marimo

• 
  marimo marimo.io · Feb 5
  Just shipped: marimo v0.19.8! Like all our releases, this one is packed. Highlights: Serve a gallery of notebooks with `marimo run`. Gallery cards can be customized with OpenGraph metadata, letting you showcase your work with custom thumbnails. (1/n)
  
  1

  Repost Quote post

  View on BlueskyCopy Bluesky URLCopy post URLTranslate postDownload imageShow all post labels
• 
  marimo marimo.io · Feb 5
  Customize gallery cards with OpenGraph metadata, letting you express yourself with rich thumbnails and descriptions
  
  1

  Repost Quote post

  View on BlueskyCopy Bluesky URLCopy post URLTranslate postDownload imageShow all post labels
• 
  marimo marimo.io · Feb 5
  Multi-modal AI – you can now attach images when using "Generate with AI". Go from whiteboard scrawlings to Tikz diagrams instantly
  
  1

  Repost Quote post

  View on BlueskyCopy Bluesky URLCopy post URLTranslate postDownload imageShow all post labels
• View full thread
  
  marimo marimo.io · Feb 5
  Release notes: github.com/marimo-team...
  

  Release 0.19.8 · marimo-team/marimo

  This release introduces notebook galleries with OpenGraph previews, along with anywidget improvements, AI enhancements, and many bug fixes. ⭐️ Highlights Serve a gallery of notebooks You can now se...

  github.com
  Repost Quote post

  View on BlueskyCopy Bluesky URLCopy post URLTranslate postShow all post labels
• 
  marimo marimo.io · Feb 4
  GDPO is a very simple idea. But you might not know that from reading the paper! Watch our latest video to see how to go from research papers to interactive explainer notebooks — using LLMs to make widgets that bring equations to life. www.youtube.com/watch?v=Ybz...
  

  From alphaXiv to interactive Python notebook

  There's a new hobby for ML people: turning papers into elaborate notebooks. Widgets and all! This video explores one example of this indepth. 00:00 Alphaxiv ...

  youtube.com
  1

  Repost Quote post

  View on BlueskyCopy Bluesky URLCopy post URLTranslate postShow all post labels
• 
  marimo marimo.io · Feb 4
  Notebook: molab.marimo.io/notebooks/n...
  

  GDPO vs GRPO - molab

  marimo notebook by Vincent in marimo team

  marimo.io
  1

  Repost Quote post

  View on BlueskyCopy Bluesky URLCopy post URLTranslate postShow all post labels
• 
  marimo marimo.io · Feb 4
  For the best reading experience, check out the paper on @askalphaxiv! www.alphaxiv.org/abs/2601.05242
  

  GDPO: Group reward-Decoupled Normalization Policy Optimization for Multi-reward RL Optimization

  View recent discussion. Abstract: As language models become increasingly capable, users expect them to provide not only accurate responses but also behaviors aligned with diverse human preferences across a variety of scenarios. To achieve this, Reinforcement learning (RL) pipelines have begun incorporating multiple rewards, each capturing a distinct preference, to guide models toward these desired behaviors. However, recent work has defaulted to apply Group Relative Policy Optimization (GRPO) under multi-reward setting without examining its suitability. In this paper, we demonstrate that directly applying GRPO to normalize distinct rollout reward combinations causes them to collapse into identical advantage values, reducing the resolution of the training signal and resulting in suboptimal convergence and, in some cases, early training failure. We then introduce Group reward-Decoupled Normalization Policy Optimization (GDPO), a new policy optimization method to resolve these issues by d

  alphaxiv.org
  Repost Quote post

  View on BlueskyCopy Bluesky URLCopy post URLTranslate postShow all post labels
• 
  marimo marimo.io · Feb 2
  marimo's pure-Python file format makes it easy for agents to author notebooks. Watch this video to learn how pairing marimo with a fast model — like @cursor_ai's Conductor — can rapidly accelerate interactive data exploration and machine learning work. youtu.be/jGMf3eCXZZA
  Repost Quote post

  View on BlueskyCopy Bluesky URLCopy post URLTranslate postShow all post labels