publications

publications by categories in reversed chronological order. generated by jekyll-scholar.

2022

    2021

    1. Vinvl: Revisiting visual representations in vision-language models
      Zhang, Pengchuan, Li, Xiujun, Hu, Xiaowei, Yang, Jianwei, Zhang, Lei, Wang, Lijuan, Choi, Yejin, and Gao, Jianfeng
      In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition 2021
    2. Out-of-distribution prediction with invariant risk minimization: The limitation and an effective fix
      Guo, Ruocheng,  Zhang, Pengchuan, Liu, Hao, and Kiciman, Emre
      arXiv preprint arXiv:2101.07732 2021
    3. Multi-scale vision longformer: A new vision transformer for high-resolution image encoding
      Zhang, Pengchuan, Dai, Xiyang, Yang, Jianwei, Xiao, Bin, Yuan, Lu, Zhang, Lei, and Gao, Jianfeng
      arXiv preprint arXiv:2103.15358 2021
    4. Multiscale Invertible Generative Networks for High-Dimensional Bayesian Inference
      Zhang, Shumao,  Zhang, Pengchuan, and Hou, Thomas Y
      arXiv preprint arXiv:2105.05489 2021
    5. 3DB: A Framework for Debugging Computer Vision Models
      Leclerc, Guillaume, Salman, Hadi, Ilyas, Andrew, Vemprala, Sai, Engstrom, Logan, Vineet, Vibhav, Xiao, Kai,  Zhang, Pengchuan, Santurkar, Shibani, Yang, Greg, and others,
      arXiv preprint arXiv:2106.03805 2021
    6. Efficient Self-supervised Vision Transformers for Representation Learning
      Li, Chunyuan, Yang, Jianwei,  Zhang, Pengchuan, Gao, Mei, Xiao, Bin, Dai, Xiyang, Yuan, Lu, and Gao, Jianfeng
      arXiv preprint arXiv:2106.09785 2021
    7. Image scene graph generation (sgg) benchmark
      Han, Xiaotian, Yang, Jianwei, Hu, Houdong, Zhang, Lei, Gao, Jianfeng, and Zhang, Pengchuan
      arXiv preprint arXiv:2107.12604 2021
    8. Dynamic detr: End-to-end object detection with dynamic attention
      Dai, Xiyang, Chen, Yinpeng, Yang, Jianwei,  Zhang, Pengchuan, Yuan, Lu, and Zhang, Lei
      In Proceedings of the IEEE/CVF International Conference on Computer Vision 2021
    9. Focal Attention for Long-Range Interactions in Vision Transformers
      Yang, Jianwei, Li, Chunyuan,  Zhang, Pengchuan, Dai, Xiyang, Xiao, Bin, Yuan, Lu, and Gao, Jianfeng
      Advances in Neural Information Processing Systems 2021
    10. Florence: A New Foundation Model for Computer Vision
      Yuan, Lu, Chen, Dongdong, Chen, Yi-Ling, Codella, Noel, Dai, Xiyang, Gao, Jianfeng, Hu, Houdong, Huang, Xuedong, Li, Boxin, Li, Chunyuan, and others,
      arXiv preprint arXiv:2111.11432 2021
    11. Grounded Language-Image Pre-training
      Li, Liunian Harold,  Zhang, Pengchuan, Zhang, Haotian, Yang, Jianwei, Li, Chunyuan, Zhong, Yiwu, Wang, Lijuan, Yuan, Lu, Zhang, Lei, Hwang, Jenq-Neng, and others,
      arXiv preprint arXiv:2112.03857 2021
    12. RegionCLIP: Region-based Language-Image Pretraining
      Zhong, Yiwu, Yang, Jianwei,  Zhang, Pengchuan, Li, Chunyuan, Codella, Noel, Li, Liunian Harold, Zhou, Luowei, Dai, Xiyang, Yuan, Lu, Li, Yin, and others,
      arXiv preprint arXiv:2112.09106 2021

    2020

    1. Statistical adaptive stochastic gradient methods
      Zhang, Pengchuan, Lang, Hunter, Liu, Qiang, and Xiao, Lin
      arXiv preprint arXiv:2002.10597 2020
    2. Oscar: Object-semantics aligned pre-training for vision-language tasks
      Li, Xiujun, Yin, Xi, Li, Chunyuan,  Zhang, Pengchuan, Hu, Xiaowei, Zhang, Lei, Wang, Lijuan, Hu, Houdong, Dong, Li, Wei, Furu, and others,
      In European Conference on Computer Vision 2020
    3. Object-centric image generation from layouts
      Sylvain, Tristan,  Zhang, Pengchuan, Bengio, Yoshua, Hjelm, R Devon, and Sharma, Shikhar
      arXiv preprint arXiv:2003.07449 2020
    4. Novel human-object interaction detection via adversarial domain generalization
      Song, Yuhang, Li, Wenbo, Zhang, Lei, Yang, Jianwei, Kiciman, Emre, Palangi, Hamid, Gao, Jianfeng, Kuo, C-C Jay, and Zhang, Pengchuan
      arXiv preprint arXiv:2005.11406 2020
    5. Maggan: High-resolution face attribute editing with mask-guided generative adversarial network
      Wei, Yi, Gan, Zhe, Li, Wenbo, Lyu, Siwei, Chang, Ming-Ching, Zhang, Lei, Gao, Jianfeng, and Zhang, Pengchuan
      In Proceedings of the Asian Conference on Computer Vision 2020
    6. Minivlm: A smaller and faster vision-language model
      Wang, Jianfeng, Hu, Xiaowei,  Zhang, Pengchuan, Li, Xiujun, Wang, Lijuan, Zhang, Lei, Gao, Jianfeng, and Liu, Zicheng
      arXiv preprint arXiv:2012.06946 2020

    2019

    1. Using statistics to automate stochastic optimization
      Lang, Hunter, Xiao, Lin, and Zhang, Pengchuan
      Advances in Neural Information Processing Systems 2019
    2. Solving Bayesian inverse problems from the perspective of deep generative networks
      Hou, Thomas Y, Lam, Ka Chun,  Zhang, Pengchuan, and Zhang, Shumao
      Computational Mechanics 2019
    3. Recurjac: An efficient recursive algorithm for bounding jacobian matrix of neural networks and its applications
      Zhang, Huan,  Zhang, Pengchuan, and Hsieh, Cho-Jui
      In Proceedings of the AAAI Conference on Artificial Intelligence 2019
    4. TIGEr: text-to-image grounding for image caption evaluation
      Jiang, Ming, Huang, Qiuyuan, Zhang, Lei, Wang, Xin,  Zhang, Pengchuan, Gan, Zhe, Diesner, Jana, and Gao, Jianfeng
      arXiv preprint arXiv:1909.02050 2019
    5. A convex relaxation barrier to tight robustness verification of neural networks
      Salman, Hadi, Yang, Greg, Zhang, Huan, Hsieh, Cho-Jui, and Zhang, Pengchuan
      arXiv preprint arXiv:1902.08722 2019
    6. Statistical Adaptive Stochastic Optimization
      Zhang, Pengchuan, Lang, Hunter, Liu, Qiang, and Xiao, Lin
      2019
    7. Object-driven text-to-image synthesis via adversarial training
      Li, Wenbo,  Zhang, Pengchuan, Zhang, Lei, Huang, Qiuyuan, He, Xiaodong, Lyu, Siwei, and Gao, Jianfeng
      In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition 2019
    8. Provably robust deep learning via adversarially trained smoothed classifiers
      Salman, Hadi, Yang, Greg, Li, Jerry,  Zhang, Pengchuan, Zhang, Huan, Razenshteyn, Ilya, and Bubeck, Sebastien
      arXiv preprint arXiv:1906.04584 2019
    9. Understanding the role of momentum in stochastic gradient methods
      Gitman, Igor, Lang, Hunter,  Zhang, Pengchuan, and Xiao, Lin
      arXiv preprint arXiv:1910.13962 2019
    10. A convex relaxation barrier to tight robust verification of neural networks
      Salman, Hadi, Yang, Greg, Zhang, Huan, Hsieh, Cho-Jui, and Zhang, Pengchuan
      arXiv preprint arXiv:1902.08722 2019

    2018

    1. Turbo learning for captionbot and drawingbot
      Huang, Qiuyuan,  Zhang, Pengchuan, Wu, Dapeng, and Zhang, Lei
      arXiv preprint arXiv:1805.08170 2018
    2. An adaptive fast solver for a general class of positive definite matrices via energy decomposition
      Hou, Thomas Y, Huang, De, Lam, Ka Chun, and Zhang, Pengchuan
      Multiscale Modeling & Simulation 2018
    3. Attngan: Fine-grained text to image generation with attentional generative adversarial networks
      Xu, Tao,  Zhang, Pengchuan, Huang, Qiuyuan, Zhang, Han, Gan, Zhe, Huang, Xiaolei, and He, Xiaodong
      In Proceedings of the IEEE conference on computer vision and pattern recognition 2018
    4. A bird’s eye view on coherence, and a worm’s eye view on cohesion
      Cho, Woon Sang,  Zhang, Pengchuan, Zhang, Yizhe, Li, Xiujun, Wang, Mengdi, and Gao, Jianfeng
      2018
    5. Towards coherent and cohesive long-form text generation
      Cho, Woon Sang,  Zhang, Pengchuan, Zhang, Yizhe, Li, Xiujun, Galley, Michel, Brockett, Chris, Wang, Mengdi, and Gao, Jianfeng
      arXiv preprint arXiv:1811.00511 2018
    6. On the Discrimination-Generalization Tradeoff in GANs
      Zhou, Denny,  Zhang, Pengchuan, Liu, Qiang, Xu, Tao, and He, Xiaodong
      2018

    2017

    1. Exploring the locally low dimensional structure in solving random elliptic PDEs
      Hou, Thomas Y, Li, Qin, and Zhang, Pengchuan
      Multiscale Modeling & Simulation 2017
    2. On the discrimination-generalization tradeoff in GANs
      Zhang, Pengchuan, Liu, Qiang, Zhou, Dengyong, Xu, Tao, and He, Xiaodong
      arXiv preprint arXiv:1711.02771 2017
    3. Compressing Positive Semidefinite Operators with Sparse/Localized Bases
      Zhang, Pengchuan
      arXiv preprint arXiv:1711.02771 2017
    4. A sparse decomposition of low rank symmetric positive semidefinite matrices
      Hou, Thomas Y, Li, Qin, and Zhang, Pengchuan
      Multiscale Modeling & Simulation 2017
    5. Sparse operator compression of higher-order elliptic operators with rough coefficients
      Hou, Thomas Y, and Zhang, Pengchuan
      Research in the Mathematical Sciences 2017

    2016

    1. Concise summarization of heterogeneous treatment effect using total variation regularized regression
      Deng, Alex,  Zhang, Pengchuan, Chen, Shouyuan, Kim, Dong Woo, and Lu, Jiannan
      arXiv preprint arXiv:1610.03917 2016