1 code implementation • 17 Mar 2024 • Feifan Song, Bowen Yu, Hao Lang, Haiyang Yu, Fei Huang, Houfeng Wang, Yongbin Li
Additionally, the concept of diversity for prompts can be more complex than responses that are typically quantified by single digits.
no code implementations • 4 Mar 2024 • Yilong Ren, Yue Chen, Shuai Liu, Boyue Wang, Haiyang Yu, Zhiyong Cui
Traffic prediction constitutes a pivotal facet within the purview of Intelligent Transportation Systems (ITS), and the attainment of highly precise predictions holds profound significance for efficacious traffic management.
no code implementations • 27 Feb 2024 • Xinyu Lu, Bowen Yu, Yaojie Lu, Hongyu Lin, Haiyang Yu, Le Sun, Xianpei Han, Yongbin Li
The alignment problem in Large Language Models (LLMs) involves adapting them to the broad spectrum of human values.
no code implementations • 23 Feb 2024 • Qiaoyu Tang, Jiawei Chen, Bowen Yu, Yaojie Lu, Cheng Fu, Haiyang Yu, Hongyu Lin, Fei Huang, Ben He, Xianpei Han, Le Sun, Yongbin Li
The rise of large language models (LLMs) has transformed the role of information retrieval (IR) systems in the way to humans accessing information.
1 code implementation • 12 Feb 2024 • Meng-Chieh Lee, Haiyang Yu, Jian Zhang, Vassilis N. Ioannidis, Xiang Song, Soji Adeshina, Da Zheng, Christos Faloutsos
Given a node-attributed graph, and a graph task (link prediction or node classification), can we tell if a graph neural network (GNN) will perform well?
no code implementations • 3 Feb 2024 • Long Ma, Jiajia Zhang, Hongping Deng, Ningyu Zhang, Yong Liao, Haiyang Yu
The escalating quality of video generated by advanced video generation methods leads to new security challenges in society, which makes generated video detection an urgent research priority.
no code implementations • 20 Dec 2023 • Lening Wang, Yilong Ren, Han Jiang, Pinlong Cai, Daocheng Fu, Tianqi Wang, Zhiyong Cui, Haiyang Yu, Xuesong Wang, Hanchu Zhou, Helai Huang, Yinhai Wang
For human-driven vehicles, we offer proactive long-range safety warnings and blind-spot alerts while also providing safety driving recommendations and behavioral norms through human-machine dialogue and interaction.
1 code implementation • 4 Dec 2023 • Haoyu Jiang, Haiyang Yu, Nan Li, Ping Yi
We then pre-train a generative self-supervised graph autoencoder (GAE) to better learn the features of benign models in order to detect backdoor models without knowing the attack strategy.
1 code implementation • 6 Nov 2023 • Le Yu, Bowen Yu, Haiyang Yu, Fei Huang, Yongbin Li
Then, we use DARE as a versatile plug-and-play technique to sparsify delta parameters of multiple SFT homologous models for mitigating parameter interference and merge them into a single model by parameter fusing.
1 code implementation • 23 Oct 2023 • Qi Gou, Zehua Xia, Bowen Yu, Haiyang Yu, Fei Huang, Yongbin Li, Nguyen Cam-Tu
Given a textual passage and an answer, humans are able to ask questions with various expressions, but this ability is still challenging for most question generation (QG) systems.
1 code implementation • 20 Oct 2023 • Zehua Xia, Qi Gou, Bowen Yu, Haiyang Yu, Fei Huang, Yongbin Li, Cam-Tu Nguyen
Previous studies have suggested that key phrase selection is essential for question generation (QG), yet it is still challenging to connect such disjointed phrases into meaningful questions, particularly for long context.
no code implementations • 9 Sep 2023 • Teng Fu, Xiaocong Wang, Haiyang Yu, Ke Niu, Bin Li, xiangyang xue
Multiple object tracking (MOT) tends to become more challenging when severe occlusions occur.
1 code implementation • 3 Sep 2023 • Haiyang Yu, Xiaocong Wang, Bin Li, xiangyang xue
We conduct experiments on a scene dataset for benchmarking Chinese text recognition, and the results demonstrate that the proposed method can indeed improve performance through disentangling content and orientation information.
1 code implementation • ICCV 2023 • Haiyang Yu, Xiaocong Wang, Bin Li, xiangyang xue
However, despite Chinese characters possessing different characteristics from Latin characters, such as complex inner structures and large categories, few methods have been proposed for Chinese Text Recognition (CTR).
1 code implementation • 10 Aug 2023 • Yingxiu Zhao, Bowen Yu, Binyuan Hui, Haiyang Yu, Fei Huang, Yongbin Li, Nevin L. Zhang
Training large language models (LLMs) with open-domain instruction data has yielded remarkable success in aligning to end tasks and human preferences.
1 code implementation • 3 Aug 2023 • Xinghua Zhang, Bowen Yu, Haiyang Yu, Yangyu Lv, Tingwen Liu, Fei Huang, Hongbo Xu, Yongbin Li
Each perspective corresponds to the role of a specific LLM neuron in the first layer.
1 code implementation • 17 Jul 2023 • Xuan Zhang, Limei Wang, Jacob Helwig, Youzhi Luo, Cong Fu, Yaochen Xie, Meng Liu, Yuchao Lin, Zhao Xu, Keqiang Yan, Keir Adams, Maurice Weiler, Xiner Li, Tianfan Fu, Yucheng Wang, Haiyang Yu, Yuqing Xie, Xiang Fu, Alex Strasser, Shenglong Xu, Yi Liu, Yuanqi Du, Alexandra Saxton, Hongyi Ling, Hannah Lawrence, Hannes Stärk, Shurui Gui, Carl Edwards, Nicholas Gao, Adriana Ladera, Tailin Wu, Elyssa F. Hofgard, Aria Mansouri Tehrani, Rui Wang, Ameya Daigavane, Montgomery Bohde, Jerry Kurtin, Qian Huang, Tuong Phung, Minkai Xu, Chaitanya K. Joshi, Simon V. Mathis, Kamyar Azizzadenesheli, Ada Fang, Alán Aspuru-Guzik, Erik Bekkers, Michael Bronstein, Marinka Zitnik, Anima Anandkumar, Stefano Ermon, Pietro Liò, Rose Yu, Stephan Günnemann, Jure Leskovec, Heng Ji, Jimeng Sun, Regina Barzilay, Tommi Jaakkola, Connor W. Coley, Xiaoning Qian, Xiaofeng Qian, Tess Smidt, Shuiwang Ji
Advances in artificial intelligence (AI) are fueling a new paradigm of discoveries in natural sciences.
1 code implementation • 30 Jun 2023 • Feifan Song, Bowen Yu, Minghao Li, Haiyang Yu, Fei Huang, Yongbin Li, Houfeng Wang
In this manner, PRO effectively transforms human alignment into aligning the probability ranking of n responses generated by LLM with the preference ranking of humans towards these responses.
no code implementations • 29 Jun 2023 • Bowen Yu, Cheng Fu, Haiyang Yu, Fei Huang, Yongbin Li
When trying to answer complex questions, people often rely on multiple sources of information, such as visual, textual, and tabular data.
no code implementations • 18 Jun 2023 • Xin Cong. Bowen Yu, Mengcheng Fang, Tingwen Liu, Haiyang Yu, Zhongkai Hu, Fei Huang, Yongbin Li, Bin Wang
Inspired by the fact that large amount of knowledge are stored in the pretrained language models~(PLM) and can be retrieved explicitly, in this paper, we propose MetaRetriever to retrieve task-specific knowledge from PLMs to enhance universal IE.
1 code implementation • NeurIPS 2023 • Haiyang Yu, Meng Liu, Youzhi Luo, Alex Strasser, Xiaofeng Qian, Xiaoning Qian, Shuiwang Ji
Supervised machine learning approaches have been increasingly used in accelerating electronic structure prediction as surrogates of first-principle computational methods, such as density functional theory (DFT).
1 code implementation • 8 Jun 2023 • Haiyang Yu, Zhao Xu, Xiaofeng Qian, Xiaoning Qian, Shuiwang Ji
We consider the prediction of the Hamiltonian matrix, which finds use in quantum chemistry and condensed matter physics.
no code implementations • 22 May 2023 • Zihao Chen, Jia Lu, Xing-Ming Zhao, Haiyang Yu, Chunhe Li
Our results revealed the underlying mechanism for intermediate cell states governing the CAC, and identified new potential drug combinations to induce cancer adipogenesis.
1 code implementation • 18 May 2023 • Yingxiu Zhao, Bowen Yu, Haiyang Yu, Bowen Li, Jinyang Li, Chao Wang, Fei Huang, Yongbin Li, Nevin L. Zhang
To tackle this issue, we are the first to present a causally-complete dataset construction strategy for building million-level DocGD pre-training corpora.
no code implementations • 9 May 2023 • Shangchao Su, Haiyang Yu, Bin Li, xiangyang xue
In Chinese text recognition, to compensate for the insufficient local data and improve the performance of local few-shot character recognition, it is often necessary for one organization to collect a large amount of data from similar organizations.
no code implementations • 14 Apr 2023 • Minghao Li, Yingxiu Zhao, Bowen Yu, Feifan Song, Hangyu Li, Haiyang Yu, Zhoujun Li, Fei Huang, Yongbin Li
(2) How can we enhance LLMs' ability to utilize tools?
no code implementations • 20 Mar 2023 • Xinyan Zu, Haiyang Yu, Bin Li, xiangyang xue
Text segmentation is a challenging vision task with many downstream applications.
no code implementations • 18 Mar 2023 • Ziyang Ye, Haiyang Yu, Bin Li
To estimate the uncertainty, we propose a module named Pyramid Covariance Predictor to predict the covariance matrices of the target Gaussian distributions, which determine the distributions of landmarks and represent the uncertainty of landmark annotation.
no code implementations • 23 Feb 2023 • Yeqin Zhang, Haomin Fu, Cheng Fu, Haiyang Yu, Yongbin Li, Cam-Tu Nguyen
Specifically, the former efficiently finds relevant passages in a retrieval-and-reranking process, whereas the latter effectively extracts finer-grain spans within those passages to incorporate into a parametric answer generation model (BART, T5).
no code implementations • 29 Nov 2022 • Bowen Yu, Zhenyu Zhang, Jingyang Li, Haiyang Yu, Tingwen Liu, Jian Sun, Yongbin Li, Bin Wang
Open Information Extraction (OpenIE) facilitates the open-domain discovery of textual facts.
no code implementations • 24 Nov 2022 • Haiyang Yu, Jingye Chen, Bin Li, xiangyang xue
In this paper, we represent each Chinese character as a stroke tree, which is organized according to its radical structures, to fully exploit the merits of both radical and stroke levels in a decent way.
1 code implementation • 23 Nov 2022 • Yingxiu Zhao, Yinhe Zheng, Bowen Yu, Zhiliang Tian, Dongkyu Lee, Jian Sun, Haiyang Yu, Yongbin Li, Nevin L. Zhang
In this paper, we explore a novel setting, semi-supervised lifelong language learning (SSLL), where a model learns sequentially arriving language tasks with both labeled and unlabeled data.
no code implementations • 20 Oct 2022 • Haomin Fu, Yeqin Zhang, Haiyang Yu, Jian Sun, Fei Huang, Luo Si, Yongbin Li, Cam-Tu Nguyen
This paper introduces Doc2Bot, a novel dataset for building machines that help users seek information via conversations.
1 code implementation • 14 Oct 2022 • Yingxiu Zhao, Yinhe Zheng, Zhiliang Tian, Chang Gao, Bowen Yu, Haiyang Yu, Yongbin Li, Jian Sun, Nevin L. Zhang
Lifelong learning (LL) is vital for advanced task-oriented dialogue (ToD) systems.
no code implementations • 14 Jul 2022 • Zhenyu Zhang, Bowen Yu, Haiyang Yu, Tingwen Liu, Cheng Fu, Jingyang Li, Chengguang Tang, Jian Sun, Yongbin Li
In this paper, we propose a Layout-aware document-level Information Extraction dataset, LIE, to facilitate the study of extracting both structural and semantic knowledge from visually rich documents (VRDs), so as to generate accurate responses in dialogue systems.
no code implementations • 15 Jun 2022 • Jack FitzGerald, Shankar Ananthakrishnan, Konstantine Arkoudas, Davide Bernardi, Abhishek Bhagia, Claudio Delli Bovi, Jin Cao, Rakesh Chada, Amit Chauhan, Luoxin Chen, Anurag Dwarakanath, Satyam Dwivedi, Turan Gojayev, Karthik Gopalakrishnan, Thomas Gueudre, Dilek Hakkani-Tur, Wael Hamza, Jonathan Hueser, Kevin Martin Jose, Haidar Khan, Beiye Liu, Jianhua Lu, Alessandro Manzotti, Pradeep Natarajan, Karolina Owczarzak, Gokmen Oz, Enrico Palumbo, Charith Peris, Chandana Satya Prakash, Stephen Rawls, Andy Rosenbaum, Anjali Shenoy, Saleh Soltan, Mukund Harakere Sridhar, Liz Tan, Fabian Triefenbach, Pan Wei, Haiyang Yu, Shuai Zheng, Gokhan Tur, Prem Natarajan
We present results from a large-scale experiment on pretraining encoders with non-embedding parameter counts ranging from 700M to 9. 3B, their subsequent distillation into smaller models ranging from 17M-170M parameters, and their application to the Natural Language Understanding (NLU) component of a virtual assistant system.
Cross-Lingual Natural Language Inference intent-classification +5
1 code implementation • 14 Jun 2022 • Haiyang Yu, Limei Wang, Bokun Wang, Meng Liu, Tianbao Yang, Shuiwang Ji
GraphFM-IB applies FM to in-batch sampled data, while GraphFM-OB applies FM to out-of-batch data that are 1-hop neighborhood of in-batch data.
no code implementations • 4 Jun 2022 • Meng Liu, Haiyang Yu, Shuiwang Ji
Message passing graph neural networks (GNNs) are known to have their expressiveness upper-bounded by 1-dimensional Weisfeiler-Leman (1-WL) algorithm.
no code implementations • 24 May 2022 • Shaowen Zhou, Bowen Yu, Aixin Sun, Cheng Long, Jingyang Li, Haiyang Yu, Jian Sun, Yongbin Li
Open Information Extraction (OpenIE) facilitates domain-independent discovery of relational facts from large corpora.
Ranked #1 on Open Information Extraction on CaRB
Natural Language Understanding Open-Domain Question Answering +1
1 code implementation • 10 Jan 2022 • Ningyu Zhang, Xin Xu, Liankuan Tao, Haiyang Yu, Hongbin Ye, Shuofei Qiao, Xin Xie, Xiang Chen, Zhoubo Li, Lei LI, Xiaozhuan Liang, Yunzhi Yao, Shumin Deng, Peng Wang, Wen Zhang, Zhenru Zhang, Chuanqi Tan, Qiang Chen, Feiyu Xiong, Fei Huang, Guozhou Zheng, Huajun Chen
We present an open-source and extensible knowledge extraction toolkit DeepKE, supporting complicated low-resource, document-level and multimodal scenarios in the knowledge base population.
1 code implementation • 30 Dec 2021 • Haiyang Yu, Jingye Chen, Bin Li, jianqi ma, Mengnan Guan, Xixi Xu, Xiaocong Wang, Shaobo Qu, xiangyang xue
The experimental results indicate that the performance of baselines on CTR datasets is not as good as that on English datasets due to the characteristics of Chinese texts that are quite different from the Latin alphabet.
1 code implementation • 13 Dec 2021 • Jingye Chen, Haiyang Yu, jianqi ma, Bin Li, xiangyang xue
However, the recognition of low-resolution scene text images remains a challenge.
no code implementations • 20 Apr 2021 • Zhen Bi, Ningyu Zhang, Ganqiang Ye, Haiyang Yu, Xi Chen, Huajun Chen
Recent neural-based aspect-based sentiment analysis approaches, though achieving promising improvement on benchmark datasets, have reported suffering from poor robustness when encountering confounder such as non-target aspects.
Aspect-Based Sentiment Analysis Aspect-Based Sentiment Analysis (ABSA)
1 code implementation • 23 Mar 2021 • Meng Liu, Youzhi Luo, Limei Wang, Yaochen Xie, Hao Yuan, Shurui Gui, Haiyang Yu, Zhao Xu, Jingtun Zhang, Yi Liu, Keqiang Yan, Haoran Liu, Cong Fu, Bora Oztekin, Xuan Zhang, Shuiwang Ji
Although there exist several libraries for deep learning on graphs, they are aiming at implementing basic operations for graph deep learning.
1 code implementation • 9 Feb 2021 • Hao Yuan, Haiyang Yu, Jie Wang, Kang Li, Shuiwang Ji
To make the tree search more effective, we propose to use Shapley values as a measure of subgraph importance, which can also capture the interactions among different subgraphs.
no code implementations • 31 Dec 2020 • Hao Yuan, Haiyang Yu, Shurui Gui, Shuiwang Ji
To facilitate evaluations, we generate a set of benchmark graph datasets specifically for GNN explainability.
no code implementations • COLING 2020 • Haiyang Yu, Ningyu Zhang, Shumin Deng, Hongbin Ye, Wei zhang, Huajun Chen
Current supervised relational triple extraction approaches require huge amounts of labeled data and thus suffer from poor performance in few-shot settings.
no code implementations • 11 Oct 2020 • Xiaolei Ma, Enze Huo, Haiyang Yu, Honghai Li
Truck platooning refers to a series of trucks driving in close proximity via communication technologies, and it is considered one of the most implementable systems of connected and automated vehicles, bringing huge energy savings and safety improvements.
1 code implementation • EMNLP 2020 • Ningyu Zhang, Shumin Deng, Zhen Bi, Haiyang Yu, Jiacheng Yang, Mosha Chen, Fei Huang, Wei zhang, Huajun Chen
We introduce a prototype model and provide an open-source and extensible toolkit called OpenUE for various extraction tasks.
Ranked #3 on Joint Entity and Relation Extraction on WebNLG
1 code implementation • 15 Sep 2020 • Haiyang Yu, Ningyu Zhang, Shumin Deng, Zonggang Yuan, Yantao Jia, Huajun Chen
Long-tailed relation classification is a challenging problem as the head classes may dominate the training phase, thereby leading to the deterioration of the tail performance.
no code implementations • 26 Jul 2020 • Bin Fu, Yunqi Qiu, Chengguang Tang, Yang Li, Haiyang Yu, Jian Sun
Question Answering (QA) over Knowledge Base (KB) aims to automatically answer natural language questions via well-structured relation information between entities stored in knowledge bases.
no code implementations • 7 May 2017 • Haiyang Yu, Zhihai Wu, Shuqin Wang, Yunpeng Wang, Xiaolei Ma
Inspired by the domain knowledge of motion prediction, in which the future motion of an object can be predicted based on previous scenes, we propose a network grid representation method that can retain the fine-scale structure of a transportation network.