Mahtab Bigverdiمهتاب بیگ‌وردی

In Persian, Mahtab means moonlight🌙

Computer science PhD student at the University of Washington

Mahtab Bigverdi

I am a PhD student in the Paul G. Allen School at the University of Washington, advised by Ranjay Krishna and Linda Shapiro.

I work on the perceptual limits of vision-language models: what they actually see, where their spatial reasoning breaks down, and how to give them intermediate visual representations worth reasoning over.

I also work on developing and applying computer vision methods to medical and biomedical problems.

Before Seattle I earned my bachelor's degree in computer engineering at the Sharif University of Technology in Iran. In summer 2021 I received an International Undergraduate Excellence Award from the Chair for Computer Aided Medical Procedures & Augmented Reality (CAMPAR) at the Technical University of Munich.

  • Imaginative Perception Tokens Enhance Spatial Reasoning in Multimodal Language Models

    ECCV 2026

    Mahtab Bigverdi*, Linjie Li*, Weikai Huang*, Yiming Liu, Jaemin Cho, Jieyu Zhang, Tuhin Kundu, Chris Dongjoo Kim, Zelun Luo, Linda G. Shapiro, Ranjay Krishna

  • Ablate-to-Validate: Are Vision-Language Models Really Using Continuous Thought Tokens?

    Preprint, 2026

    Tianyi Zhang*, Mahtab Bigverdi*, Ranjay Krishna

  • Unfolding Spatial Cognition: Evaluating Multimodal Models on Visual Simulations

    ICLR 2026

    Linjie Li, Mahtab Bigverdi, Jiawei Gu, Zixian Ma, Yinuo Yang, Ziang Li, Yejin Choi, Ranjay Krishna

  • MedBLINK: Probing Basic Perception in Multimodal Language Models for Medicine

    ICCV 2025 Workshop on Computer Vision for Automated Medical Diagnosis

    Mahtab Bigverdi*, Wisdom Ikezogwo*, Kevin Zhang*, Hyewon Jeong, Mingyu Lu, Sungjae Cho, Linda Shapiro, Ranjay Krishna

  • Perception Tokens Enhance Visual Reasoning in Multimodal Language Models

    CVPR 2025

    Mahtab Bigverdi, Zelun Luo, Cheng-Yu Hsieh, Ethan Shen, Dongping Chen, Linda Shapiro, Ranjay Krishna

  • Gene-Level Representation Learning via Interventional Style Transfer in Optical Pooled Screening

    CVPR 2024 Workshop on Computer Vision for Microscopy Image Analysis

    Mahtab Bigverdi*, Burkhard Höckendorf*, Heming Yao, Phil Hanslovsky, Romain Lopez, David Richmond

  • Data Alignment for Zero-Shot Concept Generation in Dermatology AI

    ICLR 2024 Workshop on Navigating and Addressing Data Problems for Foundation Models

    Soham Gadgil*, Mahtab Bigverdi*

  • MIMIC: Masked Image Modeling with Image Correspondences

    CVPR 2024 Workshop for Learning 3D with Multi-View Supervision

    Mahtab Bigverdi*, Kalyani Marathe*, Nishat Khan, Tuhin Kundu, Aniruddha Kembhavi, Linda G. Shapiro, Ranjay Krishna

  • Image-based cell profiling enhancement via data cleaning methods

    PLOS ONE

    Mahtab Bigverdi*, Arghavan Rezvani*, Mohammad Hossein Rohban

* Equal contribution.

  • Research assistant

    University of Washington, Seattle, WA

  • Student Researcher

    Google, Mountain View, CA

  • Student Researcher

    Ai2, Seattle, WA

  • Research intern

    Genentech, South San Francisco, CA

  • Research intern

    Technical University of Munich, Germany

  • Research assistant

    Sharif University of Technology, Iran