WASP 2025 will have several keynote speakers. The confirmed speakers include:

  • Karin Verspoor, Dean, School of Computing Technologies, Royal Melbourne Institute of Technology, Australia
    • Impacts of AI on the Scientific Ecosystem
    • Abstract: Artificial Intelligence, in both predictive and generative forms, is increasingly being adopted to support — and in some cases, entirely perform — scientific research. In this talk, I will discuss both the significant opportunities that AI brings to science and the questions that AI raises for science. The talk will be grounded in some of my own work in use cases including bio-curation and literature-based discovery, as well as ongoing work exploring the limitations of LLMs, that may have particular impacts in the scientific arena.
  • Kartheik Iyer, NASA Hubble Fellow, Columbia University, USA
    • Wandering through the Cosmic Library: Harnessing the embedding spaces of large language models for astronomical research and discovery
    • Abstract: Astronomical literature is expanding at an unprecedented rate, with thousands of papers added every month to preprint servers like arXiv.org and indexed by the NASA Astrophysics Data System (ADS). For academics and students, staying current with relevant work while keeping track of shifting trends therefore represents a critical challenge. This talk presents lessons learned from working with the UniverseTBD collaboration to develop Pathfinder, a complement to systems like ADS that uses large language models combined with retrieval-augmented generation (RAG) to enable semantic search and question-answering across the astronomy literature. I will discuss some of the unique challenges of applying NLP and LLMs to scientific publications in astronomy, including: (1) handling domain-specific terminology and mathematical notation, (2) grounding LLM responses in archival data to minimize hallucinations, and (3) leveraging embeddings to create interpretable semantic spaces for literature exploration. Drawing from Pathfinder’s deployment (pfdr.app) and user feedback from the astronomy community, I will highlight how interpretable intermediate representations such as semantic embeddings and citation graphs can lend interpretability and rigor to otherwise black-box models, and help their adoption in research pipelines. Beyond astronomy, the development of these methods have broader implications for AI-assisted scientific discovery across disciplines. I will conclude by discussing open challenges in adapting large models in scientific contexts, the importance of retrieval mechanisms that preserve provenance, and the potential for LLM-powered tools to not just assist with literature review, but to help generate testable hypotheses and identify research gaps. As scientific publishing continues to accelerate across all fields, developing trustworthy and grounded systems for navigating the literature becomes increasingly essential.