About Me

I am a Ph.D. candidate at Duke University, advised by Prof. Cate Brinson. Before starting my Ph.D., I studied materials science and computer science at Sabanci University.

Previously, I was an AI Resident at Lila Sciences, working on scientific reasoning and information extraction. Before that, I interned at IBM Research, where I worked on scientific reasoning, AI agents, and information extraction.

Research Interests

I am interested in multimodal AI systems for scientific reasoning and knowledge extraction, with a focus on autonomously interpreting diverse scientific data sources including charts, tables, figures, and text to structure knowledge in machine-understandable form. My current work spans developing and evaluating large language models and vision-language models for interpretable information extraction from scientific literature, as well as building tool-augmented agentic workflows for verifiable scientific reasoning. My goal is to unify these capabilities into scalable pipelines that power accelerated discovery in science.

If you're interested in discussing research ideas or just want to chat, please contact me via email!

News

  • [Oct 2026] Selected to receive $20,000 in Claude usage credits through the MIT–Anthropic AI for Science Study.
  • [Apr 2026] Co-organized the AI4MAT Workshop at ICLR 2026 in Rio de Janeiro, Brazil 🇧🇷.
  • [Mar 2026] Awarded the 2026–2027 Maclin Community Connections Grant to support organizing the 3rd Annual LLM Hackathon for Applications in Materials & Chemistry at Duke.
  • [Feb 2026] Started my AI residency at Lila Sciences in Boston, MA.
  • [Dec 2025] Gave an invited talk titled "Scientific Reasoning and Information Extraction with Language Models" at Middle East Technical University (METU).
  • [Dec 2025] Presented Verifiable Chemical Reasoning through Tool-Calling Agentic Workflow at the Scaling Environments for Agents Workshop at NeurIPS 2025 in San Diego.
  • [May 2025] Started my internship at IBM Research in San Jose, California.
  • [Dec 2024] Presented 'Information extraction from diverse materials science charts/plots' at MRS in Boston.
  • [Nov 2024] Attended EMNLP 2024 in Miami .
  • [May 2024] Won an Anthropic Award at the 2024 LLMs for Materials Hackathon with the project MaSTeA, an interactive web app that enables easy testing of LLMs to evaluate their strengths and weaknesses across various subfields of materials science.
  • [Apr 2024] Presented 'Using Large Language Models for Data Extraction from Tables in Materials Literature' at the SouthNLP Symposium. View the SouthNLP poster.
  • [Feb 2024] Presented 'Using Large Language Models to Mine Materials Literature' at Materials Research Data Alliance (MARDA) Annual Meeting. The presentation is available on YouTube.
  • [Dec 2023] Presented 'Retrieval of Synthesis Parameters of Polymer Nanocomposites Using LLMs' at AI4MAT Workshop at NeurIPS (New Orleans) and ML4Molecules Workshop.
  • [Nov 2023] Attended OpenAI Developers Conference in San Francisco.
  • [Oct 2023] Interviewed by the Materials Research Data Alliance (MARDA) on building the future of materials research.
  • [Aug 2022] Received full tuition and stipend support from the AI for Understanding and Designing Materials program.
  • [Aug 2022] Started my Ph.D. at Duke.
🌟 Life Outside Research

When I'm not working on research, you can find me:

  • 🧗‍♀️ Bouldering at the climbing gym
  • 🏃‍♀️ Running on Saturdays: Follow my progress on Strava!
  • 🧘‍♀️ Practicing hot yoga

Selected Publications

  1. Figure for RegExtract: A Benchmark for PFAS Regulatory Information Extraction with LLMsAI4Law at ICML
    Circi, D., Lionti, K., Swaminathan, S., Sanders, D. P., Brinson, L. C., Dhingra, B., Shbita, B., Elkaref, M., Capponi, S., Erdmann, T., Ransom, B.
    AI for Law Workshop at ICML 2026
  2. Figure for Information Extraction from Diverse Charts in Materials ScienceLM4Sci at COLM
    Circi, D., Bradley, M., Blouir, S., Wilthan, B., Anastasopoulos, A., Shehu, A., Brinson, L. C., Dhingra, B.
    LLM for Scientific Discovery Workshop at COLM 2025
  3. Figure for Challenges and Vision for Standardization of Biopolymer Data Sets for Machine LearningBiomacromolecules
    Lalonde, J. N., Circi, D., Marrone, B. L., Zauscher, S., Brinson, L. C.
    Biomacromolecules, 2026
  4. Figure for Evaluating Morphological Compositional Generalization in Large Language ModelsNAACL
    Ismayilzada, M., Circi, D., Sälevä, J., Sirin, H., Köksal, A., Dhingra, B., Bosselut, A., Ataman, D., van der Plas, L.
    NAACL 2025
  5. Figure for How Well Do Large Language Models Understand Tables in Materials Science?IMMI
    Circi, D., Khalighinejad, G., Chen, A., Dhingra, B., Brinson, L.
    Integrating Materials and Manufacturing Innovation, 2024
  6. Figure for Retrieval of Synthesis Parameters of Polymer Nanocomposites Using LLMsAI4Materials at NeurIPS
    Circi, D., Khalighinejad, G., Badhwar, S., Dhingra, B., Brinson, L.
    AI4Materials Workshop at NeurIPS 2023
  7. Figure for 14 Examples of How LLMs Can Transform Materials Science and Chemistry: A Reflection on a Large Language Model HackathonDigital Discovery
    Jablonka, K. M., Ai, Q., Al-Feghali, A., Badhwar, S., Bocarsly, J. D., Bran, A. M., Bringuier, S., Brinson, L. C., Choudhary, K., Circi, D., Cox, S., et al.
    Digital Discovery, 2023
  8. Figure for The Mutation Profile of SARS-CoV-2 Is Primarily Shaped by the Host Antiviral DefenseViruses
    Azgari, C., Kilinc, Z., Turhan, B., Circi, D., Adebali, O.
    Viruses, 2021

Services

Reviewing Roles

  • AI for Accelerated Materials Design Workshop at ICLR 2025
  • Machine Learning for Life and Material Science Workshop
  • Computational Materials Science
  • Integrating Materials and Manufacturing Innovation
  • Data in Brief
  • COLM 2026

Organizer and Volunteer Roles

  • Apr 2026: Organizer for the AI4MAT Workshop at ICLR 2026.
  • Sep 2025: Organizer for the LLM Hackathon for Applications in Materials and Chemistry at Duke. Read our event write-up.
  • 2024–2025: AI for Designing Materials Program Guest Speaker Committee Chair
    👥 View Previous Guest Speakers
    • Shruti Badhwar (Entrepreneur)
    • Gowoon Cheon (Research Scientist at Google DeepMind)
    • Martin van der Schelling (Ph.D. Student at Brown)
    • Abhijeet Gangan (Ph.D. Student at UCLA)
    • Tong Xie (Entrepreneur)
  • 2024–2025: Library Graduate Advisory Board Member
  • May 2024: Organizer for 2024 LLM Hackathon for Applications in Materials and Chemistry
  • Dec 2023: Volunteer for NeurIPS Women in ML Workshop