A selection of peer-reviewed publications. For a more complete list see my Google Scholar profile.
2022
ReFormer: The Relational Transformer for Image Captioning
Xuewen Yang, Yingru Liu, Xin Wang
Proceedings of the 30th ACM International Conference on Multimedia (ACM MM), 2022.
[semantic scholar]
2021
Journalistic Guidelines Aware News Image Captioning
Xuewen Yang, Svebor Karaman, Joel Tetreault, Alejandro Jaimes
Proceedings of EMNLP, 2021.
[arXiv] · [code]
2020
Fashion Captioning: Towards Generating Accurate Descriptions with Semantic Rewards
Xuewen Yang, Heming Zhang, Di Jin, Yingru Liu, Chi-Hao Wu, Jianchao Tan, Dongliang Xie, Jue Wang, Xin Wang
European Conference on Computer Vision (ECCV), 2020.
Introduces the FACAD dataset for fashion image captioning.
[springer] · [code + data]
Adaptive Activation Network and Functional Regularization for Efficient and Flexible Deep Multi-Task Learning
Yingru Liu, Xuewen Yang, Dongliang Xie, Xin Wang, Li Shen, Haozhi Huang, Niranjan Balasubramanian
AAAI Conference on Artificial Intelligence (AAAI), 2020.
[AAAI]
Paper Reviewing
Conducted 200+ reviews for NeurIPS, ACL, EMNLP, CVPR, ECCV, ICCV, AAAI, IJCAI, TPAMI, Knowledge-Based Systems, and IEEE Transactions on Affective Computing.
Open Source
Active contributor to Axolotl and ms-swift — submissions around scalable post-training, instruction tuning, and RL training pipelines.