avatar

Joe Fioresi

Ph.D. Candidate
University of Central Florida
joseph.fioresi (at) ucf.edu


About Me

I am a 4rd year Ph.D. candidate at the University of Central Florida (UCF) studying Computer Vision under Dr. Mubarak Shah. I recently had a summer internship with Adobe working on smart media organization. My main focus is in video understanding tasks, with an emphasis on learning useful representations under privacy and fairness constraints. I am currently exploring extending these efforts to video-text multimodal generative models along with agentic frameworks. Feel free to reach out with questions or to discuss research!

Research Interests

News

Work Experience

PhD Research Scientist/Engineer Intern
Adobe Inc., Seattle, Washington, USA. May 2025 - Nov. 2025
Mentors: Pankaj Nathani, Fabian Caba, Kushal Kafle
  • Developed an efficient model to generate useful embedding space transformations via natural language inputs, achieving high clustering/classification performance while maintaining the benefits of a useful semantic embedding space.
  • Worked closely with product teams and end users to validate and discuss implementation of our model.
  • Filed for a patent, submitted paper currently under review.

Publications

  1. arXiv
    Learning to Share: Selective Memory for Efficient Parallel Agentic Systems
    Joseph Fioresi, Parth Parag Kulkarni, Ashmal Vayani, Song Wang, Mubarak Shah
    arXiv preprint, 2026.
    PDF ArXiV Project Page Preprint
    arXiv
    MedRoute: RL-Based Dynamic Specialist Routing in Multi-Agent Medical Diagnosis
    Ashmal Vayani, Parth Parag Kulkarni, Joseph Fioresi, Song Wang, Mubarak Shah
    arXiv preprint, 2026.
    PDF ArXiV Project Page Preprint
    ICLR
    Privacy Beyond Pixels: Latent Anonymization for Privacy-Preserving Video Understanding
    Joseph Fioresi, Ishan Dave, Mubarak Shah
    International Conference on Learning Representations (ICLR), 2026.
    PDF ArXiV Code Project Page Poster Presentation
    AAAI
    SafeR-CLIP: Mitigating NSFW Content in Vision-Language Models While Preserving Pre-Trained Knowledge
    Adeel Yousaf, Joseph Fioresi, James Beetham, Amrit Singh Bedi, Mubarak Shah
    Association for the Advancement of Artificial Intelligence (AAAI), 2026.
    PDF ArXiV Code Project Page Poster Presentation
    arXiv
    ImplicitQA: Going beyond frames towards Implicit Video Reasoning
    Sirnam Swetha, Rohit Gupta, Parth Parag Kulkarni, David G Shatwell, Jeffrey A Chan Santiago, Nyle Siddiqui, Joseph Fioresi, Mubarak Shah
    arXiv preprint, 2025.
    PDF ArXiV Project Page Preprint
    ICLR
    ALBAR: Adversarial Learning approach to mitigate Biases in Action Recognition
    Joseph Fioresi, Ishan Dave, Mubarak Shah
    International Conference on Learning Representations (ICLR), 2025.
    PDF ArXiV Code Project Page Poster Presentation
    ICCV
    TeD-SPAD: Temporal Distinctiveness for Self-supervised Privacy-preservation for video Anomaly Detection
    Joseph Fioresi, Ishan Dave, Mubarak Shah
    International Conference on Computer Vision (ICCV), 2023.
    PDF ArXiV Code Project Page Poster Presentation
    JPV
    Electroluminescence Analysis and Grading of Hail Damaged Solar Panels
    Andrew M. Gabor, Philip J. Knodle, Maurice Covino, Joseph Fioresi, Dylan J. Colvin, Kristopher O. Davis
    IEEE Journal of Photovoltaics (JPV), 2022.
    PDF Journal Publication
    PVSC/JPV
    Automated Defect Detection and Localization in Photovoltaic Cells using Semantic Segmentation of Electroluminescence Images
    Joseph Fioresi, Dylan J. Colvin, Rafaela Frota, Rohit Gupta, Mengjie Li, Hubert P. Seigneur, Shruit Vyas, Sofia Oliveira, Mubarak Shah, Kristopher O. Davis
    IEEE Journal of Photovoltaics (JPV)/IEEE Photovoltaics Specialists Conference (PVSC), 2021.
    PDF Code Oral Presentation/Journal Publication

Services

Conference Reviewing

Journal Reviewing


Powered by Jekyll and Minimal Light theme.