Nicholas C. Ikechukwu

665 Commonwealth Ave., Boston, MA, USA

ncholas [at] bu [dot] edu

I am a CS PhD student at Boston University, where I have the rare good fortune of being co-advised by Profs. Bryan Plummer and Deepti Ghadiyaram. My research interests sit at the crossroads of Computer Vision, Machine Learning, and Robotics. This intersection continually shapes both my work and my curiosity. I study query-based vision models and long-term visual perception for autonomous systems, driven by a simple but ambitious question: how can machines learn not just to visually perceive, but to remember, adapt, and act over time? With a background in Computer Engineering and prior industry experience building AI-driven software across diverse applications, I enjoy bringing a practical lens to theoretically grounded research.

As a Teaching Fellow at BU, I also enjoy the rare privilege of talking about what I love, supporting and guiding students through AI, Machine Learning, and Reinforcement Learning while discovering that teaching often reveals insights research alone cannot.

Outside the lab and classroom, I unwind at the piano, experiment with delightfully unpolished art, explore the city by bike, and find clarity at the gym.

News

Jan 20, 2026	Presented my first talk at the AIR Seminar at BU!
Dec 21, 2025	Completed two semesters as a Teaching Fellow for CS440 (AI Course)
May 22, 2025	Co-authored my second paper! Read (online) here: ArXiv:

Selected publications

DORI

Right side up? disentangling orientation understanding in mllms with fine-grained multi-axis perception tasks

Keanu Nichols, Nazia Tasnim, Yuting Yan, Nicholas Ikechukwu, and 3 more authors

arXiv preprint arXiv:2505.21649, 2025

Abs

Object orientation understanding represents a fundamental challenge in visual perception critical for applications like robotic manipulation and augmented reality. Current vision-language benchmarks fail to isolate this capability, often conflating it with positional relationships and general scene understanding. We introduce DORI (Discriminative Orientation Reasoning Intelligence), a comprehensive benchmark establishing object orientation perception as a primary evaluation target. DORI assesses four dimensions of orientation comprehension: frontal alignment, rotational transformations, relative directional relationships, and canonical orientation understanding. Through carefully curated tasks from 11 datasets spanning 67 object categories across synthetic and real-world scenarios, DORI provides insights on how multi-modal systems understand object orientations. Our evaluation of 15 state-of-the-art vision-language models reveals critical limitations: even the best models achieve only 54.2% accuracy on coarse tasks and 33.0% on granular orientation judgments, with performance deteriorating for tasks requiring reference frame shifts or compound rotations. These findings demonstrate the need for dedicated orientation representation mechanisms, as models show systematic inability to perform precise angular estimations, track orientation changes across viewpoints, and understand compound rotations - suggesting limitations in their internal 3D spatial representations. As the first diagnostic framework specifically designed for orientation awareness in multimodal systems, DORI offers implications for improving robotic control, 3D scene reconstruction, and human-AI interaction in physical environments