Bryce Grant

Electrical Engineering PhD Candidate

Case Western Reserve University

I am a 2nd year Ph.D. student at Case Western Reserve University where I’m advised by Prof. Peng “Edward” Wang. I received my dual B.S. in Electrical and Computer Engineering from the University of Kentucky in 2024. I’m currently funded by the NSF GRFP.

I’m interested in building robotic systems that reason about pose, motion, and uncertainty through geometric structures and causal inference.

I’m currently working on semantic affordances and topology-informed interpretability for VLAs.

Email / Google Scholar / Twitter / GitHub / Resume
Bryce Grant
Adventures

Not All Features Are Created Equal

A Mechanistic Study of Vision-Language-Action Models

TrianguLang

Geometry-Aware Semantic Consensus for Pose-Free 3D Localization

Sheaf Interpretability

Gluing Local Contexts into Global Meaning via Sheaf Cohomology

Quat Viz

Quaternion Visualizations

Updates

* denotes equal contribution

Not All Features Are Created Equal: A Mechanistic Study of Vision-Language-Action Models

Bryce Grant*, Xijia Zhao*, Peng Wang

Under Review | Presenting @ ICLR 2026 MM Intelligence Workshop

Paper Project Page Action Atlas

TrianguLang: Geometry-Aware Semantic Consensus for Pose-Free 3D Localization

Bryce Grant, Aryeh Rothenberg, Atri Banerjee, Peng Wang

Under Review

Paper Project Page

Gluing Local Contexts into Global Meaning

Bryce Grant, Peng Wang

Presenting @ ICLR 2026 UCLR Workshop

Paper

Quaternion Approximation Networks for Enhanced Image Classification and Oriented Object Detection

Bryce Grant, Peng Wang

IROS 2025 | Oral

Paper Project Page Code

Projects

Selected research and class projects.

Causal DenseFusion

Computer Vision · Causal Inference

2024

Causal DenseFusion

Refines 6D pose estimates using causal interventions and backdoor adjustments based on structural causal models. Improves robustness to viewpoint ambiguity and symmetry.

  • PointNet
  • Causal ML
PDF → Code →
Probabilistic Digital Twin

Robotics · Probabilistic Modeling

2024

Probabilistic Digital Twin

ROS2-integrated Dynamic Bayesian Network for real-time fault detection in Universal Robots using Unscented Kalman Filtering to track friction, damping, and wear parameters.

  • ROS2
  • UKF
  • DBN
PDF → Code →
Obstructive Sleep Apnea Detection

Machine Learning · Healthcare

2024

Obstructive Sleep Apnea Detection

Machine learning system for detecting obstructive sleep apnea events using physiological signal processing and deep learning techniques for real-time classification of respiratory disturbances.

  • Deep Learning
  • Signal Processing
Code →
Older Projects →