Categories

All (12)

Agentic coding (1)

Agriculture (1)

AI safety (1)

Benchmarking (1)

Biodiversity (1)

Camera trap (1)

Classification (1)

CLIP (1)

Clustering (1)

Computer vision (5)

Deep learning (9)

Earth science (1)

Ecology (1)

Energy (2)

Explainability (1)

GenAI (4)

Hydrology (1)

Image classification (1)

Image data (3)

Image segmentation (2)

Interpretability (1)

LLM (4)

Medical imaging (1)

ML Marathon (12)

MLM24 (3)

MLM25 (4)

MLM26 (5)

Multilingual (1)

Neuroscience (1)

NLP (5)

OCR (1)

Projects (12)

Protein language models (1)

RAG (2)

Retrieval (2)

RNN (1)

Signal processing (1)

Sustainability (2)

Text analysis (1)

Time-series (1)

U-Net (2)

Unsupervised learning (1)

UW-Madison (2)

Projects

Explore hands-on ML/AI projects from the UW-Madison community, past and present. From the annual Machine Learning Marathon – including the currently running challenges – to campus lab collaborations, these projects showcase real-world applications, lessons learned, and community insights.

Projects and Nexus go hand in hand. Nexus resources – workshops, guides, models, and datasets – help practitioners hit the ground running on new challenges. In turn, projects surface blind spots, new tools, and hard-won lessons that get contributed back to Nexus. The result is a virtuous cycle: each project makes the next one easier for everyone.

Badger Scribe: Transcribing 19th-Century Handwritten Archives on a Single GPU

Computer vision

Badger Scribe is a challenge in the 2026 Machine Learning Marathon (MLM26), organized with the UW Digital Collections Center at UW–Madison Libraries. Institutional archives…

Chris Endemann, Scott Prater, Kevin Chovanec

Badger Code: Building a Local Coding Agent on a Single GPU

Badger Code is a challenge in the 2026 Machine Learning Marathon (MLM26). Teams build the best open coding agent they can on a single GPU – no proprietary models, no giant…

WattBot 2026: Investigating AI’s Environmental Footprint with RAG

WattBot is back for the 2026 Machine Learning Marathon (MLM26) – bigger and tougher than last year. Teams build retrieval-augmented generation (RAG) systems that answer over…

Snapshot Wisconsin: Oh Deer – Predicting Population Dynamics from Trail Cameras

Computer vision

Image classification

Snapshot Wisconsin: Oh Deer is a challenge in the 2026 Machine Learning Marathon (MLM26), hosted by Ryan Bemowski. Snapshot Wisconsin has collected over one hundred million…

Fixing the Poisoned Well: Reverse-Engineering a Backdoored Streamflow Model

Interpretability

Fixing the Poisoned Well is a challenge in the 2026 Machine Learning Marathon (MLM26), created by Fraser King. A neural network trained to predict hourly streamflow at…

Clustering the BioTrove Dataset

Computer vision

Unsupervised learning

Clustering the BioTrove Dataset was featured in the 2025 Machine Learning Marathon (MLM25). This challenge asks participants to discover genus- and species-level structure…

Brain-to-Text ’25: Decoding Speech from Neural Activity

Signal processing

Brain-to-Text ’25 was featured in the 2025 Machine Learning Marathon (MLM25). This Kaggle competition challenges participants to decode intracortical neural activity during…

MaveDB: Protein Variant Effect Prediction

Protein language models

The MaveDB challenge was featured in the 2025 Machine Learning Marathon (MLM25). Participants explored protein language models and other ML methods to predict variant…

WattBot 2025: Estimating AI Emissions with RAG

WattBot was a challenge in the 2025 Machine Learning Marathon (MLM25). Teams built retrieval-augmented generation (RAG) systems to extract credible, citation-backed…

Natural Language Processing with Disaster Tweets

The Disaster Tweets challenge is a beginner-friendly NLP competition featured in the 2024 Machine Learning Marathon (MLM24). Participants build models to classify whether…

UW-Madison GI Tract Image Segmentation

Image segmentation

Computer vision

Medical imaging

The UW-Madison GI Tract Image Segmentation challenge was featured in the 2024 Machine Learning Marathon (MLM24). Originally a major Kaggle competition (1,500+ teams), this…

Infected Tomato Leaf - Vein Segmentation

Image segmentation

Computer vision

The Infected Tomato Leaf - Vein Segmentation challenge was featured in the 2024 Machine Learning Marathon (MLM24). This UW-Madison-originated Kaggle competition focuses on…