Publications

Peer-reviewed work and preprints — LLM interpretability, geometry & statistics, and mobile sensing.

Google Scholar ↗

2026

2026

  1. Understanding and Mitigating Dataset Corruption in LLM Steering
    Understanding and Mitigating Dataset Corruption in LLM Steering
    arXiv 2026
    Cullen Anderson , Narmeen Oozeer , Foad Namjoo, Remy Ogasawara , Amirali Abdullah , and Jeff M. Phillips
    2026
    How noisy and adversarial corruption in steering datasets degrades LLM control — and robust estimation that mitigates it.
    arXiv

2025

2025

  1. Designing a Secure and Resilient Distributed Smartphone Participant Data Collection System
    Designing a Secure and Resilient Distributed Smartphone Participant Data Collection System
    SmartSP 2025
    Foad Namjoo, Neng Wan , Devan Mallory , Yuyi Chang , Nithin Sugavanam , Longyin Lee , Ning Xiong , Emre Ertin , and Jeff M. Phillips
    In Proceedings of the EAI International Conference on Security and Privacy in Smart Cities (SmartSP) , 2025
    The system design behind MotionPI: secure, resilient, privacy-first mobile data collection at scale.
    arXiv
  2. Addressing Data Limitations to Explore Management Strategies and Adaptations Using Stylized Agent-Based Modeling: A Case Study of Socio-Environmental Systems
    Addressing Data Limitations to Explore Management Strategies and Adaptations Using Stylized Agent-Based Modeling: A Case Study of Socio-Environmental Systems
    Ecol. Model. 2025
    Mehrsa Pouladi , Parsa Pouladi , Saba Naderian Jahromi , and Foad Namjoo
    Ecological Modelling, 2025
    Stylized agent-based modeling to explore management strategies for socio-environmental systems under limited data.
    Link
  3. Efficient and Stable Multi-Dimensional Kolmogorov–Smirnov Distance
    Efficient and Stable Multi-Dimensional Kolmogorov–Smirnov Distance
    arXiv 2025
    Peter Matthew Jacobs , Foad Namjoo, and Jeff M. Phillips
    2025
    Authors listed alphabetically, following the convention in theory.
    A multi-dimensional Kolmogorov–Smirnov distance that’s a true metric, with a stable finite-sample two-sample test, near-linear in 2–4D.
    arXiv

2024

2024

  1. A Hyperspectral Change Detection (HCD-Net) Framework Based on Double Stream Convolutional Neural Networks and an Attention Module
    A Hyperspectral Change Detection (HCD-Net) Framework Based on Double Stream Convolutional Neural Networks and an Attention Module
    Remote Sens. 2024
    Seyd Teymoor Seydi , Mahboubeh Boueshagh , Foad Namjoo, Seyed Mohammad Minouei , Zahir Nikraftar , and Meisam Amani
    Remote Sensing, 2024
    A dual-stream CNN with an attention module for change detection in hyperspectral imagery.
    Link

2021

2021

  1. A Machine Learning Approach for Harmful Algal Bloom (Red Tide) Forecasting Using MODIS Level 3 Ocean Colour Products from Google Earth Engine
    A Machine Learning Approach for Harmful Algal Bloom (Red Tide) Forecasting Using MODIS Level 3 Ocean Colour Products from Google Earth Engine
    AGU 2021
    Moein Izadi , Foad Namjoo, and Zahir Nikraftar
    In AGU Fall Meeting Abstracts , 2021
    Forecasting harmful algal blooms (red tide) from MODIS ocean-colour products on Google Earth Engine.
    Link

2020

2020

  1. Statistical Learning Approach to Harmful Algal Bloom Forecasting Using MODIS Ocean Colour Parameters
    Statistical Learning Approach to Harmful Algal Bloom Forecasting Using MODIS Ocean Colour Parameters
    AGU 2020
    Moein Izadi , Mohamed Sultan , Racha Kadiri , Amin Ghannadi , Zahir Nikraftar , and Foad Namjoo
    In AGU Fall Meeting Abstracts , 2020
    A statistical-learning approach to harmful algal bloom forecasting from MODIS ocean-colour parameters.
    Link
  2. Australian 2020 Bushfire Propagation, Network Science Approach
    Australian 2020 Bushfire Propagation, Network Science Approach
    Conf. 2020
    Foad Namjoo, Ali Kamandi , and Seyed Mohammad Minouei
    In National Conference on Vision of the Country , 2020
    Modeling the 2020 Australian bushfire propagation with a network-science approach.
    Link