Yawen Ouyang
Postdoctoral Researcher, Tsinghua University
ouyangyawen [AT] air.tsinghua.edu.cn
yawenouyang1996 [AT] gmail.com
Bio
I am currently a postdoctoral researcher at Tsinghua University, working with Prof. Weiying Ma and Prof. Hao Zhou, funded by NSFC. My research lies at the intersection of artificial intelligence and materials science, with the goal of accelerating the discovery of novel materials for clean energy and climate change mitigation. My recent work has focused on materials generation [NeurIPS'25, ICLR'25, Digital Discovery], materials property prediction [AI4MAT-ICLR'25, AI4MAT-ICLR'25].
Prior to this, I completed my Ph.D. at Nanjing University under the supervision of Prof. Xinyu Dai, where I worked on open-environment natural language processing, with a particular focus on out-of-distribution detection [ACL'23, COLING'22, ACL'21] and natural language understanding [EMNLP'23, EMNLP'23, ACL'20]. During my Ph.D., I also interned at the Bytedance AI Lab, working with Prof. Hongning Wang.
Publications
MOF-BFN: Metal-Organic Frameworks Structure Prediction via Bayesian Flow Networks
Rui Jiao, Hanlin Wu, Wenbing Huang, Yuxuan Song, Yawen Ouyang, Yu Rong, Tingyang Xu, Pengju Wang, Hao Zhou, Wei-Ying Ma, Jingjing Liu, Yang Liu
NeurIPS 2025.
A Periodic Bayesian Flow for Material Generation
Hanlin Wu, Yuxuan Song, Jingjing Gong, Ziyao Cao, Yawen Ouyang, Jianbing Zhang, Hao Zhou, Wei-Ying Ma, Jingjing Liu
ICLR 2025 (Spotlight).
MoMa: A Modular Deep Learning Framework for Material Property Prediction
Botian Wang, Yawen Ouyang, Yaohui Li, Yiqun Wang, Haorui Cui, Jianbing Zhang, Xiaonan Wang, Wei-Ying Ma, Hao Zhou
AI4MAT-ICLR 2025 (Spotlight).
Towards Extrapolation in Deep Material Property Regression
Pan Mianzhi, JianFei Li, Yawen Ouyang, Wei-Ying Ma, Jianbing Zhang, Hao Zhou
AI4MAT-ICLR 2025 (Spotlight).
Generative AI-Powered Inverse Design for Tailored Narrowband Molecular Emitters
Mianzhi Pan, Tianhao Tan, Yawen Ouyang, Qian Jin, Yougang Chu, Wei-Ying Ma, Jianbing Zhang, Lian Duan, Dong Wang, Hao Zhou
Digital Discovery.
M2DF: Multi-grained Multi-curriculum Denoising Framework for Multimodal Aspect-based Sentiment Analysis
Fei Zhao, Chunhui Li, Zhen Wu, Yawen Ouyang, Jianbing Zhang, Xinyu Dai
EMNLP'23.
Debias NLU Datasets via Training-free Perturbations
Qi Guo, Yuanhang Tang, Yawen Ouyang, Zhen Wu, Xinyu Dai
EMNLP'23 Findings.
On Prefix-tuning for Lightweight Out-of-distribution Detection
Yawen Ouyang, Yongchang Cao, Yuan Gao, Zhen Wu, Jianbing Zhang, Xinyu Dai
ACL'23.
Towards Multi-label Unknown Intent Detection
Yawen Ouyang, Zhen Wu, Xinyu Dai, Shujian Huang, Jiajun Chen
COLING'22.
Energy-based Unknown Intent Detection with Data Manipulation
Yawen Ouyang, Jiasheng Ye, Yu Chen, Xinyu Dai, Shujian Huang, Jiajun Chen
ACL'21 Findings.
Dialogue State Tracking with Explicit Slot Connection Modeling
Yawen Ouyang, Moxin Chen, Xinyu Dai, Yinggong Zhao, Shujian Huang, Jiajun Chen
ACL'20.