Entries matching “grounding”

Andrew Brown's three-hour freeCodeCamp course on building apps and agent workflows with Muse Spark and the Muse Code CLI, ending in a full-stack Go/SQLite/Docker build.

Lightweight LoRA that makes Muse Glimmer 30B output a target element's bounding box directly from a screenshot and instruction, for computer-use agents.

Fei Xia

@xf1280

Fun visually-grounded 3d visualization with Muse Spark - by asking the model to generate a 3d visualization of how much each component cost on a xbox 360 motherboard (and put the bar on the component).

Derya Unutmaz, MD

@DeryaTR_

Here is a crazy Jev @typesafeai example that I’m betting nobody has thought about: I asked @Muse from @Meta to use Jev to select the top 100 unanswered questions in immunology from 10,000 literature-grounded candidates. A few minutes later, it came back with some of the best

Demo of a QLoRA adapter for Muse Glimmer 30B that points at UI elements in web screenshots, returning a click point from an instruction like "filter by MATEIN brand".

Simon Willison

@simonw

Pelicans for Meta's new Muse Spark models - plus I did a bit of a deep dive into the Code Interpreter and fascinating "container.visual_grounding" tools in their meta.ai chat UI simonwillison.net/2026/Apr/8/mus…

Deedy

@deedydas

The coolest thing Meta AI's Muse Spark can do by far is counting objects! As you can tell, it's far from perfect. They call it "visual grounding" and it can count objects and do bounding boxes. I've been playing with the new model and here's what I think so far: Good stuff: –

QLoRA adapter that teaches Muse Glimmer 30B to return click points on web screenshots from instructions, trained on the MolmoWeb dataset.

Michelle Ko

@michelleekokoko

dragging our friends to hot yoga every sunday just for me to have slightly better yoga form than @andrewztan the model is natively multimodal, which allows visual grounding + coding to make interactive UIs like this! ai.meta.com/blog/introduci…

merve

@mervenoyann

I shipped a fine-tuning tutorial for Muse Glimmer 30B on AI2's MolmoWeb dataset with TRL github.com/merveenoyan/sm… > but merve, this model is sota on ScreenSpot-Pro? yes, but it doesn't work well with ambiguous prompts of MolmoWeb that are close to how you interact with computer,

Matt Deitke

@mattdeitke

The multimodal grounding abilities combined with web development in Muse Spark are so good! 🎨 Prompt: <image of dogs> Make a website where you point to each of the dogs and say their breed.

@jeperkins4

@jeperkins4

A zero-dependency Ruby client for Meta's Model API focused on the Responses API: reasoning replay across tool loops, previous_response_id state, web_search grounding and typed errors with retries.