Published 'KdConv: A Chinese Multi-domain Dialogue Dataset Towards Multi-turn Knowledge-driven Conversation' at ACL 2020, 'CrossWOZ: A Large-Scale Chinese Cross-Domain Task-Oriented Dialogue Dataset' at TACL 2020. Latest research 'ColBERT-serve: Efficient Multi-Stage Memory-Mapped Scoring' accepted and presented at ECIR 2025.
Research Experience
Working as an Applied Scientist at Microsoft, focusing on natural language processing and multi-modality modeling. Previously worked as a Machine Learning Engineer at ByteDance for one year.
Education
Master's degree in Computer Science from Stanford University; Bachelor's degree from Tsinghua University, advisor information not provided.
Background
An enthusiastic machine learning engineer and researcher. Interests span natural language processing, large language models, information retrieval, multi-modality, question answering, dialog systems, etc.