projects

Research I have done, from RL post-training and evaluation to retrieval and open datasets, plus the open-source repositories behind it. Teaching and coursework from Stanford at the bottom.

Research

Open source

  • CDial-GPT thu-coai/CDial-GPT
    LCCC, a 12M-dialogue cleaned Chinese conversation corpus, with pre-trained dialogue models. NLPCC 2020 Best Student Paper.
    GitHub stars for thu-coai/CDial-GPT Hugging Face monthly downloads for thu-coai/lccc
  • CrossWOZ thu-coai/CrossWOZ
    The first large-scale Chinese cross-domain task-oriented dialogue dataset, with a user simulator and benchmark models. TACL 2020.
    GitHub stars for thu-coai/CrossWOZ Hugging Face monthly downloads for GEM/CrossWOZ
  • KdConv thu-coai/KdConv
    A multi-domain knowledge-driven dialogue dataset grounded in knowledge graphs, with benchmark models. ACL 2020.
    GitHub stars for thu-coai/KdConv Hugging Face monthly downloads for thu-coai/kdconv
  • ColBERT-Serve stanford-futuredata/colbert-serve
    Memory-mapped, multi-stage serving for ColBERT with hybrid scoring; 90% less RAM. ECIR 2025.
    GitHub stars for stanford-futuredata/colbert-serve

Teaching

Coursework