Bishoy M. Galoaa

PhD student in Electrical and Computer Engineering
Northeastern University

I work with Sarah Ostadabbas in the Augmented Cognition Lab.

Portrait of Bishoy Galoaa

Research

I study the foundations of visual intelligence and visual learning. I want to understand how machines learn from visual experience, and how those learned representations support perception, reasoning, and generation.

I use motion, space, and physical interactions to study what visual models learn about the world. My goal is to build systems that use that knowledge to interpret what they see and generate scenes and events that are consistent with how the world works.

“Thoughts without content are empty, intuitions without concepts are blind.”

Immanuel Kant, Critique of Pure Reason (A51/B75)

Publications

2027

  • ViMoLa: Discrete Motion Tokens for Language-Guided Video Generation
    B. Galoaa and S. Ostadabbas — WACV 2027 arXiv GitHub
  • Track and Caption Any Motion: Open-Vocabulary Spatiotemporal Captioning via Trajectory-Conditioned Generation
    B. Galoaa and S. Ostadabbas — WACV 2027 arXiv GitHub

2026

  • Structure Over Scale: Learning Visual Reasoning from Pedagogical Video
    B. Galoaa, X. Bai, and S. Ostadabbas — NeurIPS 2026 arXiv GitHub
  • Motion-o: Trajectory-Grounded Video Reasoning
    B. Galoaa*, S. Moezzi*, X. Bai, and S. Ostadabbas — NeurIPS 2026 arXiv GitHub
  • PanoWorld: Geometry-Consistent Panoramic Video World Modeling
    L. Jiang, X. Bai, B. Galoaa, et al. — NeurIPS 2026 arXiv GitHub
  • MoReGen: Multi-Agent Motion-Reasoning Engine for Code-based Text-to-Video Synthesis
    X. Bai, H. Liang, B. Galoaa, et al. — CVPR 2026 New arXiv GitHub
  • UniTrack: Differentiable Graph Representation Learning for Multi-Object Tracking
    B. Galoaa, X. Bai, U. Nandi, S. Amraee, S. Ostadabbas — ICLR 2026 Nectar Track · Spotlight Oral · 3DV 2026 arXiv GitHub
  • HORNet: Task-Guided Frame Selection for Video Question Answering with Vision-Language Models
    X. Bai*, B. Galoaa*, and S. Ostadabbas — CV4Smalls Workshop, CVPR 2026 arXiv GitHub
  • K-Track: Kalman-Enhanced Tracking for Accelerating Deep Point Trackers on Edge Devices
    B. Galoaa, P. Closas, S. Ostadabbas — WACVW 2026 arXiv GitHub
  • LAPA: Look Around and Pay Attention — Multi-camera Point Tracking Reimagined with Transformers
    B. Galoaa, X. Bai, S. Moezzi, et al. — 3DV 2026 Oral Best Paper Award arXiv GitHub

2025

  • SPARTAN: Spatiotemporal Pose-Aware Retrieval for Text-Guided Autonomous Navigation
    X. Bai, S. A. Sreeramagiri, B. Galoaa, et al. — BMVC 2025 GitHub
  • More Than Meets the Eye: Enhancing Multi-Object Tracking with Softmax Splatting and Optical Flow
    B. Galoaa, S. Amraee, S. Ostadabbas — ICML 2025 GitHub
  • Dragontrack: Transformer-Enhanced Graphical Multi-Person Tracking
    B. Galoaa, S. Amraee, S. Ostadabbas — WACV 2025 GitHub
  • Classification of Infant Sleep–Wake States from Natural Overnight In-Crib Videos
    S. Moezzi, M. Wan, B. Galoaa, et al. — WACVW 2025 GitHub
  • Advancing Prognostics in Oncology: ML Models for Predicting Survival in Undifferentiated Pleomorphic Sarcoma
    A. G. Girgis, B. M. Galoaa, et al. — Annals of Surgical Oncology, 2025
  • Predicting Long-Term Survival in Myxofibrosarcoma
    S. Rampam, A. G. Girgis, B. M. Galoaa, et al. — Surgical Oncology, 2025
  • Extraskeletal Osteosarcoma: MicroRNA Patterns
    S. A. Lozano-Calderon, B. M. Galoaa, et al. — CTOS 2025
  • Real-Time Uncertainty Detection for Safe, Adaptive Exoskeleton Control
    B. Galoaa et al. — ICRA Workshops 2025

2024

  • Multiple Toddler Tracking in Indoor Videos
    S. Amraee, B. Galoaa, et al. — WACVW 2024 arXiv GitHub
  • A Personalized Predictive Model for Salivary Gland Cancer
    A. Girgis, B. Galoaa, A. Devaiah — COSM 2024
  • A Novel AI Model for Optimizing Treatment of Salivary Gland Malignancies
    A. Girgis, B. Galoaa, A. Devaiah — AAO-HNSF 2024
  • Bias or Best Fit? SEER vs. NCDB in ML for Osteosarcoma Survival
    A. G. Girgis, B. M. Galoaa, et al. — Clinical Orthopaedics and Related Research, 2024
  • Machine Learning–Assisted Decision Making in Orthopaedic Oncology
    P. A. Rizk, M. R. Gonzalez, B. M. Galoaa, et al. — accepted for publication

Preprints & Under Review

  • Lang2Motion: Bridging Language and Motion Through Joint Embedding Spaces
    B. Galoaa, X. Bai, and S. Ostadabbas — under review, 2026 Preprint arXiv GitHub
  • Uncertainty-Aware Ankle Exoskeleton Control
    F. M. Tourk*, B. Galoaa*, S. Shajan*, A. J. Young, M. Everett, and M. K. Shepherd — arXiv preprint arXiv:2508.21221, 2025 arXiv
  • Cognitive Learning through Hierarchical Prototypes and Dynamic Focus
    B. Galoaa, S. Ostadabbas — under review, 2025 Preprint
  • ML Algorithms for Survival Prediction in Synovial Sarcoma
    J. O. Werenski, S. Rampam, B. Galoaa, et al. — under review Preprint

Datasets

  • PhiLLM Data

    Synthetic Newtonian point-mass problems with exact simulator ground truth.

  • PhiLLM Results

    Evaluation metrics, model predictions, and figures from experiments on Newtonian reasoning.

  • Motion-o-MCoT (PLM + motion keyframes)

    3,168 training examples of motion-centric chain-of-thought reasoning with sharded keyframes, a subset of STGR.

  • MotionBlind

    A contrastive benchmark for physical-motion perception in Video-LLMs, from MotionBlind: Probing the Illusion of Motion Understanding in Video-LLMs.

Awards

  • Best Paper Award — International Conference on 3D Vision (3DV 2026) Winner
    For "Look Around and Pay Attention: Multi-camera Point Tracking Reimagined with Transformers"
  • Best Poster Presentation Award — COSM-AHNSF (Spring 2025)
  • COE Outstanding Graduate Student Award — Northeastern University (2025)
  • COE Outstanding Graduate Student Award — Northeastern University (2024)
  • Best of Scientific Orals — AAO-HNSF Annual Meeting & OTO EXPO (2024)

Talks

Software

  • Anvil — A research-first, evaluation-first inference library for LLMs with reproducible manifests, per-request logits processors, and built-in support for DoLa contrastive decoding. Available on PyPI: pip install anvil-eval
30-Day Novel Ideas Challenge

I set out to develop one new idea per day for a month and published five ideas.

Originally shared as a public challenge on LinkedIn.