Projects

We're proud of the projects ML Collective members have worked on! Each project below is by at least one author with an MLC affiliation or acknowledges MLC research support.

If you're an MLC researcher and would like your project posted here, here's how to add it.

Project img

AfriCaption: Establishing a New Paradigm for Image Captioning in African Languages

Mardiyyah Oduwole, Prince Mireku, Fatimo Adebanjo, Oluwatosin Olajide, Mahi Aminu Aliyu, Jekaterina Novikova

In submission

ArXiv (pdf) | dataset

Project img

From Scarcity to Efficiency: Investigating the Effects of Data Augmentation on African Machine Translation

Mardiyyah Oduwole, Oluwatosin Olajide, Jamiu Suleiman, Faith Hunja, Busayo Awobade, Fatimo Adebanjo, Comfort Akanni, Chinonyelum Igwe, Peace Ododo, Promise Omoigui, Abraham Owodunni, Steven Kolawole

Published at Language Models for Underserved Communities, AAAI-2026

ArXiv (pdf)

Project img

Privacy Isn’t Free: Benchmarking the Systems Cost of Privacy-Preserving

Nnaemeka Casmir Obiefuna, Samuel Oladayo Oyeneye, Similoluwa Odunaiya, Iremide Blessing Oyelaja, Steven Kolawole

Published at ES-FoMo III: 3rd Workshop on Efficient Systems for Foundation Models, ICML 2025

Paper (pdf) | code

Project img

Flatness-Aware Regularization for Robust Generalization in Deep Neural Networks

Chisom Chibuike and Fatimo Adebanjo

Published at WiML Workshop at NeurIPS 2025

Paper (pdf)

Project img

Improving BGE-M3 Multilingual Dense Embeddings for Nigerian Low Resource Languages

Abdulmatin Omotoso, Habeeb Shopeju, Adejumobi Monjolaoluwa Joshua, Shiloh Oni

Published at WiNLP workshop, EMNLP 2025

Paper (pdf) | code

Project img

SharpXR: Structure-Aware Denoising for Pediatric Chest X-Rays

Ilerioluwakiiye Abolade, Emmanuel Idoko, Solomon Odelola, Promise Omoigui, Adetola Adebanwo, Aondana Iorumbur, Udunna Anazodo, Alessandro Crimi, Raymond Confidence

Published at MIRASOL Workshop, MICCAI 2025

ArXiv (pdf) | code

Project img

Evaluating Robustness of LLMs to Typographical Noise in Yorùbá QA

Paul Okewunmi, Favour James, Oluwadunsin Fajemila

Published at Sixth Workshop on African Natural Language Processing (AfricaNLP 2025), ACL 2025

Paper (pdf)

Project img

The NaijaVoices Dataset: Cultivating Large-Scale, High-Quality, Culturally-Rich Speech Data for African Languages

Chris Emezue, NaijaVoices Community, Busayo Awobade, Abraham Owodunni, Handel Emezue, Gloria Monica Tobechukwu Emezue, Nefertiti Nneoma Emezue, Sewade Ogun, Bunmi Akinremi, David Ifeoluwa Adelani, Chris Pal

Published at Interspeech 2025

ArXiv (pdf)

Project img

Secure and Scalable Horizontal Federated Learning for Bank Fraud Detection

Nnaemeka Obiefuna, Iremide Oyelaja, Similoluwa Odunaiya, Samuel Oyeneye

Published at Advances in Financial AI Workshop, ICLR 2025

Paper (pdf) | code

Project img

De-Identification of Sensitive Personal Data in Datasets Derived from IIT-CDIP

Stefan Larson, Nicole Cornehl Lima, Santiago Pedroza Diaz, Amogh Manoj Joshi, Siddharth Betala, Jamiu Tunde Suleiman, Yash Mathur, Kaushal Kumar Prajapati, Ramla Alakraa, Junjie Shen, Temi Okotore, Kevin Leach

Published at EMNLP 2024

Paper (pdf) | Paper page: page

Project img

Asynchronous Perception Machine For Test Time Training

Rajat Modi, Yogesh Singh Rawat

Published at NeurIPS 2024

Paper (pdf) | ArXiv | blog | code

Project img

Scaling Down Deep Learning

Sam Greydanus, Dmitry Kobak

Published at ICML 2024

Paper (pdf) | ArXiv | blog | code

Project img

What Happens When Small Is Made Smaller? Exploring the Impact of Compression on Small Data Pretrained Language Models

Busayo Awobade, Mardiyyah Oduwole, Steven Kolawole

Published at AfricaNLP workshop, ICLR 2024

ArXiv (pdf)

Project img

Extremely Simple Activation Shaping for Out-of-Distribution Detection

Andrija Djurisic, Nebojsa Bozanic, Arjun Ashok, Rosanne Liu

Published at ICLR 2023

Paper (pdf) | ArXiv | blog | code | video

Project img

Sign-to-Speech Model for Sign Language Understanding: A Case Study of Nigerian Sign Language

Steven Kolawole, Opeyemi Osakuade, Nayan Saxena, Babatunde K. Olorisade

Published at IJCAI 2022 (initially presented at ML4D Workshop, NeurIPS 2021)

Paper (pdf) | ArXiv | blog | code | video

Project img

Estimating Example Difficulty Using Variance of Gradients

Chirag Agarwal, Daniel D'souza, Sara Hooker

Published at CVPR 2022

Paper (pdf) | ArXiv | blog | code

Project img

NeuralArTS: Structuring Neural Architecture Search with Type Theory (Student Abstract)

Robert Wu, Nayan Saxena , Rohan Jain

Published at AAAI 2022

Paper (pdf) | ArXiv | code

Project img

Towards One Shot Search Space Poisoning in Neural Architecture Search (Student Abstract)

Nayan Saxena, Robert Wu , Rohan Jain

Published at AAAI 2022

Paper (pdf) | ArXiv | code

Project img

Language Models are Few-shot Multilingual Learners

Genta Indra Winata, Andrea Madotto, Zhaojiang Lin, Rosanne Liu, Jason Yosinski, Pascale Fung

Published at MRL Workshop, EMNLP 2021

Paper (pdf) | ArXiv | code | video

Project img

Deep Synoptic Monte Carlo Planning in Reconnaissance Blind Chess

Gregory Clark

Published at NeurIPS 2021

Paper (pdf) | ArXiv

Project img

When does loss-based prioritization fail?

Niel Teng Hu, Xinyu Hu, Rosanne Liu, Sara Hooker, Jason Yosinski

Published at SubSetML Workshop, ICML 2021

Paper (pdf) | ArXiv

Project img

A Tale Of Two Long Tails

Daniel D'souza, Zach Nussbaum, Chirag Agarwal, Sara Hooker

Published at UDL Workshop, ICML 2021

Paper (pdf) | ArXiv | code

Project img

Multi-layer Hebbian networks with modern deep learning frameworks

Thomas Miconi

ArXiv (pdf) | code

Project img

Supermasks in Superposition

Mitchell Wortsman, Vivek Ramanujan, Rosanne Liu, Aniruddha Kembhavi, Mohammad Rastegari, Jason Yosinski, Ali Farhadi

Published at NeurIPS 2020

Paper (pdf) | ArXiv | blog | code

Project img

Estimating Q(s,s’) with Deep Deterministic Dynamics Gradients

Ashley D. Edwards, Himanshu Sahni, Rosanne Liu, Jane Hung, Ankit Jain, Rui Wang, Adrien Ecoffet, Thomas Miconi, Charles Isbell, Jason Yosinski

Published at ICML 2020

Paper (pdf) | code | video

Project img

Plug and Play Language Models: a Simple Approach to Controlled Text Generation

Sumanth Dathathri, Andrea Madotto, Janice Lan, Jane Hung, Eric Frank, Piero Molino, Jason Yosinski, Rosanne Liu

Published at ICLR 2020

Paper (pdf) | ArXiv | blog | code | video | Colab

Project img

LCA: Loss Change Allocation for Neural Network Training

Janice Lan, Rosanne Liu, Hattie Zhou, Jason Yosinski

Published at NeurIPS 2019

Paper (pdf) | ArXiv | blog | code | video

Project img

Hamiltonian Neural Networks

Sam Greydanus, Misko Dzamba, and Jason Yosinski

Published at NeurIPS 2019

Paper (pdf) | ArXiv | blog | code

Project img

Deconstructing Lottery Tickets: Zeros, Signs, and the Supermask

Hattie Zhou, Janice Lan, Rosanne Liu, Jason Yosinski

Published at NeurIPS 2019

Paper (pdf) | ArXiv | blog | code

Project img

Metropolis-Hastings Generative Adversarial Networks

Ryan Turner, Jane Hung, Eric Frank, Yunus Saatci, and Jason Yosinski

Published at ICML 2019

Paper (pdf) | ArXiv | blog | code

Project img

Faster Neural Networks Straight from JPEG

Lionel Gueguen, Alex Sergeev, Ben Kadlec, Rosanne Liu, Jason Yosinski

Published at NeurIPS 2018

Paper (pdf) | blog | code

Project img

An Intriguing Failing of Convolutional Neural Networks and the CoordConv Solution

Rosanne Liu, Joel Lehman, Piero Molino, Felipe Petroski Such, Eric Frank, Alex Sergeev, Jason Yosinski

Published at NeurIPS 2018

Paper (pdf) | ArXiv | blog | code | video

Project img

Measuring the intrinsic dimension of objective landscapes

Chunyuan Li, Heerad Farkhoor, Rosanne Liu, Jason Yosinski

Published at ICLR 2018

Paper (pdf) | ArXiv | blog | code | video