Machine Learning Marathon: Team Mixer

The Team Mixer is for registered MLM26 participants. Apply now and claim your ticket to attend. A few seats are still open, and there is still time to get in before Wednesday. Applications are per-individual, not per-team. If you already know who you want to work with, the application asks, and we'll try to keep you together (assuming all teammates apply). We'll admit about 12 people per challenge. Teams of 3-6 form at the Team Mixer on 9/2, and your ticket comes with a challenge assignment plus a private Slack channel if you want to start coordinating early.

About: The 4th annual Machine Learning Marathon (MLM26) is a 13-week AI/ML hackathon (Sept 9 - Dec 9) where teams of 3-6 tackle real-world Challenges, share tools and insights, and build skills along the way. Weekly sessions bring workshops, team shareouts, and advisors. Participants also get cloud credits (with training) and access to hosted models. We encourage diverse backgrounds and experience levels; this isn't just for computer scientists, though some challenges may require more expertise than others. Researchers and graduate students are especially encouraged to apply. Open to UW-Madison affiliates with a NetID (students, staff, faculty, etc.).

Once you have your ticket, join us Wednesday, September 2, 4:30-6:00pm in the Discovery Building Atrium (330 N Orchard St) to meet the other people working your challenge, pick up your badge, and settle your team before the Sept 9 kickoff. Light refreshments provided.

This year's challenges are:

• Badger Code - Building a coding agent on relatively small open-weight models, scored on Terminal-Bench
• Badger Scribe - Transcribing 19th-century archival manuscripts with vision-language models and OCR/HTR
• Brain Decoding - Predicting perceived imagery from EEG recordings. Kaggle page coming soon. Watch the Challenge Showcase recording to hear from the organizer.
• Fixing the Poisoned Well - Auditing a tampered neural network for planted behavior and repairing it, using mechanistic interpretability
• Snapshot WI - Oh Deer - Estimating deer populations from trail-camera imagery
• WattBot 2026 - AI+Sustainability literature review and Q&A with retrieval augmented generation (RAG)