My research explores efficiency problems in ML with a focus on making AI more accessible.
The work spans three main areas: developing efficient inference methods, addressing resource constraints
in multilingual settings, and building practical applications for social impact.
ML Efficiency & Systems
Duncan Soiffer, Steven Kolawole, Virginia Smith
ICML 2025 (ES-FOMO)
Extends agreement-based cascading to open-ended generation tasks, enabling efficient routing
for language model queries without requiring additional training data or model modifications.
Nnaemeka Obiefuna, Samuel Oyeneye, Similoluwa Odunaiya, Iremide Oyelaja, Steven Kolawole
ICML 2025 (ES-FOMO)
Comprehensive benchmarking study examining the computational overhead of privacy-preserving techniques
in machine learning, conducted primarily with URM students from ML Collective.
Steven Kolawole, Keshav Santhanam, Virginia Smith, Pratiksha Thaker
NeurIPS 2024 (AFM)
Introduces PARALLELPROMPT, a benchmark revealing that 10% of natural user queries contain latent parallelism.
Demonstrates semantic decomposition methods achieving up to 5× speedups without hardware modifications.
Steven Kolawole*, Don Dennis*, Ameet Talwalkar, Virginia Smith
Under Review, 2025
Develops a training-free cascading framework using ensemble agreement as a confidence signal.
Achieves 2-25× cost reductions while maintaining or improving accuracy across diverse tasks.
Steven Kolawole*, Lucio Dery*, Jean-François Kagy, Virginia Smith, Graham Neubig, Ameet Talwalkar
Under Review, 2025
Presents Bonsai, a forward-pass-only structured pruning method that outperforms gradient-based approaches
while using 3× less memory, making model compression accessible on everyday hardware.
Resource-Constrained NLP
Busayo Awobade*, Mardiyyah Oduwole*, Steven Kolawole*
ICLR 2024 (AfricaNLP)
Investigates compression techniques on AfriBERTa, demonstrating that pruning, knowledge distillation,
and quantization remain effective in the "low-resource double-bind" of small-data language models.
Colin Leong, ..., Steven Kolawole, et al.
ICLR 2023 (AfricaNLP)
Explores efficient training methods for African language processing under computational constraints,
addressing the challenge of limited data and limited compute resources simultaneously.
Applied ML & Social Good
Nahid Alam*, Steven Kolawole*, Simardeep Sethi*, Nishant Bansali, Karina Nguyen
arXiv preprint, 2023
Comprehensive survey examining how Vision Transformers can be optimized for mobile deployment,
analyzing architecture modifications and efficiency techniques for resource-constrained environments.
Steven Kolawole, Opeyemi Osakuade, Nayan Saxena, Babatunde Kazeem Olorisade
IJCAI 2022 (AI for Social Good Track)
Develops a sign-to-speech system for Nigerian Sign Language to bridge communication gaps.
This work earned the national AI Champion award from the Nigeria Computer Society, demonstrating practical AI for social impact.
* denotes equal contribution
This list includes peer-reviewed publications, workshop papers, and preprints.
For the most up-to-date list with citation counts, please visit my Google Scholar profile.