6 papers
EndoExtract: Co-Designing Structured Text Extraction from Endometriosis Ultrasound Reports
Haiyi Li, Yiyang Zhao, Yutong Li +5
Endometriosis ultrasound reports are often unstructured free-text documents that require manual abstraction for downstream tasks such as analytics, machine learning model training,…
Online-PVLM: Advancing Personalized VLMs with Online Concept Learning
Huiyu Bai, Runze Wang, Zhuoyun Du +6
Personalized Visual Language Models (VLMs) are gaining increasing attention for their formidable ability in user-specific concepts aligned interactions (e.g., identifying a user's…
GEM: Generative Entropy-Guided Preference Modeling for Few-shot Alignment of LLMs
Yiyang Zhao, Huiyu Bai, Xuejiao Zhao
Alignment of large language models (LLMs) with human preferences typically relies on supervised reward models or external judges that demand abundant annotations. However, in field…
Automatic Large Language Models Creation of Interactive Learning Lessons
Jionghao Lin, Jiarui Rao, Yiyang Zhao +6
We explore the automatic generation of interactive, scenario-based lessons designed to train novice human tutors who teach middle school mathematics online. Employing prompt engine…
GFRIEND: Generative Few-shot Reward Inference through EfficieNt DPO
Yiyang Zhao, Huiyu Bai, Xuejiao Zhao
The ability to train high-performing reward models with few-shot data is critical for enhancing the efficiency and scalability of Reinforcement Learning from Human Feedback (RLHF).…
Negative Metric Learning for Graphs
Yiyang Zhao, Chengpei Wu, Lilin Zhang +1
Graph contrastive learning (GCL) often suffers from false negatives, which degrades the performance on downstream tasks. The existing methods addressing the false negative issue us…