Welcome to Chenyan Xiong’s research group’s website. We are based in the Language Technologies Institute at Carnegie Mellon University’s School of Computer Science. Our work broadly spans areas in information retrieval, natural language processing, and machine learning. A few of our current research topics include (but are not limited to):

• Foundational models: data curation for pretraining, efficient language models, and interpretability.
• Retrieval: dense retrieval, representations for universal information retrieval.
• Applications: LLMs for healthcare, retrieval grounded in special domains (e.g., multimodal, long document).

Update April 2024: Our website is up! Please check back in the following weeks for updates.

Photo: taken April 2024 in front of the Fence @ CMU