About Me

I am a Staff Research Scientist working on image and video generation models in GenAI at Meta.   In the past, I have been woking on efficient neural network design, neural architecture search, and data efficient learning. I received the B.S. degree from Peking University in 2014, and the Ph. D. degree from Princeton University in July 2019.

Education

• 2014 - 2019, PhD,  Princeton University

• 2010 - 2014, Bachelor of Science, Peking University

Work Experience

• 02/2023 - current, Staff Research Scientist, Media Foundation at GenAI, Meta.

  • Pretraining stage leading IC and babysitter in Meta's Movie Gen.

  • Tech lead in Meta's image generation model Emu.

• 09/2019 - 02/2023, Research Scientist, Mobile Computer Vision, Meta.

• 05/2018 - 01/2019, Research Intern, Mobile Computer Vision. Meta.

• 05/2016 - 08/2016, DSP Software Engineer Intern, Tensilica.

Research Interests

• Generative AI

• Efficient deep neural network

• Data efficient learning

Selected Publications                                                                            

• Meta Movie Gen Team, "Movie Gen: A Cast of Media Foundation Models", arXiv:2410.13720 (2024).

• B. Lai, X. Dai, L. Chen, G, Pang, J. M. Rehg, and M. Liu, "Lego: Learning egocentric action frame generation via visual instruction tuning", ECCV 2024, Best paper candidate

• X. Dai, et al. "Emu: Enhancing image generation models using photogenic needles in a haystack." arXiv preprint arXiv:2309.15807 (2023).

• J. Tian, X. Dai, C. Ma, Z. He, Y. Liu, Z. Kira, "Trainable Projected Gradient Method for Robust Fine-tuning", CVPR 2023.

• J. Hou, X. Dai, Z. He, A. Dai, M. Nießner, "Mask3D: Pre-training 2D Vision Transformers by Learning Masked 3D Priors", CVPR 2023.

• H. You, Y. Xiong, X. Dai, B. Wu, P. Zhang, H. Fan, P Vajda, Y. Lin, "Castling-ViT: Compressing Self-Attention via Switching Towards Linear-Angular Attention During Vision Transformer Inference", CVPR 2023.

• F. Liang, B. Wu, X. Dai, K. Li, Y. Zhao, H. Zhang, P. Zhang, P. Vajda, and D. Marculescu, "Open-Vocabulary Semantic Segmentation with Mask-adapted CLIP", CVPR 2023.

• D. Bolya, C.-Y. Fu, X. Dai, P. Zhang, C. Feichtenhofer, J. Hoffman, "Token Merging: Your ViT But Faster", ICLR 2023.

• T. Zhang, D. Cheng, Y. He, Z. Chen, X. Dai, L. Xiong, F. Yan, H. Li, Y. Chen, W. Wen, "NASRec: Weight Sharing Neural Architecture Search for Recommender Systems", WWW 2023.

• Y. Liu, C. Ma, X. Dai, J. Tian, P. Vajda, Z. He, Z. Kira, “Open-Set Semi-Supervised Object Detection”, ECCV, 2022.

• D. Bolya, C.-Y. Fu, X. Dai, P. Zhang, J. Hoffman, "Hydra attention: Efficient attention with many heads", ECCV CADL Workshop (Best Paper Award), 2022.

• Y. Li, X. Dai, C. Ma, Y. Liu, K. Chen, B. Wu, Z. He, K. Kitani, P. Vajda"Cross-Domain Adaptive Teacher for Object Detection", CVPR, 2022.

• X. Dai, A. Wan, P. Zhang, B. Wu, Z. He, Z. Wei, K. Chen, Y. Tian, M. Yu, P. Vajda, and J. Gonzalez, “FBNetV3: Joint Architecture-Recipe Search using Neural Acquisition Function,” CVPR, 2021.

• Z. Yan, X. Dai, P. Zhang, Y. Tian, B. Wu, M. Feiszli, “FP-NAS: Fast Probabilistic Neural Architecture Search”, CVPR, 2021.

• B. Wu, C. Xu, X. Dai, A. Wan, P. Zhang, Z. Yan, M. Tomizuka, K. Keutzer, P. Vajda, “Visual Transformers: Where Do Transformers Really Belong in Vision Models?” ICCV, 2021.

• A. Wan, X. Dai, P. Zhang, Z. He, Y. Tian, S. Xie, B. Wu, M. Yu, T. Xu, K. Chen, P. Vajda, and J. Gonzatez, “FBNetV2: Differentiable Neural Architecture Search for Spatial and Channel Dimensions,” CVPR, 2020.

• X. Dai, P. Zhang, B. Wu, H. Yin, F. Sun, Y. Wang, M. Dukhan, Y. Hu, Y. Wu, Y. Jia, P. Vajda, M. Uyttendaele, and N. K. Jha, “ChamNet: Towards Efficient Network Design through Platform-Aware Model Adaptation,” CVPR, 2019.

• B. Wu, X. Dai, P. Zhang, Y. Wang, Y., F. Sun, Y. Wu, Y. Tian, P. Vajda, Y. Jia, and K. Keutzer, “FBNet: Hardware-Aware Efficient ConvNet Design via Differentiable Neural Architecture Search,” CVPR, 2019.

• X. Dai, H. Yin, and N. K. Jha, “NeST: A Neural Network Synthesis Tool Based on a Grow-and-prune Paradigm,” IEEE Trans. on Computers, 2019.

• X. Dai, H. Yin, and N. K. Jha, “Grow and Prune Compact, Fast, and Accurate LSTMs,” IEEE Trans. on Computers, 2019.         

• X. Dai, H. Yin, and N. K. Jha, “Incremental Learning Using a Grow-and-Prune Paradigm with Efficient Neural Networks,” IEEE Trans. on Emerging Topics in Computing, 2021.

• A. Mosenia, X. Dai, P. Mittal and N. K. Jha, “PinMe: Tracking a Smartphone User around the World,” IEEE Trans. on Multi-scale Computing Syst., Aug. 2017.

Academic Service

Reviewer / Program committee

• IEEE Conf. on Computer Vision and Pattern Recognition (CVPR)

• Neural Information Processing Systems  (NeurIPS)

• IEEE International Conf. on Computer Vision (ICCV)

• European Conference on Computer Vision (ECCV)

• International Conference on Learning Representations (ICLR)

• IEEE Winter Conf. on Applications of Computer Vision (WACV)

• IEEE Trans. on Pattern Analysis and Machine Intelligence

• IEEE Trans. on Neural Networks and Learning Systems

• IEEE Trans. on Computers

• IEEE Trans. on Image Processing

• IEEE Trans. on Emerging Topics in Computing

• IEEE Trans. on Multi-scale Computing Systems

• IEEE Signal Processing Letters

• J. Visual Communication and Image Representation

• J. Selected Topics in Signal Processing

• Efficient Deep Learning in Computer Vision  (EDLCV) Workshop

• Medical Image Computing and Computer Assisted Interventions (MICCAI)