Paper Reading: Weight Space Programming
Details
Join us for a discussion on latest advancements in machine learning with : "Weight Space programming" presented by Logan. Weight Space programming is using an llm to directly edits weights without finetuning or training. This approach was popularized from a blog post from MIT CSAIL recently.
([https://rikiyat.github.io/blog/weight-space-programming/)](https://rikiyat.github.io/blog/weight-space-programming/)), https://github.com/RikiyaT/lm_understand-logs)
Since then others have suggested that frontier llms may not necessarily be needed for this and that some of this can also be done by linear programming (https://nathan.rs/posts/weight-space-lp/
https://github.com/nathanrs/weight-space-lp).
Additional related work:
https://github.com/suayptalha/wsr
https://www.alphaxiv.org/pdf/2611.weight-space-reading-language-models
https://wsp-scope.github.io/
https://www.alphaxiv.org/pdf/2611.09382
Silicon Valley Generative AI has two meeting formats.
1. Paper Reading - Every second week we meet to discuss machine learning papers. This is a collaboration between Silicon Valley Generative AI and Boulder Data Science.
2. Talks - Once a month we meet to have someone present on a topic related to generative AI. Speakers can range from industry leaders, researchers, startup founders, subject matter experts and those with an interest in a topic and would like to share. Topics vary from technical to business focused. They can be on how the latest in generative models work and how they can be used, applications and adoption of generative AI, demos of projects and startup pitches or legal and ethical topics. The talks are meant to be inclusive and for a more general audience compared to the paper readings.
If you would like to be a speaker please contact:
Matt White
