no code implementations • 1 Apr 2024 • Shikai Li, Jianglin Fu, Kaiyuan Liu, Wentao Wang, Kwan-Yee Lin, Wayne Wu
We present CosmicMan, a text-to-image foundation model specialized for generating high-fidelity human images.
1 code implementation • 12 Feb 2024 • Yulu Qin, Wentao Wang, Brenden M. Lake
However, a significant gap exists between the training data for these models and the linguistic input a child receives.
1 code implementation • 1 Feb 2024 • A. Emin Orhan, Wentao Wang, Alex N. Wang, Mengye Ren, Brenden M. Lake
These results suggest that important temporal aspects of a child's internal model of the world may be learnable from their visual experience using highly generic learning algorithms and without strong inductive biases.
1 code implementation • 16 Dec 2023 • Wentao Wang, Xuanyao Huang, Tianyang Wang, Swalpa Kumar Roy
This paper explores the image synthesis capabilities of GPT-4, a leading multi-modal large language model.
1 code implementation • bioRxiv 2023 • Yilun Zhang, Wentao Wang, Jiahui Guan, Deepak Kumar Jain, Tianyang Wang, Swalpa Kumar Roy
Drug-target interactions (DTIs) is essential for advancing pharmaceuticals.
1 code implementation • 10 Feb 2023 • Harry Shomer, Wei Jin, Wentao Wang, Jiliang Tang
It aims to predict unseen edges by learning representations for all the entities and relations in a KG.
1 code implementation • 22 Sep 2022 • Xue Yang, Gefan Zhang, Xiaojiang Yang, Yue Zhou, Wentao Wang, Jin Tang, Tao He, Junchi Yan
Existing detection methods commonly use a parameterized bounding box (BBox) to model and detect (horizontal) objects and an additional rotation angle parameter is used for rotated objects.
no code implementations • 2 May 2022 • Yaxin Li, Xiaorui Liu, Han Xu, Wentao Wang, Jiliang Tang
Deep Neural Network (DNN) are vulnerable to adversarial attacks.
3 code implementations • 29 Jan 2022 • Xue Yang, Yue Zhou, Gefan Zhang, Jirui Yang, Wentao Wang, Junchi Yan, Xiaopeng Zhang, Qi Tian
This is in contrast to recent Gaussian modeling based rotation detectors e. g. GWD loss and KLD loss that involve a human-specified distribution distance metric which require additional hyperparameter tuning that vary across datasets and detectors.
no code implementations • CVPR 2022 • Wentao Wang, Li Niu, Jianfu Zhang, Xue Yang, Liqing Zhang
Different from feed-forward methods, they seek for a closest latent code to the corrupted image and feed it to a pretrained generator.
no code implementations • 28 Jul 2021 • Wentao Wang, Han Xu, Xiaorui Liu, Yaxin Li, Bhavani Thuraisingham, Jiliang Tang
Adversarial training has been empirically proven to be one of the most effective and reliable defense methods against adversarial attacks.
no code implementations • 9 Jun 2021 • Han Xu, Xiaorui Liu, Wentao Wang, Wenbiao Ding, Zhongqin Wu, Zitao Liu, Anil Jain, Jiliang Tang
In this work, we study the effect of memorization in adversarial trained DNNs and disclose two important findings: (a) Memorizing atypical samples is only effective to improve DNN's accuracy on clean atypical samples, but hardly improve their adversarial robustness and (b) Memorizing certain atypical samples will even hurt the DNN's performance on typical samples.
2 code implementations • NeurIPS 2021 • Xue Yang, Xiaojiang Yang, Jirui Yang, Qi Ming, Wentao Wang, Qi Tian, Junchi Yan
Taking the perspective that horizontal detection is a special case for rotated object detection, in this paper, we are motivated to change the design of rotation regression loss from induction paradigm to deduction methodology, in terms of the relation between rotation and horizontal detection.
Ranked #14 on Object Detection In Aerial Images on DOTA (using extra training data)
2 code implementations • 28 Jan 2021 • Xue Yang, Junchi Yan, Qi Ming, Wentao Wang, Xiaopeng Zhang, Qi Tian
Boundary discontinuity and its inconsistency to the final detection metric have been the bottleneck for rotating detection regression loss design.
Ranked #16 on Object Detection In Aerial Images on DOTA (using extra training data)
no code implementations • ICCV 2021 • Wentao Wang, Jianfu Zhang, Li Niu, Haoyu Ling, Xue Yang, Liqing Zhang
Conventional deep image inpainting methods are based on auto-encoder architecture, in which the spatial details of images will be lost in the down-sampling process, leading to the degradation of generated results.
3 code implementations • CVPR 2021 • Xue Yang, Liping Hou, Yue Zhou, Wentao Wang, Junchi Yan
Rotation detection serves as a fundamental building block in many visual applications involving aerial image, scene text, and face etc.
Ranked #29 on Object Detection In Aerial Images on DOTA (using extra training data)
1 code implementation • EMNLP 2020 • Haochen Liu, Wentao Wang, Yiqi Wang, Hui Liu, Zitao Liu, Jiliang Tang
Extensive experiments on two real-world conversation datasets show that our framework significantly reduces gender bias in dialogue models while maintaining the response quality.
1 code implementation • 23 Sep 2020 • Wentao Wang, Guowei Xu, Wenbiao Ding, Gale Yan Huang, Guoliang Li, Jiliang Tang, Zitao Liu
Extensive experiments conducted on three real-world data sets demonstrate the superiority of our framework on learning representations from limited data with crowdsourced labels, comparing with various state-of-the-art baselines.
1 code implementation • Findings of the Association for Computational Linguistics 2020 • Shuai Lin, Wentao Wang, Zichao Yang, Xiaodan Liang, Frank F. Xu, Eric Xing, Zhiting Hu
That is, the model learns to imitate the writing style of any given exemplar sentence, with automatic adaptions to faithfully describe the content record.
no code implementations • 27 Sep 2018 • Wentao Wang, Zhiting Hu, Zichao Yang, Haoran Shi, Eric P. Xing
Neural text generation models such as recurrent networks are typically trained by maximizing data log-likelihood based on cross entropy.
4 code implementations • ACL 2019 • Zhiting Hu, Haoran Shi, Bowen Tan, Wentao Wang, Zichao Yang, Tiancheng Zhao, Junxian He, Lianhui Qin, Di Wang, Xuezhe Ma, Zhengzhong Liu, Xiaodan Liang, Wangrong Zhu, Devendra Singh Sachan, Eric P. Xing
The versatile toolkit also fosters technique sharing across different text generation tasks.