Chenyan Xiong

Chenyan Xiong is an Associate Professor at the Language Technologies Institute (LTI) at Carnegie Mellon University (CMU). Previously, she spent five years (2018-2023) at Microsoft Research, focusing on conversational search, dense retrieval, healthcare AI, and large-scale pretraining. She earned her Ph.D. at LTI, CMU in 2018 under Jamie Callan, after completing her undergraduate degree at Wuhan University (2009) and a master's at the Institute of Software, Chinese Academy of Science (2012), with internships at Microsoft Research Asia.

Her research groups actively contribute to information retrieval, machine learning, and natural language processing communities, with a current focus on foundation and large language models (LLMs). She explores data-centric approaches to improve model efficiency, embedding learning for multimodal representation, and new application scenarios enabled by Generative AI, particularly in healthcare and next-gen information retrieval. Her work includes developing methods for loss-less compression and functional operations in embedding spaces.

• Current Research Interests:
  • Foundation and Large Language Models
  • Data-Centric AI
  • Embedding Learning
  • Generative AI Applications
  • Healthcare LLMs
  • Multi-Modality Systems
• Recruitment Plans:
  • Ph.D. students at CMU (2024 Fall and 2025 Fall) for pretraining and application of foundation models
  • Specialized Ph.D. student for healthcare LLMs (2024 Fall)