Ruisheng Cao 💻
Ruisheng Cao Rhythm Tsao

staff research scientist

About Me

Ruisheng Cao currently works as a research scientist at Alibaba Qwen Coder Team. He obtained CS PhD at X-LANCE Lab supervised by professor Kai Yu, in Shanghai Jiao Tong University (SJTU). His research interests mainly lie in structured natural language understanding (including semantic parsing, text-to-SQL, code intelligence and task-oriented dialogue systems), model-based data generation or augmentation with cycle learning and iterative training, and large language model (LLM) or vision language model (VLM) based multi-modal agents in fields like coding, software engineering, data science and engineering, website navigation and computer control.

Download CV
Interests
  • LLM/VLM-based Multimodal Agents
  • Semantic Parsing
  • Text-to-SQL
  • Task-oriented Dialogue System
  • Structured NLU and NLG
Education
  • PhD in Computer Technology

    Shanghai Jiao Tong University

  • M.Eng. in Computer Technology

    Shanghai Jiao Tong University

  • B.Eng. in Computer Science

    Shanghai Jiao Tong University

Featured Publications
Recent Publications

Here are publications sorted by year.

(2025). NeuSym-RAG: Hybrid Neural Symbolic Retrieval with Multiview Structuring for PDF Question Answering. Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), Vienna, Austria, July 27 - August 1, ACL 2025.
(2025). Reducing Tool Hallucination via Reliability Alignment. Proceedings of the 42nd International Conference on Machine Learning, Vancouver, Canada. PMLR 267, ICML 2025.
(2025). EveMRC: Two-Stage Bidirectional Evidence Modeling for Multi-Choice Machine Reading Comprehension. IEEE Transaction on Audio, Speech and Language Processing, vol. 33, pp. 1011-1022, TASLP 2025.
(2025). Spider 2.0: Evaluating Language Models on Real-World Enterprise Text-to-SQL Workflows. International Conference on Learning Representations (ICLR), 2025.
(2024). Spider2-V: How Far Are Multimodal Agents From Automating Data Science and Engineering Workflows?. Advances in Neural Information Processing Systems (NeurIPS), 2024.