Ph.D. candidate at Brown University 🐻I am currently working towards my Ph.D. at Brown University in the Department of Computer Science where I am advised by Dr. Stephen Bach in the BATS research group and AI ‘superlab’. I am primarily interested in developing novel solutions for mining and learning from large, real-world datasets while also exploiting new methods for harvesting and labeling data. Lately, I have been interested in solutions for datasets in the scientific domain.
My current research has been largely in collaboration with Dr. Jonathan Pober at Brown’s Department of Physics on SWIFT - Spectrum and Wireless Innovation enabled by Future Technologies. SWIFT is an NSF-funded effort to develop machine learning applications for the detection and removal of radio frequency interference (RFI) from 21cm cosmology data. The challenge presented by this task is the sheer volume of unlabeled data that is produced by the data sources (telescopes), prompting the introduction of weak supervision to harvest RFI detection rules that produce meaningful training datasets for anomaly detection models.
Before starting my graduate studies at Brown, I graduated with my B.Sc. in Computer Science from RIT. I was advised by and worked on data science and machine learning applications to general aviation flight data, particularly for the FAA-funded National General Aviation Flight Information Database (NGAFID)
Action required
Problem: The current root path of this site is "baseurl ("/people/alabella") configured in _config.yml.
Solution: Please set the
baseurl in _config.yml to "Education
-
Brown UniversityPh.D., Computer Science (in progress)Sep. 2023 - present
-
Brown UniversitySc.M., Computer ScienceSep. 2023 - May 2025
-
Rochester Institute of TechnologyB.Sc. (honors), Computer ScienceSep. 2018 - May 2023
Selected Publications (view all )
![[Tiny Paper] Toward Pixel-Grounded World Models for Powered Descent: A Rocket Landing Benchmark and Expert Baseline](/people/alabella/assets/images/covers/2026-rocket-landing-fig1.jpg)
[Tiny Paper] Toward Pixel-Grounded World Models for Powered Descent: A Rocket Landing Benchmark and Expert Baseline
Charles Duong, Aviral Vaidya, Aditya Iyer, Lucas Maes, Aidan LaBella, Randall Balestriero
ICLR 2026 Workshop on World Models: Understanding, Modelling and Scaling 2026
Introduces RocketLanding, a powered-descent benchmark for studying pixel-grounded world models under realistic actuation and touchdown constraints, with an analytical expert baseline for offline trajectory generation.
[Tiny Paper] Toward Pixel-Grounded World Models for Powered Descent: A Rocket Landing Benchmark and Expert Baseline
Charles Duong, Aviral Vaidya, Aditya Iyer, Lucas Maes, Aidan LaBella, Randall Balestriero
ICLR 2026 Workshop on World Models: Understanding, Modelling and Scaling 2026
Introduces RocketLanding, a powered-descent benchmark for studying pixel-grounded world models under realistic actuation and touchdown constraints, with an analytical expert baseline for offline trajectory generation.
GATS: A Time-Series Dataset for Addressing General Aviation Flight Safety
Aidan LaBella, Charles Duong, Pak Iong Long, Nathan DePiero, Aditya Iyer, Elise Carman, Randall Balestriero, Travis Desell
1st ICML Workshop on Foundation Models for Structured Data 2026
Releases GATS, a time-series dataset of general aviation flights from the NGAFID, and benchmarks aircraft classification and missing-data reconstruction tasks for aviation safety research.
GATS: A Time-Series Dataset for Addressing General Aviation Flight Safety
Aidan LaBella, Charles Duong, Pak Iong Long, Nathan DePiero, Aditya Iyer, Elise Carman, Randall Balestriero, Travis Desell
1st ICML Workshop on Foundation Models for Structured Data 2026
Releases GATS, a time-series dataset of general aviation flights from the NGAFID, and benchmarks aircraft classification and missing-data reconstruction tasks for aviation safety research.
Predictive Maintenance for General Aviation Using Convolutional Transformers
Hong Yang, Aidan LaBella, Travis Desell
Proceedings of the AAAI Conference on Artificial Intelligence 2022
Introduces the NGAFID Maintenance Classification dataset and a convolutional multi-headed self-attention model for classifying multivariate flight time series for predictive aircraft maintenance.
Predictive Maintenance for General Aviation Using Convolutional Transformers
Hong Yang, Aidan LaBella, Travis Desell
Proceedings of the AAAI Conference on Artificial Intelligence 2022
Introduces the NGAFID Maintenance Classification dataset and a convolutional multi-headed self-attention model for classifying multivariate flight time series for predictive aircraft maintenance.
Optimized Flight Safety Event Detection in the National General Aviation Flight Information Database
Aidan LaBella, Joshua A Karns, Farhad Akhbardeh, Travis Desell, Andrew J Walton, Zechariah Morgan, Brandon Wild, Mark Dusenbury
Proceedings of the 37th ACM/SIGAPP Symposium on Applied Computing 2022
Redesigns NGAFID flight data ingestion and safety-event computation, substantially reducing processing cost while adding advanced event calculations for proximity, glide path deviation, stall, and loss of control.
Optimized Flight Safety Event Detection in the National General Aviation Flight Information Database
Aidan LaBella, Joshua A Karns, Farhad Akhbardeh, Travis Desell, Andrew J Walton, Zechariah Morgan, Brandon Wild, Mark Dusenbury
Proceedings of the 37th ACM/SIGAPP Symposium on Applied Computing 2022
Redesigns NGAFID flight data ingestion and safety-event computation, substantially reducing processing cost while adding advanced event calculations for proximity, glide path deviation, stall, and loss of control.