1 code implementation • Findings (NAACL) 2022 • Wanjun Zhong, Siyuan Wang, Duyu Tang, Zenan Xu, Daya Guo, Yining Chen, Jiahai Wang, Jian Yin, Ming Zhou, Nan Duan
In this paper, we study the challenge of analytical reasoning of text and collect a new dataset consisting of questions from the Law School Admission Test from 1991 to 2016.
no code implementations • 7 Jun 2024 • Lianyu Pang, Jian Yin, Baoquan Zhao, Feize Wu, Fu Lee Wang, Qing Li, Xudong Mao
We attribute these issues to the incorrect learning of the embedding alignment for the concept.
1 code implementation • 23 May 2024 • Haiming Wang, Huajian Xin, Zhengying Liu, Wenda Li, Yinya Huang, Jianqiao Lu, Zhicheng Yang, Jing Tang, Jian Yin, Zhenguo Li, Xiaodan Liang
This approach allows the theorem to be tackled incrementally by outlining the overall theorem at the first level and then solving the intermediate conjectures at deeper levels.
no code implementations • 1 Feb 2024 • Qilong Yan, Yufeng Zhang, Jinghao Zhang, Jingpu Duan, Jian Yin
This could lead the meta-learner to face complex tasks too soon, hindering proper learning.
1 code implementation • 26 Dec 2023 • Lianyu Pang, Jian Yin, Haoran Xie, Qiping Wang, Qing Li, Xudong Mao
Additionally, a fast version of our method allows for capturing an input image in roughly 26 seconds, while surpassing the baseline methods in terms of both reconstruction and editability.
no code implementations • 31 Oct 2023 • Guoliang Lin, Hanjiang Lai, Yan Pan, Jian Yin
This new perspective allows us to explore how entropy minimization influences test-time adaptation.
1 code implementation • 1 Oct 2023 • Haiming Wang, Huajian Xin, Chuanyang Zheng, Lin Li, Zhengying Liu, Qingxing Cao, Yinya Huang, Jing Xiong, Han Shi, Enze Xie, Jian Yin, Zhenguo Li, Heng Liao, Xiaodan Liang
Our ablation study indicates that these newly added skills are indeed helpful for proving theorems, resulting in an improvement from a success rate of 47. 1% to 50. 4%.
Ranked #1 on Automated Theorem Proving on miniF2F-test (Pass@100 metric)
1 code implementation • ICCV 2023 • Wentao Hu, Jia Zheng, Zixin Zhang, Xiaojun Yuan, Jian Yin, Zihan Zhou
In this paper, we develop a new method to automatically convert 2D line drawings from three orthographic views into 3D CAD models.
1 code implementation • 26 Jun 2023 • Daya Guo, Canwen Xu, Nan Duan, Jian Yin, Julian McAuley
In this paper, we introduce a new task for code completion that focuses on handling long code input and propose a sparse Transformer model, called LongCoder, to address this task.
no code implementations • 20 Jun 2023 • Huiguo He, Tianfu Wang, Huan Yang, Jianlong Fu, Nicholas Jing Yuan, Jian Yin, Hongyang Chao, Qi Zhang
The proposed framework consists of a large language model (LLM), a diffusion-based image generator, and a series of visual rewards by design.
no code implementations • 1 Jun 2023 • Xiao Dong, Runhui Huang, XiaoYong Wei, Zequn Jie, Jianxing Yu, Jian Yin, Xiaodan Liang
Recent advances in vision-language pre-training have enabled machines to perform better in multimodal object discrimination (e. g., image-text semantic alignment) and image synthesis (e. g., text-to-image generation).
1 code implementation • 23 May 2023 • Da Yu, Sivakanth Gopi, Janardhan Kulkarni, Zinan Lin, Saurabh Naik, Tomasz Lukasz Religa, Jian Yin, Huishuai Zhang
Besides performance improvements, our framework also shows that with careful pre-training and private fine-tuning, smaller models can match the performance of much larger models that do not have access to private data, highlighting the promise of private learning as a tool for model compression and efficiency.
no code implementations • 5 May 2023 • Wangzhen Guo, Linyin Luo, Hanjiang Lai, Jian Yin
The parser uses the KoPL to generate the transparent logical forms.
no code implementations • CVPR 2023 • Liangdao Wang, Yan Pan, Cong Liu, Hanjiang Lai, Jian Yin, Ye Liu
This paper presents an optimization method that finds hash centers with a constraint on the minimal distance between any pair of hash centers, which is non-trivial due to the non-convex nature of the problem.
no code implementations • 20 Oct 2022 • Wanjun Zhong, Tingting Ma, Jiahai Wang, Jian Yin, Tiejun Zhao, Chin-Yew Lin, Nan Duan
This paper presents ReasonFormer, a unified reasoning framework for mirroring the modular and compositional reasoning process of humans in complex decision-making.
no code implementations • 12 Oct 2022 • Ge-Yang Ke, Yan Pan, Jian Yin, Chang-Qin Huang
The formulation of MTL that directly optimizes evaluation metrics is the combination of two parts: (1) a regularizer defined on the weight matrix over all tasks, in order to capture the relatedness of these tasks; (2) a sum of multiple structured hinge losses, each corresponding to a surrogate of some evaluation metric on one task.
1 code implementation • 28 Sep 2022 • Guoliang Lin, Yongheng Xu, Hanjiang Lai, Jian Yin
In this paper, we try to interpret these metric-based few-shot learning methods via causal mechanism.
no code implementations • 5 Aug 2022 • Wanjun Zhong, Yifan Gao, Ning Ding, Zhiyuan Liu, Ming Zhou, Jiahai Wang, Jian Yin, Nan Duan
Task generalization has been a long standing challenge in Natural Language Processing (NLP).
1 code implementation • 6 Jun 2022 • Da Yu, Gautam Kamath, Janardhan Kulkarni, Tie-Yan Liu, Jian Yin, Huishuai Zhang
Differentially private stochastic gradient descent (DP-SGD) is the workhorse algorithm for recent advances in private deep learning.
1 code implementation • NAACL 2022 • Wanjun Zhong, Yifan Gao, Ning Ding, Yujia Qin, Zhiyuan Liu, Ming Zhou, Jiahai Wang, Jian Yin, Nan Duan
Furthermore, ProQA exhibits strong ability in both continual learning and transfer learning by taking the advantages of the structural prompt.
1 code implementation • 28 Apr 2022 • Bowen Tian, Qinliang Su, Jian Yin
The goal of anomaly detection is to identify anomalous samples from normal ones.
2 code implementations • ACL 2022 • Daya Guo, Shuai Lu, Nan Duan, Yanlin Wang, Ming Zhou, Jian Yin
Furthermore, we propose to utilize multi-modal contents to learn representation of code fragment with contrastive learning, and then align representations among programming languages using a cross-modal generation task.
no code implementations • 15 Jan 2022 • Wanjun Zhong, JunJie Huang, Qian Liu, Ming Zhou, Jiahai Wang, Jian Yin, Nan Duan
CARP utilizes hybrid chain to model the explicit intermediate reasoning process across table and text for question answering.
Ranked #2 on Question Answering on OTT-QA
no code implementations • 14 Jan 2022 • Qinkang Gong, Liangdao Wang, Hanjiang Lai, Yan Pan, Jian Yin
Specifically, from pixels to continuous features, we first propose a feature-preserving module, using the corrupted image as input to reconstruct the original feature from the pre-trained ViT model and the complete image, so that the feature extractor can focus on preserving the meaningful information of original data.
1 code implementation • 12 Dec 2021 • Wentao Xu, Yingce Xia, Weiqing Liu, Jiang Bian, Jian Yin, Tie-Yan Liu
Next, we use a tree-attention aggregator to incorporate the graph structure information into the aggregation module on the meta-path.
2 code implementations • COLING 2022 • Zhiping Luo, Wentao Xu, Weiqing Liu, Jiang Bian, Jian Yin, Tie-Yan Liu
Learning the embeddings of knowledge graphs (KG) is vital in artificial intelligence, and can benefit various downstream applications, such as recommendation and question answering.
1 code implementation • 1 Nov 2021 • Da Yu, Huishuai Zhang, Wei Chen, Jian Yin, Tie-Yan Liu
We are the first to unveil an important population property of the perturbations of these attacks: they are almost \textbf{linearly separable} when assigned with the target labels of the corresponding samples, which hence can work as \emph{shortcuts} for the learning objective.
2 code implementations • 26 Oct 2021 • Wentao Xu, Weiqing Liu, Lewen Wang, Yingce Xia, Jiang Bian, Jian Yin, Tie-Yan Liu
To overcome the shortcomings of previous work, we proposed a novel stock trend forecasting framework that can adequately mine the concept-oriented shared information from predefined concepts and hidden concepts.
no code implementations • 14 Oct 2021 • Siyuan Liu, Yusong Wang, Tong Wang, Yifan Deng, Liang He, Bin Shao, Jian Yin, Nanning Zheng, Tie-Yan Liu
The identification of active binding drugs for target proteins (termed as drug-target interaction prediction) is the key challenge in virtual screening, which plays an essential role in drug discovery.
no code implementations • 29 Sep 2021 • Yunhao Zhang, Junchi Yan, Zhenyu Ren, Jian Yin
To fill the gap, we propose Mixture of Neural Temporal Point Processes (NTPP-MIX), a general framework that can utilize many existing NTPPs for event sequence clustering.
1 code implementation • 14 Sep 2021 • Wentao Xu, Weiqing Liu, Jiang Bian, Jian Yin, Tie-Yan Liu
In this paper, we propose a simple yet efficient instance-wise graph-based framework to utilize the inter-dependencies of different variables at different time stamps for multivariate time series forecasting.
no code implementations • ICLR 2022 • Daya Guo, Alexey Svyatkovskiy, Jian Yin, Nan Duan, Marc Brockschmidt, Miltiadis Allamanis
To evaluate models, we consider both ROUGE as well as a new metric RegexAcc that measures success of generating completions matching long outputs with as few holes as possible.
1 code implementation • 17 Jun 2021 • Da Yu, Huishuai Zhang, Wei Chen, Jian Yin, Tie-Yan Liu
We propose a reparametrization scheme to address the challenges of applying differentially private SGD on large neural networks, which are 1) the huge memory cost of storing individual gradients, 2) the added noise suffering notorious dimensional dependence.
no code implementations • 17 May 2021 • Andrey Ignatov, Grigory Malivenko, David Plowman, Samarth Shukla, Radu Timofte, Ziyu Zhang, Yicheng Wang, Zilong Huang, Guozhong Luo, Gang Yu, Bin Fu, Yiran Wang, Xingyi Li, Min Shi, Ke Xian, Zhiguo Cao, Jin-Hua Du, Pei-Lin Wu, Chao Ge, Jiaoyang Yao, Fangwen Tu, Bo Li, Jung Eun Yoo, Kwanggyoon Seo, Jialei Xu, Zhenyu Li, Xianming Liu, Junjun Jiang, Wei-Chi Chen, Shayan Joya, Huanhuan Fan, Zhaobing Kang, Ang Li, Tianpeng Feng, Yang Liu, Chuannan Sheng, Jian Yin, Fausto T. Benavide
While many solutions have been proposed for this task, they are usually very computationally expensive and thus are not applicable for on-device inference.
1 code implementation • 14 Apr 2021 • Wanjun Zhong, Siyuan Wang, Duyu Tang, Zenan Xu, Daya Guo, Jiahai Wang, Jian Yin, Ming Zhou, Nan Duan
Analytical reasoning is an essential and challenging task that requires a system to analyze a scenario involving a set of particular circumstances and perform reasoning over it to make conclusions.
no code implementations • 15 Feb 2021 • Wentao Xu, Weiqing Liu, Chang Xu, Jiang Bian, Jian Yin, Tie-Yan Liu
To remedy the first shortcoming, we propose to model the stock context and learn the effect of event information on the stocks under different contexts.
1 code implementation • EMNLP 2020 • Wanjun Zhong, Duyu Tang, Zenan Xu, Ruize Wang, Nan Duan, Ming Zhou, Jiahai Wang, Jian Yin
To address this, we propose a graph-based model that utilizes the factual structure of a document for deepfake detection of text.
1 code implementation • ICLR 2021 • Daya Guo, Shuo Ren, Shuai Lu, Zhangyin Feng, Duyu Tang, Shujie Liu, Long Zhou, Nan Duan, Alexey Svyatkovskiy, Shengyu Fu, Michele Tufano, Shao Kun Deng, Colin Clement, Dawn Drain, Neel Sundaresan, Jian Yin, Daxin Jiang, Ming Zhou
Instead of taking syntactic-level structure of code like abstract syntax tree (AST), we use data flow in the pre-training stage, which is a semantic-level structure of code that encodes the relation of "where-the-value-comes-from" between variables.
Ranked #3 on Type prediction on ManyTypes4TypeScript
1 code implementation • 21 Jul 2020 • Da Yu, Huishuai Zhang, Wei Chen, Jian Yin, Tie-Yan Liu
Even further, we show that the proposed approach can achieve higher MI attack success rates on models trained with some data augmentation than the existing methods on models trained without data augmentation.
no code implementations • ACL 2020 • Jianxing Yu, Wei Liu, Shuang Qiu, Qinliang Su, Kai Wang, Xiaojun Quan, Jian Yin
Specifically, we first build a multi-hop generation model and guide it to satisfy the logical rationality by the reasoning chain extracted from a given text.
1 code implementation • ACL 2020 • Daya Guo, Duyu Tang, Nan Duan, Jian Yin, Daxin Jiang, Ming Zhou
Generating inferential texts about an event in different perspectives requires reasoning over different contexts that the event occurs.
Ranked #1 on Common Sense Reasoning on Event2Mind test (BLEU metric)
1 code implementation • ACL 2020 • Wentao Xu, Shun Zheng, Liang He, Bin Shao, Jian Yin, Tie-Yan Liu
In recent years, knowledge graph embedding becomes a pretty hot research topic of artificial intelligence and plays increasingly vital roles in various downstream applications, such as recommendation and question answering.
Ranked #1 on Link Prediction on YAGO37
no code implementations • ACL 2020 • Wanjun Zhong, Duyu Tang, Zhangyin Feng, Nan Duan, Ming Zhou, Ming Gong, Linjun Shou, Daxin Jiang, Jiahai Wang, Jian Yin
The graph is used to obtain graph-enhanced contextual representations of words in Transformer-based architecture.
no code implementations • 25 Apr 2020 • Wanjun Zhong, Duyu Tang, Nan Duan, Ming Zhou, Jiahai Wang, Jian Yin
We study question answering over a dynamic textual environment.
no code implementations • 7 Apr 2020 • Daya Guo, Akari Asai, Duyu Tang, Nan Duan, Ming Gong, Linjun Shou, Daxin Jiang, Jian Yin, Ming Zhou
In this work, we use multiple knowledge sources as fuels for the model.
no code implementations • 20 Dec 2019 • Haien Zeng, Hanjiang Lai, Jian Yin
Second, since the image may contain other unwanted attributes, an attribute disentanglement network is used to separate the individual embedding and learn the common embedding that contains information about the face attribute (e. g., race).
no code implementations • 26 Nov 2019 • Da Yu, Huishuai Zhang, Wei Chen, Tie-Yan Liu, Jian Yin
By using the \emph{expected curvature}, we show that gradient perturbation can achieve a significantly improved utility guarantee that can theoretically justify the advantage of gradient perturbation over other perturbation methods.
no code implementations • 19 Nov 2019 • Haien Zeng, Hanjiang Lai, Jian Yin
Fine-grained image hashing is a challenging problem due to the difficulties of discriminative region localization and hash code generation.
no code implementations • 19 Nov 2019 • Haien Zeng, Hanjiang Lai, Hanlu Chu, Yong Tang, Jian Yin
The modal-aware operation consists of a kernel network and an attention network.
no code implementations • ACL 2020 • Wanjun Zhong, Jingjing Xu, Duyu Tang, Zenan Xu, Nan Duan, Ming Zhou, Jiahai Wang, Jian Yin
We evaluate our system on FEVER, a benchmark dataset for fact checking, and find that rich structural information is helpful and both our graph-based mechanisms improve the accuracy.
Ranked #2 on Fact Verification on FEVER
no code implementations • ACL 2019 • Jianxing Yu, Zheng-Jun Zha, Jian Yin
This paper focuses on the topic of inferential machine comprehension, which aims to fully understand the meanings of given text to answer generic questions, especially the ones needed reasoning skills.
no code implementations • ACL 2019 • Daya Guo, Duyu Tang, Nan Duan, Ming Zhou, Jian Yin
In this paper, we present an approach to incorporate retrieved datapoints as supporting evidence for context-dependent semantic parsing, such as generating source code conditioned on the class environment.
no code implementations • CVPR 2020 • Haoye Dong, Xiaodan Liang, Yixuan Zhang, Xujie Zhang, Zhenyu Xie, Bowen Wu, Ziqi Zhang, Xiaohui Shen, Jian Yin
Interactive fashion image manipulation, which enables users to edit images with sketches and color strokes, is an interesting research problem with great application value.
no code implementations • 4 Apr 2019 • Yifan Yang, Libing Geng, Hanjiang Lai, Yan Pan, Jian Yin
In recent years, deep-networks-based hashing has become a leading approach for large-scale image retrieval.
no code implementations • 3 Apr 2019 • Shaoying Wang, Haijiang Lai, Yifan Yang, Jian Yin
The following three steps are repeated until convergence: 1) the database network encodes all training samples into binary codes to obtain a whole rank list, 2) the query network is trained based on policy learning to maximize a reward that indicates the performance of the whole ranking list of binary codes, e. g., mean average precision (MAP), and 3) the database network is updated as the query network.
no code implementations • ICCV 2019 • Haoye Dong, Xiaodan Liang, Bochao Wang, Hanjiang Lai, Jia Zhu, Jian Yin
Given an input person image, a desired clothes image, and a desired pose, the proposed Multi-pose Guided Virtual Try-on Network (MG-VTON) can generate a new person image after fitting the desired clothes into the input image and manipulating human poses.
Ranked #1 on Virtual Try-on on Deep-Fashion
1 code implementation • NeurIPS 2018 • Daya Guo, Duyu Tang, Nan Duan, Ming Zhou, Jian Yin
We present an approach to map utterances in conversation to logical forms, which will be executed on a large-scale knowledge base.
no code implementations • NeurIPS 2018 • Haoye Dong, Xiaodan Liang, Ke Gong, Hanjiang Lai, Jia Zhu, Jian Yin
Despite remarkable advances in image synthesis research, existing works often fail in manipulating images under the context of large geometric transformations.
no code implementations • 5 Sep 2018 • Wanjun Zhong, Duyu Tang, Nan Duan, Ming Zhou, Jiahai Wang, Jian Yin
Although neural network approaches achieve remarkable success on a variety of NLP tasks, many of them struggle to answer questions that require commonsense knowledge.
no code implementations • EMNLP 2018 • Daya Guo, Yibo Sun, Duyu Tang, Nan Duan, Jian Yin, Hong Chi, James Cao, Peng Chen, Ming Zhou
We study how to learn a semantic parser of state-of-the-art accuracy with less supervised training data.
no code implementations • COLING 2018 • Danqing Huang, Jing Liu, Chin-Yew Lin, Jian Yin
Experimental results show that (1) The copy and alignment mechanism is effective to address the two issues; (2) Reinforcement learning leads to better performance than maximum likelihood on this task; (3) Our neural model is complementary to the feature-based model and their combination significantly outperforms the state-of-the-art results.
no code implementations • ACL 2018 • Danqing Huang, Jin-Ge Yao, Chin-Yew Lin, Qingyu Zhou, Jian Yin
To solve math word problems, previous statistical approaches attempt at learning a direct mapping from a problem description to its corresponding equation system.
no code implementations • 26 Nov 2017 • Siyu Zhou, Weiqiang Zhao, Jiashi Feng, Hanjiang Lai, Yan Pan, Jian Yin, Shuicheng Yan
Second, we propose a new occupational-aware adversarial face aging network, which learns human aging process under different occupations.
no code implementations • 26 Nov 2017 • Xi Zhang, Siyu Zhou, Jiashi Feng, Hanjiang Lai, Bo Li, Yan Pan, Jian Yin, Shuicheng Yan
The proposed new adversarial network, HashGAN, consists of three building blocks: 1) the feature learning module to obtain feature representations, 2) the generative attention module to generate an attention mask, which is used to obtain the attended (foreground) and the unattended (background) feature representations, 3) the discriminative hash coding module to learn hash functions that preserve the similarities between different modalities.
no code implementations • EMNLP 2017 • Danqing Huang, Shuming Shi, Chin-Yew Lin, Jian Yin
This method learns the mappings between math concept phrases in math word problems and their math expressions from training data.
no code implementations • 30 Oct 2015 • Hanjiang Lai, Shengtao Xiao, Yan Pan, Zhen Cui, Jiashi Feng, Chunyan Xu, Jian Yin, Shuicheng Yan
We propose a novel end-to-end deep architecture for face landmark detection, based on a deep convolutional and deconvolutional network followed by carefully designed recurrent network structures.