**Please contact me if some PDF files are not avaliable.**
Selected Preprint
PyGlove: Efficiently Exchanging ML Ideas as Code[arXiv][BibTex] Daiyi Peng, Xuanyi Dong, Esteban Real, Yifeng Lu, Quoc V. Le
arXiv, 2023
2024
Gemini: a family of highly capable multimodal models[Google Report] Gemini Team
tech report, 2024
Automated Deep Learning: Neural Architecture Search Is Not the End[arXiv][FnT@ML][BibTex] Xuanyi Dong, David Jacob Kedziora, Katarzyna Musial, Bogdan Gabrys
Foundations and Trends® in Machine Learning, Vol. 17: No. 5, pp 767-920
2023
DoReMi: Optimizing Data Mixtures Speeds Up Language Model Pretraining[arXiv][BibTex] Sang Michael Xie, Hieu Pham, Xuanyi Dong, Nan Du, Hanxiao Liu, Yifeng Lu, Percy Liang, Quoc V. Le, Tengyu Ma, Adams Wei Yu
NeurIPS, 2023
Symbolic Discovery of Optimization Algorithms[arXiv][BibTex] Xiangning Chen, Chen Liang, Da Huang, Esteban Real, Kaiyuan Wang, Yao Liu, Hieu Pham, Xuanyi Dong, Thang Luong, Cho-Jui Hsieh, Yifeng Lu, Quoc V. Le
NeurIPS, 2023
2022
Towards the Co-design of Neural Networks and Accelerators[PDF][arXiv][BibTex] Yanqi Zhou, Xuanyi Dong, Tianjian Meng, Mingxing Tan, Berkin Akin, Daiyi Peng, Amir Yazdanbakhsh, Da Huang, Ravi Narayanaswami, James Laudon
Proceedings of Machine Learning and Systems (MLSys), 2022
TRACE: Triangular, Variable-Specific Attention for Long Sequence Multivariate Time Series Forecasting Razvan Cirstea, Tung Kieu, Chenjuan Guo, Xuanyi Dong, Shirui Pan, Bin Yang
The International Joint Conference on Artificial Intelligence (IJCAI), 2022
2021
Recognizing Vector Graphics without Rasterization[arXiv][BibTex] Xinyang Jiang, Lu Liu, Caihua Shan, Yifei Shen, Xuanyi Dong, Dongsheng Li
The Conference on Neural Information Processing Systems (NeurIPS), 2021
Efficient and Reproducible Automated Deep Learning[PDF] Xuanyi Dong Ph.D. Thesis
NATS-Bench: Benchmarking NAS Algorithms for Architecture Topology and Size[arXiv][IEEE][Full-Code][API/Data][Project][BibTex] Xuanyi Dong, Lu Liu, Katarzyna Musial, Bogdan Gabrys
(Regular) IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI), 2021
Isometric Propagation Network for Generalized Zero-shot Learning[arXiv][ICLR-PDF][BibTex] Lu Liu, Tianyi Zhou, Guodong Long, Jing Jiang, Xuanyi Dong, Chengqi Zhang
International Conference on Learning Representations (ICLR), 2021
Auto-Navigator: Decoupled Neural Architecture Search for Visual Navigation[PDF] Tianqi Tang, Xin Yu, Xuanyi Dong, Yi Yang
Winter Conference on Applications of Computer Vision (WACV), 2021
2020
PyGlove: Symbolic Programming for Automated Machine Learning[PDF][Appendix][arXiv][NeurIPS-Oral-Slides][BibTex][Medium] Daiyi Peng, Xuanyi Dong, Esteban Real, Mingxing Tan, Yifeng Lu, Hanxiao Liu, Gabriel Bender, Adam Kraft, Chen Liang, Quoc V. Le
(Oral) Neural Information Processing Systems (NeurIPS), 2020
NAS-Bench-201: Extending the Scope of Reproducible Neural Architecture Search[PDF][arXiv][Code][Dataset][API][Poster][BibTex] Xuanyi Dong, Yi Yang
(Spotlight) International Conference on Learning Representations (ICLR), 2020
Supervision by Registration and Triangulation for Landmark Detection[arXiv][IEEE][Preview-PDF][Project][Models][Code][BibTex] Xuanyi Dong, Yi Yang, Shih-En Wei, Xinshuo Weng, Yaser Sheikh, Shoou-I Yu
(Regular) IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI), 2020
Self-Paced Multi-View Co-Training[PDF][Code][BibTex] Fan Ma, Deyu Meng, Xuanyi Dong, Yi Yang
Journal of Machine Learning Research (JMLR), 2020
Asymptotic Soft Filter Pruning for Deep Convolutional Neural Networks[PDF][BibTex] Yang He, Xuanyi Dong, Guoliang Kang, Yanwei Fu, Chenggang Yan, Yi Yang
IEEE Transactions on Cybernetics (TCYB), 2020
When Humans Meet Machines: Towards Efficient Segmentation Networks[PDF] Peike Li, Xuanyi Dong, Xin Yu, Yi Yang
The British Machine Vision Conference (BMVC), 2020
One-Shot Neural Architecture Search via Self-Evaluated Template Network[arXiv][Official-ICCV-PDF][Code][BibTex] Xuanyi Dong, Yi Yang
IEEE Conference on International Conference on Computer Vision (ICCV), 2019
Teacher Supervises Students How to Learn from Partially Labeled Images for Facial Landmark Detection[arXiv][Official-ICCV-PDF][Code][BibTex] Xuanyi Dong, Yi Yang
IEEE Conference on International Conference on Computer Vision (ICCV), 2019
Searching for A Robust Neural Architecture in Four GPU Hours[arXiv][Official-CVPR-PDF][Code][BibTex] Xuanyi Dong, Yi Yang
IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2019
Few-Example Object Detection with Model Communication[arXiv][IEEE][Preview-PDF][Code][Dataset][BibTex] Xuanyi Dong, Liang Zheng, Fan Ma, Yi Yang, Deyu Meng
(Regular) IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI), 2019
Late Fusion via Subspace Search with Consistency Preservation[PDF][Code][BibTex] Xuanyi Dong, Yan Yan, Mingkui Tan, Yi Yang, Ivor W. Tsang
IEEE Transactions on Image Processing (TIP), 2019
Auto-ReID: Searching for a Part-Aware ConvNet for Person Re-Identification[arXiv][Official-ICCV-PDF][BibTex] Ruijie Quan, Xuanyi Dong, Yu Wu, Linchao Zhu, Yi Yang
IEEE Conference on International Conference on Computer Vision (ICCV), 2019
Progressive Learning for Person Re-Identification with One Example[PDF][Dataset][BibTex] Yu Wu, Yutian Lin, Xuanyi Dong, Yan Yan, Wei Bian, Yi Yang
IEEE Transactions on Image Processing (TIP), 2019.
A Bottom-Up Clustering Approach to Unsupervised Person Re-Identification[PDF][Code][BibTex] Yutian Lin, Xuanyi Dong, Liang Zheng, Yan Yan, Yi Yang
(Oral) AAAI Conference on Artificial Intelligence (AAAI), 2019
2018
Supervision-by-Registration: An Unsupervised Approach to Improve the Precision of Facial Landmark Detectors[arXiv][Official-CVPR-PDF][FB-Code][Code][Video][Blog][BibTex] Xuanyi Dong, Shoou-I Yu, Xinshuo Weng, Shih-En Wei, Yi Yang, Yaser Sheikh
IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2018
Fast Parameter Adaptation for Few-Shot Image Captioning and Visual Question Answering[PDF][Official-PDF][Code][BibTex] Xuanyi Dong, Linchao Zhu, De Zhang, Yi Yang, Fei Wu
ACM International Conference on Multimedia (ACM-MM), 2018.
Soft Filter Pruning for Accelerating Deep Convolutional Neural Networks[PDF][Code][Models][BibTex] Yang He, Guoliang Kang, Xuanyi Dong, Yanwei Fu, Yi Yang
International Joint Conference on Artificial Intelligence (IJCAI), 2018
Exploit the Unknown Gradually: One-Shot Video-Based Person Re-Identification by Stepwise Learning[PDF][Code][Dataset][BibTex] Yu Wu, Yutian Lin, Xuanyi Dong, Yan Yan, Wanli Ouyang, Yi Yang
IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2018
2017
More is Less: A More Complicated Network with Less Inference Complexity[PDF][Official-PDF][BibTex] Xuanyi Dong, Junshi Huang, Yi Yang, Shuicheng Yan
IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2017
Self-Paced Co-training[PDF][Code][BibTex] Fan Ma, Deyu Meng, Qi Xie, Zina Li, Xuanyi Dong International Conference on Machine Learning (ICML), 2017
A Dual-Network Progressive Approach to Weakly Supervised Object Detection[PDF][Official-PDF][Code][BibTex] Xuanyi Dong, Deyu Meng, Fan Ma, Yi Yang
ACM International Conference on Multimedia (ACM-MM), 2017