Rosni Vasu

PhD Student (Research Assistant) at University of Zurich, Visiting Student at Ai2.

prof_pic.jpg

Department of Informatics

University of Zurich

Zürich, Switzerland

👋 Hi! I am Rosni Vasu, a PhD candidate in Department of Informatics at the University of Zurich, advised by Prof. Abraham Bernstein.

Currently, I am visiting the Allen Institute for AI (Ai2), in Seattle, working with the Aristo team — fortunate to collaborate with Bhavana Dalvi and Peter Clark — on literature-grounded hypothesis generation and ranking.

🎓 I hold a master’s degree in Artificial Intelligence from the University of Hyderabad, where I worked with Prof. Vineet Padmanabhan on recommender systems.
Before joining my PhD, I was a researcher in the Cybersecurity and Privacy group at Tata Research Development and Design Centre, Pune, India, where I had the privilege to work with Sachin Lodha.

🧑‍🔬 Research Interests: My research focuses on AI-assisted scientific discovery, specifically in building language model systems that support complex reasoning over scientific knowledge. I have worked on knowledge distillation, literature-grounded research idea generation, and structuring scientific knowledge for downstream use. I am also passionate about using large language models to the broader societal benefit.

📬 If you are interested in collaboration, feel free to send me an email.


what's new

Aug 20, 2025 Our paper HypER: Literature‑grounded Hypothesis Generation and Distillation with Provenance got accepted at EMNLP 2025 — see you in Suzhou, China! 🎉 :boom:
Jun 17, 2025 Our poster on A Large Language Model based Framework for Dementia Related Hypothesis Generation has been accepted and successfully presented at HealTAC 2025 in Glasgow (16–18 June) 🎉
Jun 15, 2025 Our work has been released as an arXiv preprint: HypER: Literature‑grounded Hypothesis Generation and Distillation with Provenance —now available at 🔗arXiv:2506.12937.🎉✨🚀
Mar 01, 2025 Excited to start as a visiting student at Ai2, where I continue working on scientific hypothesis generation and ranking.
Nov 13, 2024 Presented our dataset paper “SciHyp: A Fine-grained Dataset Describing Hypotheses and Their Components from Scientific Articles” at ISWC 2024. Excitingly, our work was nominated for the Best Resource Paper Award! 🏅

selected publications

  1. EMNLP
    HypER: Literature-grounded Hypothesis Generation and Distillation with Provenance
    Vasu, Rosni, Basu, Chandrayee,  Mishra, Bhavana Dalvi and 3 more authors
    2025
  2. HealTAC
    A Large Language Model based Framework for Dementia Related Hypothesis Generation
    Vasu, Rosni, Dong, Hang,  Abdulle, Yusuf and 2 more authors
    In Healthcare Text Analytics Conference Jun 2025
  3. ISWC
    SciHyp: A Fine-grained Dataset Describing Hypotheses and Their Components from Scientific Articles.
    Vasu, Rosni, Sarasua, Cristina,  and Bernstein, Abraham
    In International Semantic Web Conference Nov 2024
  4. AAAI
    Med-EASi: Finely Annotated Dataset and Models for Controllable Simplification of Medical Texts.
    Basu, Chandrayee,  Vasu, Rosni,  Yasunaga, Michihiro and 1 more author
    In Association for the Advancement of Artificial Intelligence, AAAI 2023 Feb 2023
  5. HUMAN.AI@AAAI
    Automatic Medical Text Simplification: Challenges of Data Quality and Curation.
    Basu, Chandrayee,  Vasu, Rosni,  Yasunaga, Michihiro and 2 more authors
    In Human Partnership with Medical Artificial Intelligence (HUMAN.AI) ), AAAI Fall 2021 Symposium Nov 2021