CV

Education

B.S. at Department of Computer Science and Engineering, SJTU, 2015 - 2019
M.S. at Department of Electronic Engineering, SJTU, 2019 - 2022
PhD at Mila - Quebec AI Institute, 2022 - 2026 (expected)

Work experience

Sep 2017 - Dec 2021: Research Assistant
- Shanghai Jiao Tong University
- Duties included: Developing Transfer Learning algorithms for Computer Vision
- Supervisor: Prof. Bingbing Ni
Mar 2020 - Dec 2021: Research Assistant
- Mila - Quebec AI Institute
- Duties included: Developing Graph Representation Learning algorithms
- Supervisor: Prof. Jian Tang and Hongyu Guo
Oct 2020 - Jun 2021: Research Intern
- ByteDance Inc.
- Duties included: Developing Self-supervised Visual Representation Learning algorithms
- Supervisor: Zhenbang Sun
Jul 2022 - Oct 2021: Part-time Research Intern
- Meta AI
- Duties included: Developing multi-relational data modeling algorithms
- Supervisor: Yuandong Tian and Xinlei Chen

Publications

Learning Context Graph for Person Search

Yan, Y., Zhang, Q., Ni, B., Zhang, W., Xu, M., & Yang, X. (2019). Learning context graph for person search. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (pp. 2158-2167).

Variational Few-Shot Learning

Zhang, J., Zhao, C., Ni, B., Xu, M., & Yang, X. (2019). Variational few-shot learning. In Proceedings of the IEEE International Conference on Computer Vision (pp. 1685-1694).

Fine-grained Video Captioning via Graph-based Multi-granularity Interaction Learning

Yan, Y., Zhuang, N., Zhang, J., Xu, M., Zhang, Q., ZHENG, Z., ... & Zhang, W. (2019). Fine-grained video captioning via graph-based multi-granularity interaction learning. IEEE Transactions on Pattern Analysis and Machine Intelligence.

Adversarial Domain Adaptation with Domain Mixup

Xu, M., Zhang, J., Ni, B., Li, T., Wang, C., Tian, Q., & Zhang, W. (2019). Adversarial domain adaptation with domain mixup. arXiv preprint arXiv:1912.01805.

Cross-domain Detection via Graph-induced Prototype Alignment

Xu, M., Wang, H., Ni, B., Tian, Q., & Zhang, W. (2020). Cross-domain Detection via Graph-induced Prototype Alignment. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (pp. 12355-12364).

Learning to Combine: Knowledge Aggregation for Multi-Source Domain Adaptation

Wang, H., Xu, M., Ni, B., & Zhang, W. (2020). Learning to Combine: Knowledge Aggregation for Multi-Source Domain Adaptation. In Proceedings of the European Conference on Computer Vision (pp. 727-744).

Self-supervised Graph-level Representation Learning with Local and Global Structure

Xu, M., Wang, H., Ni, B., Guo, H., & Tang, J. (2021). Self-supervised Graph-level Representation Learning with Local and Global Structure. arXiv preprint arXiv:2106.04113.

Cross-category Video Highlight Detection via Set-based Learning

Xu, M., Wang, H., Ni, B., Zhu, R., Sun, Z., & Wang, C. (2021). Cross-category Video Highlight Detection via Set-based Learning. arXiv preprint arXiv:2108.11770.

PIT: Position-Invariant Transform for Cross-FoV Domain Adaptation

Gu, Q., Zhou, Q., Xu, M., Feng, Z., Cheng, G., Lu, X., Shi, J., & Ma, L. (2021). PIT: Position-Invariant Transform for Cross-FoV Domain Adaptation. arXiv preprint arXiv:2108.07142.

Joint Modeling of Visual Objects and Relations for Scene Graph Generation

Xu, M., Qu, M., Ni, B., & Tang, J. (2021). Joint Modeling of Visual Objects and Relations for Scene Graph Generation. In Advances in Neural Information Processing Systems.

Graphical Modeling for Multi-Source Domain Adaptation

Xu, M., Wang, H., & Ni, B. (2022). Graphical Modeling for Multi-Source Domain Adaptation. IEEE Transactions on Pattern Analysis and Machine Intelligence.

HIRL: A General Framework for Hierarchical Image Representation Learning

Xu, M., Guo, Y., Zhu, X., Li, J., Sun, Z., Tang, J., Xu, Y., & Ni, B. (2022). HIRL: A General Framework for Hierarchical Image Representation Learning. arXiv preprint arXiv:2205.13159.

HCSC: Hierarchical Contrastive Selective Coding

Guo, Y., Xu, M., Li, J., Ni, B., Zhu, X., Sun, Z., & Xu, Y. (2022). HCSC: Hierarchical Contrastive Selective Coding. arXiv preprint arXiv:2202.00455.

PEER: A Comprehensive and Multi-Task Benchmark for Protein Sequence Understanding

Xu, M., Zhang, Z., Lu, J., Zhu, Z., Zhang, Y., Ma., C, Liu, R., & Tang, J. (2022). PEER: A Comprehensive and Multi-Task Benchmark for Protein Sequence Understanding. In Advances in Neural Information Processing Systems.

EurNet: Efficient Multi-Range Relational Modeling of Protein Structure

Xu, M., Guo, Y., Xu, Y., Tang, J., Chen., X., & Tian, Y. (2023). EurNet: Efficient Multi-Range Relational Modeling of Protein Structure. In ICLR MLDD Workshop.

Protein Representation Learning by Geometric Structure Pretraining

Zhang, Z., Xu, M., Arian, J., Vijil, C., Aurelie, L., Payel, D., & Tang, J. (2023). Protein Representation Learning by Geometric Structure Pretraining. In International Conference on Learning Representations.

ProtST: Multi-Modality Learning of Protein Sequences and Biomedical Texts

Xu, M., Yuan, X., Santiago, M., & Tang, J. (2023). ProtST: Multi-Modality Learning of Protein Sequences and Biomedical Texts. In International Conference on Machine Learning.

Pre-Training Protein Encoder via Siamese Sequence-Structure Diffusion Trajectory Prediction

Zhang, Z., Xu, M., Aurelie, L., Vijil, C., Payel, D., & Tang, J. (2023). Pre-Training Protein Encoder via Siamese Sequence-Structure Diffusion Trajectory Prediction. In Advances in Neural Information Processing Systems.

ProtLLM: An Interleaved Protein-Language LLM with Protein-as-Word Pre-Training

Zhuo, L., Chi, Z., Xu, M., Huang, H., Zhao, J., Zheng, H., He, C., Mao, X., & Zhang, W. (2024). ProtLLM: An Interleaved Protein-Language LLM with Protein-as-Word Pre-Training. In Annual Meeting of the Association for Computational Linguistics.

Academic Services

Reviewer of NeurIPS 2020, 2021, 2022; ICML 2022; ICLR 2022, 2023; CVPR 2020, 2021, 2022; ICCV 2021

Minghao (Alan) Xu

CV