2208.07232v1 · Lei Li, Zhiyuan Zhang, Ruihan Bao et al.2022 · 4 citationsarXiv
Hierarchical Inductive Transfer for Continual Dialogue Learning2203.10484v1 · Shaoxiong Feng, Xuancheng Ren, Kan Li et al.2022 · 3 citationsarXiv
Auto-Encoding Knowledge Graph for Unsupervised Medical Report Generation2111.04318v2 · Fenglin Liu, Chenyu You, Xian Wu et al.2021 · 80 citationsarXiv
Well-classified Examples are Underestimated in Classification with Deep Neural Networks2110.06537v6 · Guangxiang Zhao, Wenkai Yang, Xuancheng Ren et al.2021 · 18 citationsarXiv
Topology-Imbalance Learning for Semi-Supervised Node Classification2110.04099v1 · Deli Chen, Yankai Lin, Guangxiang Zhao et al.2021 · 57 citationsarXiv
Dynamic Knowledge Distillation for Pre-trained Language Models2109.11295v1 · Lei Li, Yankai Lin, Shuhuai Ren et al.2021 · 40 citationsarXiv
Text AutoAugment: Learning Compositional Augmentation Policy for Text Classification2109.00523v1 · Shuhuai Ren, Jinchao Zhang, Lei Li et al.2021 · 26 citationsarXiv
Adversarial parameter defense by multi-step risk minimization.34500254 · Zhang, Zhiyuan, Luo, Ruixuan, Ren, Xuancheng et al.2021 · 5 citationsNeural networks : the official journal of the International Neural Network Society. 2021;144:154-163
ASAT: Adaptively Scaled Adversarial Training in Time Series2108.08976v2 · Zhiyuan Zhang, Wei Li, Ruihan Bao et al.2021 · 6 citationsNeurocomputing 522 (2023) pp. 11-23
O2NA: An Object-Oriented Non-Autoregressive Approach for Controllable Video Captioning2108.02359v2 · Fenglin Liu, Xuancheng Ren, Xian Wu et al.2021 · 26 citationsarXiv
Contrastive Attention for Automatic Chest X-ray Report Generation2106.06965v5 · Fenglin Liu, Changchang Yin, Xian Wu et al.2021 · 178 citationsarXiv
Alleviating the Knowledge-Language Inconsistency: A Study for Deep Commonsense Knowledge2105.13607v2 · Yi Zhang, Lei Li, Yunfang Wu et al.2021 · 3 citationsarXiv
Learning Relation Alignment for Calibrated Cross-modal Retrieval2105.13868v2 · Shuhuai Ren, Junyang Lin, Guangxiang Zhao et al.2021 · 17 citationsarXiv
Be Careful about Poisoned Word Embeddings: Exploring the Vulnerability of the Embedding Layers in NLP Models2103.15543v1 · Wenkai Yang, Lei Li, Zhiyuan Zhang et al.2021 · 96 citationsarXiv
Multi-View Feature Representation for Dialogue Generation with Bidirectional Distillation2102.10780v1 · Shaoxiong Feng, Xuancheng Ren, Kan Li et al.2021 · 11 citationsarXiv
CascadeBERT: Accelerating Inference of Pre-trained Language Models via Calibrated Complete Models Cascade2012.14682v2 · Lei Li, Yankai Lin, Deli Chen et al.2020 · 35 citationsarXiv
EQG-RACE: Examination-Type Question Generation2012.06106v1 · Xin Jia, Wenjie Zhou, Xu Sun et al.2020 · 48 citationsarXiv
CAPT: Contrastive Pre-Training for Learning Denoised Sequence Representations2010.06351v4 · Fuli Luo, Pengcheng Yang, Shicheng Li et al.2020 · 14 citationsarXiv
Regularizing Dialogue Generation by Imitating Implicit Scenarios2010.01893v2 · Shaoxiong Feng, Xuancheng Ren, Hongshen Chen et al.2020 · 19 citationsarXiv
Graph-based Multi-hop Reasoning for Long Text Generation2009.13282v1 · Liang Zhao, Jingjing Xu, Junyang Lin et al.2020 · 10 citationsarXiv
Collaborative Group Learning2009.07712v4 · Shaoxiong Feng, Hongshen Chen, Xuancheng Ren et al.2020 · 11 citationsarXiv
Exploring the Vulnerability of Deep Neural Networks: A Study of Parameter Corruption2006.05620v2 · Xu Sun, Zhiyuan Zhang, Xuancheng Ren et al.2020 · 24 citationsarXiv
Building BROOK: A Multi-modal and Facial Video Database for Human-Vehicle Interaction Research2005.08637v2 · Xiangjun Peng, Zhentao Huang, Xu Sun2020 · 2 citationsarXiv
Parallel Data Augmentation for Formality Style Transfer2005.07522v1 · Yi Zhang, Tao Ge, Xu Sun2020 · 70 citationsarXiv
Jointly Modeling Aspect and Sentiment with Dynamic Heterogeneous Graph Neural Networks2004.06427v1 · Shu Liu, Wei Li, Yunfang Wu et al.2020 · 7 citationsarXiv
Exploring and Distilling Cross-Modal Information for Image Captioning2002.12585v2 · Fenglin Liu, Xuancheng Ren, Yuanxin Liu et al.2020 · 58 citationsarXiv
Mining Commonsense Facts from the Physical World2002.03149v3 · Yanyan Zou, Wei Lu, Xu Sun2020 · 1 citationarXiv
Visual Agreement Regularized Training for Multi-Modal Machine Translation1912.12014v1 · Pengcheng Yang, Boxing Chen, Pei Zhang et al.2019 · 37 citationsarXiv
Explicit Sparse Transformer: Concentrated Attention Through Explicit Selection1912.11637v1 · Guangxiang Zhao, Junyang Lin, Zhiyuan Zhang et al.2019 · 85 citationsarXiv
MUSE: Parallel Multi-Scale Attention for Sequence to Sequence Learning1911.09483v1 · Guangxiang Zhao, Xu Sun, Jingjing Xu et al.2019 · 41 citationsarXiv
Understanding and Improving Layer Normalization1911.07013v1 · Jingjing Xu, Xu Sun, Zhiyuan Zhang et al.2019 · 253 citationsarXiv
HighwayGraph: Modelling Long-distance Node Relations for Improving General Graph Neural Network1911.03904v2 · Deli Chen, Xiaoqian Liu, Yankai Lin et al.2019 · 3 citationsarXiv
An Adaptive and Momental Bound Method for Stochastic Learning1910.12249v1 · Jianbang Ding, Xuancheng Ren, Ruixuan Luo et al.2019 · 36 citationsarXiv
Pun-GAN: Generative Adversarial Network for Pun Generation1910.10950v1 · Fuli Luo, Shunyao Li, Pengcheng Yang et al.2019 · 24 citationsarXiv
Aligning Cross-Lingual Entities with Multi-Aspect Information1910.06575v1 · Hsiu-Wei Yang, Yanyan Zou, Peng Shi et al.2019 · 178 citationsarXiv
Group, Extract and Aggregate: Summarizing a Large Amount of Finance News for Forex Movement Prediction1910.05032v1 · Deli Chen, Shuming ma, Keiko Harimoto et al.2019 · 23 citationsarXiv
Recursive Graphical Neural Networks for Text Classification1909.08166v1 · Wei Li, Shuheng Li, Shuming Ma et al.2019 · 10 citationsarXiv
Sequence-to-sequence Pre-training with Data Augmentation for Sentence Rewriting1909.06002v2 · Yi Zhang, Tao Ge, Furu Wei et al.2019 · 15 citationsarXiv
Measuring and Relieving the Over-smoothing Problem for Graph Neural Networks from the Topological View1909.03211v2 · Deli Chen, Yankai Lin, Wei Li et al.2019 · 1,110 citationsarXiv
Career total: 185 works. 106 are in this corpus.Showing the 50 most recent.
Profile built from the corpus for this byline.
Author records are still filling in while the Hub is in alpha. If this is your page, you'll be able to claim it soon. Spot a mistake? Tell us.