CIIR Talk Series: Parisa Kordjamshidi, Spatial Intelligence: Neurosymbolic Modeling with Multiple Modalities

Content

Speaker

Parisa Kordjamshidi, Michigan State University

Abstract

Recent research shows that large language models (LLMs) often lack consistent reliability in tasks requiring complex reasoning, especially when a situated understanding of the physical world is involved. While they can produce fluent and well-structured text, they frequently fail at basic spatial reasoning skills such as understanding that left is the opposite of right, and struggle to ground such concepts in real-world contexts involving perception and action. In this talk, I will present our findings on how LLMs interpret spatial language and the challenges they face in reasoning and grounding it into visual modality. I will argue that symbolic representations can enhance neural models’ capacity for spatial and compositional reasoning by bridging linguistic structures with visual perception. Finally, I will introduce DomiKnowS, our generic neurosymbolic framework. DomiKnowS framework facilitates the seamless integration of symbolic logic and sub-symbolic representations to solve complex, AI-complete problems through various underlying algorithms.

Bio

Parisa Kordjamshidi is an Associate Professor of Computer Science and Engineering at Michigan State University. Her research focuses on Natural Language Processing, multimodal reasoning across vision and language, and neuro-symbolic learning. She received her Ph.D. from KU Leuven and conducted postdoctoral research at the University of Illinois Urbana-Champaign. She is a recipient of the NSF CAREER, Amazon Faculty Research, and Fulbright Scholar Awards, and her research team received the NAACL-2025 Outstanding and EMNLP-2025 SAC paper awards. Dr. Kordjamshidi serves as Associate Editor of JAIR, Co-editor in Chief of  ARR, Action Editor for TACL and  has held  roles in organization committee of major conferences including ACL, NAACL, EACL, EMNLP, ECML-PKDD, and AAAI. Recently, she was visiting associate professor at UCLA and currently is visiting professor at Bloomberg.

About

The CIIR Talk Series is an initiative for researchers and practitioners working on information retrieval and related disciplines to present their work.

Subscribe to the Zoom link/passcode notification mailing list by sending an email to ciir-talks-request [at] cs [dot] umass [dot] edu (ciir-talks-request[at]cs[dot]umass[dot]edu) with "subscribe" as the email subject (without the quotation marks), or click here for the Zoom link and reach out to zamani [at] cs [dot] umass [dot] edu (subject: CIIR%20Talks%20Passcode) (Hamed Zamani) for the passcode.