Yawen Ouyang
Researcher, Shanghai AI Lab
ouyangyawen [AT] air.tsinghua.edu.cn
yawenouyang1996 [AT] gmail.com
WeChat: 17366080217
Bio
I am currently a researcher at Shanghai AI Lab, focusing on LLMs for science. Previously, I was a postdoctoral researcher at Tsinghua University, working with Prof. Weiying Ma and Prof. Hao Zhou, supported by the NSFC. Before that, I completed my Ph.D. at Nanjing University under the supervision of Prof. Xinyu Dai. During my Ph.D., I also interned at ByteDance AI Lab. Here is my CV.
Selected Works
PFArena: Benchmarking Language Models for Protein Modification
Tech report, Sep. 2026.
AMix-2: Establishing Protein as a Native Modality in Large Language Models
Tech report, May 2026.
Enhancing Spatial Reasoning in Large Language Models for Metal-Organic Frameworks Structure Prediction
KDD 2026.
MoMa: A Modular Deep Learning Framework for Material Property Prediction
ICLR 2026.
MOF-BFN: Metal-Organic Frameworks Structure Prediction via Bayesian Flow Networks
NeurIPS 2025.
A Periodic Bayesian Flow for Material Generation
ICLR 2025 (Spotlight).
Towards Extrapolation in Deep Material Property Regression
AI4MAT-ICLR 2025 (Spotlight).
Generative AI-Powered Inverse Design for Tailored Narrowband Molecular Emitters
Digital Discovery.
Debias NLU Datasets via Training-free Perturbations
EMNLP'23 Findings.
On Prefix-tuning for Lightweight Out-of-distribution Detection
ACL'23.
Towards Multi-label Unknown Intent Detection
COLING'22.
Energy-based Unknown Intent Detection with Data Manipulation
ACL'21 Findings.
Dialogue State Tracking with Explicit Slot Connection Modeling
ACL'20.