ProtLLM: An Interleaved Protein-Language LLM with Protein-as-Word Pre-Training
Published in ACL, 2024
Authors: Le Zhuo*, Zewen Chi*, Minghao Xu*, Heyan Huang, Jianan Zhao, Heqi Zheng, Conghui He, Xian-Ling Mao, Wentao Zhang (* equal contribution)
Publications
Pre-Training Protein Encoder via Siamese Sequence-Structure Diffusion Trajectory Prediction
Published in NeurIPS, 2023 (Spotlight)
Authors: Zuobai Zhang*, Minghao Xu*, Aurelie Lozano, Vijil Chenthamarakshan, Payel Das, Jian Tang (* equal contribution)
ProtST: Multi-Modality Learning of Protein Sequences and Biomedical Texts
Published in ICML, 2023 (Oral)
Authors: Minghao Xu, Xinyu Yuan, Santiago Miret, Jian Tang
Protein Representation Learning by Geometric Structure Pretraining
Published in ICLR, 2023
Authors: Zuobai Zhang, Minghao Xu, Arian Jamasb, Vijil Chenthamarakshan, Aurelie Lozano, Payel Das, Jian Tang
EurNet: Efficient Multi-Range Relational Modeling of Protein Structure
Published in ICLR MLDD Workshop, 2023
Authors: Minghao Xu, Yuanfan Guo, Yi Xu, Jian Tang, Xinlei Chen, Yuandong Tian
PEER: A Comprehensive and Multi-Task Benchmark for Protein Sequence Understanding
Published in NeurIPS, 2022
Authors: Minghao Xu*, Zuobai Zhang*, Jiarui Lu, Zhaocheng Zhu, Yangtian Zhang, Chang Ma, Runcheng Liu, Jian Tang (* equal contribution)
HCSC: Hierarchical Contrastive Selective Coding
Published in CVPR, 2022
Authors: Yuanfan Guo*, Minghao Xu*, Jiawen Li, Bingbing Ni, Xuanyu Zhu, Zhenbang Sun, Yi Xu (* equal contribution)
HIRL: A General Framework for Hierarchical Image Representation Learning
Published in arXiv, 2022
Authors: Minghao Xu*, Yuanfan Guo*, Xuanyu Zhu, Jiawen Li, Zhenbang Sun, Jian Tang, Yi Xu, Bingbing Ni (* equal contribution)
Graphical Modeling for Multi-Source Domain Adaptation
Published in TPAMI, 2022
Authors: Minghao Xu, Hang Wang, Bingbing Ni
In this work, we propose a Conditional Random Field (CRF) method and another Markov Random Field (MRF) method to solve the Multi-Source Domain Adaptation problem.
Joint Modeling of Visual Objects and Relations for Scene Graph Generation
Published in NeurIPS, 2021
Authors: Minghao Xu, Meng Qu, Bingbing Ni, Jian Tang
PIT: Position-Invariant Transform for Cross-FoV Domain Adaptation
Published in ICCV, 2021
Authors: Qiqi Gu, Qianyu Zhou, Minghao Xu, Zhengyang Feng, Guangliang Cheng, Xuequan Lu, Jianping Shi, Lizhuang Ma
Cross-category Video Highlight Detection via Set-based Learning
Published in ICCV, 2021
Authors: Minghao Xu, Hang Wang, Bingbing Ni, Riheng Zhu, Zhenbang Sun, Changhu Wang
Self-supervised Graph-level Representation Learning with Local and Global Structure
Published in ICML, 2021
Authors: Minghao Xu, Hang Wang, Bingbing Ni, Hongyu Guo, Jian Tang
Learning to Combine: Knowledge Aggregation for Multi-Source Domain Adaptation
Published in ECCV, 2020
Authors: Hang Wang*, Minghao Xu*, Bingbing Ni, Wenjun Zhang (* equal contribution)
In this work, we propose a Learning to Combine framework, in which the knowledges acquired from multiple source domains are aggregated and applied to the target domain.
Cross-domain Detection via Graph-induced Prototype Alignment
Published in CVPR, 2020 (Oral)
Authors: Minghao Xu, Hang Wang, Bingbing Ni, Qi Tian, Wenjun Zhang
In this work, we propose a Graph-induced Prototype Alignment (GPA) framework to align source and target domain for cross-domain detection tasks.
Adversarial Domain Adaptation with Domain Mixup
Published in AAAI, 2020 (Oral)
Authors: Minghao Xu, Jian Zhang, Bingbing Ni, Teng Li, Chengjie Wang, Qi Tian, Wenjun Zhang
In this work, we propose to promote adversarial domain adaptation with both pixel-level and feature-level domain mixup.
Fine-grained Video Captioning via Graph-based Multi-granularity Interaction Learning
Published in TPAMI, 2019
Authors: Yichao Yan, Ning Zhuang, Bingbing Ni, Jian Zhang, Minghao Xu, Qiang Zhang, Zhang Zheng, Shuo Cheng, Qi Tian, Xiaokang Yang, Wenjun Zhang
In this work, we collect a new video dataset from YouTube.com, called Sports Video Narrative (SVN), for fine-grained sports auto-narrative. Also, we propose a novel framework to encode both intra- and inter- team interactions.
Variational Few-Shot Learning
Published in ICCV, 2019
Authors: Jian Zhang, Chenglong Zhao, Bingbing Ni, Minghao Xu, Xiaokang Yang
In this work, we propose a variational Bayesian framework to approximate bias-eliminated class specific sample distributions for few-shot learning.
Learning Context Graph for Person Search
Published in CVPR, 2019 (Oral)
Authors: Yichao Yan, Qiang Zhang, Bingbing Ni, Wendong Zhang, Minghao Xu, Xiaokang Yang
In this work, we build a graph learning framework to employ context information for person search.