ML+Coffee: GB10/DGX-Spark, "OpenScholar" RAG, and more

ML+Coffee offers a supportive and casual environment to discuss ongoing ML/AI projects and share knowledge & tools across campus. Whether you're looking for advice on applying ML/AI to your data, hoping to demo a favorite tool, or interested in discussing a paper, ML+Coffee offers the perfect space. The majority of our attendees are applied practitioners from diverse fields, not AI/ML purists looking to critique. Coffee provided ☕ to keep the ideas flowing, courtesy of our sponsors.

Register: https://forms.gle/dHavKeyBTt5TgXKC8

Feb 18 Schedule

• 9-9:30 (Intros & Resource Sharing): The first 30-minutes are typically focused on introductions and causal share-outs about new ML/AI tools or resources folks are using.
• 9:30-10:00am (Dell Pro Max GB10 and related hardware): Learn about the capabilities and limitations of the Dell Pro Max GB10 (AI development workspace), and share any personal use-cases (current or future-looking). With 128 GB memory shared between the CPU and GPU, this little machine is capable of supporting AI workloads in roughly the 1-70B parameter range (4-bit). While it's slower than some server-tier GPUs, it can be a convenient option for 24/7 development access before scaling things up.
• 10-11am (RAG Paper Discussion): Synthesizing scientific literature with retrieval-augmented language models (https://www.nature.com/articles/s41586-025-10072-4). Please email endemann@wisc.edu if you'd like to take the lead on this discussion.

Have a demo, paper, or ongoing project to discuss? Join the discussion queue! forms.gle/F5LYqnY5TMiZrzXW6.  No formal presentation is required—this event prioritizes open dialogue and casual discussion over formal presentations. If helpful, you're welcome to bring a couple of slides (e.g., to share data, methods, or results). Many participants just bring a few key points or a rough overview of their work, and the conversation flows naturally from there.