Zhengyuan Liu

Asst. Head of the AI4EDU Programme
Tech Lead of Multimodal Generative AI Group
Institute for Infocomm Research, A*STAR, Singapore
IEEE Senior Member

[Email] [Google Scholar] [LinkedIn]

Research Interest
Multimodal and Multilingual Foundation Models.
Generative AI for Education, Healthcare, and Life Science.
Accessibility, Reliability, and Explainability for Human-Centered AI.

Zhengyuan

Current Key Projects
🌟 AI for Education Programme | Human-centered AI
> Our vision is to transform how people learn knowledge and advance science by creating AI systems that can understand, reason, and collaborate across disciplines and languages.
> Special Interest Group on Human-AI Collaborative Learning, Exploration, and Discovery (SIGCoLED)

🚀 National Large Language Model Programme (MERaLiON SG)
> Working on improving multilingual and multimodal LLMs' capabilities of knowledge and reasoning.

  • “Imagination is more important than knowledge.” – Albert Einstein.

    • Join Us & Collaboration (📧 just email me)
    ○ Research Assistant / Student Intern in AI for Education. Remote intern is also welcome!
    Topic Conversational intelligent tutoring systems, Human-AI collaborative learning, etc.
    ○ Research Assistant / Student Intern in Generative AI and Multimodal Fundation Models.
    Topic Knowledge-enhanced reasoning, Multi-agent collaboration, etc.
    ○ Research Collaboration in AI for Life Science & Healthcare.
    Topic Reach out to me for an online / in-person chat (☕) on next-generation science accelerators, etc.

    News [Jun. 2025] Our work “COGENT: A Curriculum-oriented Framework for Generating Grade-appropriate Educational Content” will appear in BEA 2025.
    News [May. 2025] Our work “SingaKids: A Multilingual Multimodal Dialogic Tutor for Language Learning” will appear in ACL 2025.
    News [May. 2025] Our work “Reinforcing Compositional Retrieval: Retrieving Step-by-Step for Composing Informative Contexts” will appear in ACL 2025.
    News [Mar. 2025] Our work “Scaling Up Collaborative Dialogue Analysis: An AI-driven Approach to Understanding Dialogue Patterns in Computational Thinking Education” got published in LAK 2025.
    News [Jan. 2025] Our paper “CrossIn: An Efficient Instruction Tuning Approach for Cross-Lingual Knowledge Alignment” got the 🏅 Best Paper Award in SumEval@COLING 2025.
    News [Nov. 2024] Our paper “Learning planning-based reasoning by trajectories collection and process reward synthesizing” got the 🏅 Outstanding Paper Award in EMNLP 2024.
    News [Nov. 2024] Presented our work “Personality-aware Student Simulation for Conversational Intelligent Tutoring Systems” in EMNLP 2024.
    News [Sep. 2024] Presented our work “Optimizing Code-Switching in Conversational Tutoring Systems: A Pedagogical Framework and Evaluation” in SIGDIAL 2024.
    News [Sep. 2024] Our paper “CRAFT: Extracting and Tuning Cultural Instructions from the Wild” got the 🏅 Best Paper Award in C3NLP@ACL2024.
    News [Feb. 2024] Presented our work “Scaffolding Language Learning via Multi-modal Tutoring Systems with Pedagogical Instructions” in IEEE CAI 2024.
    News [Dec. 2023] Our paper “Joint Dialogue Topic Segmentation and Categorization: A Case Study on Clinical Spoken Conversations” got the 🏅 Outstanding Paper Award in EMNLP 2023.
    News [Jul. 2022] Presented our work “Learning from Bootstrapping and Stepwise Reinforcement Reward: A Semi-Supervised Framework for Text Style Transfer” in NAACL 2022.
    News [Sep. 2021] Our paper “Coreference-Aware Dialogue Summarization” got the 🏅 Best Paper Award in SIGDIAL 2021.

    Academic Service
    Conference Program Committee and Reviewer: NeurIPS, ICLR, ACL, EMNLP, NAACL, AAAI, etc.
    Conference Session Chair: ICASSP and Interspeech.
    Journal Reviewer: IEEE TASLP, ACM CSUR, Neurocomputing, Computer Speech & Language, etc.