Qingyun Wang

Qingyun Wang

Ph.D. student, Siebel School of Computing and Data Science, University of Illinois at Urbana-Champaign

About me

Email: qwang16 [at] wm [dot] edu

Hello!

I am Qingyun Wang, an incoming Assistant Professor of the Data Science Department at William & Mary, starting in August 2025.

I am a Ph.D. student in the Siebel School of Computing and Data Science at the University of Illinois at Urbana-Champaign. I have been a member of the BLENDER Lab since 2017, supervised by Prof. Heng Ji. Previously, I graduated a summa cum laude from Rensselaer Polytechnic Institute with a dual B.S. degree in Computer Science and Mathematics.

I am among the first researchers to develop a virtual scientific research assistant (i.e., PaperRobot [ACL 2019]) for literature-based discovery by extracting and synthesizing insights from papers. My research interest lies in Automated Literature Understanding and Scientific Discovery. My long-term vision is to develop AI for Scientists (AI4Scientist) tools to effectively accelerate and democratize the entire research lifecycle for scientists, from knowledge acquisition [(NAACL ‘21 Best Demo🏆)I,II,III], hypothesis generation [IV], multimedia procedure planning for experiment design [V], experiment execution[VI], conduction to writing[VII,VIII], and evaluating the paper draft[IX].

Research Interests

  1. Scientific Multimodal Foundation Models with Critical Thinking: Build a new multimodal scientific LLM to understand formulas, tables, figures, and charts; Design model can dynamically extract and integrate new multimodal knowledge elements without additional training
  2. Few-Shot Scientific Knowledge Acquisition: Investigate methods for extracting knowledge from scientific corpora with limited annotation
  3. Planning and Reasoning in Scientific Domain: Utilize both structured and unstructured knowledge as well as logic rules among knowledge elements to produce trustworthy and explainable results
  4. Scientific Research Agents with Physical World Interactions: Train a new human-in-the-loop reinforcement learning framework with human, experimental, and literature feedback, which can leverage small datasets in closed-loop discovery platforms; Develop a human-in-the-loop self-driving laboratory that can complete the scientific research lifecycle through interactions with the physical world, such as a robotic laboratory

Prospective students

I am constantly looking for highly motivated PhD students (as fully-funded RAs) and interns to join my lab! If you are interested in working with me, please fill [this form]. After completing the form, you are also welcome to reach out via email (qwang16 [at] wm [dot] edu). I will read all submitted forms and emails but I do apologize for not being able to respond to each of them. Prospective Students English, Prospective Students Chinese

I’m happy to collaborate and answer questions about my research. I especially encourage students from underrepresented groups to reach out, as I commited to foster diversity, equity and inclusion in our community.

Recent News

Load More