Carlos

carlos-async

·

AI & ML interests

None yet

Recent Activity

reacted to ErenAta00's post with 🚀 about 1 hour ago

Maverick 1.1 is out. When we released the first version, the feedback was clear: real people do not give one clean command at a time. They change their minds, they point and say "put that on the shelf", they ask for a lamp that is in another room, and sometimes the one speaking is a remote expert helping someone on site. 1.1 is built around exactly that. - Say "no, the other one" and it undoes the last action and repeats it on the other object. If the effect can't be undone, like a button that was already pressed, it tells you. - It sees what people are looking at or pointing at, and who is speaking. - It finds objects in other rooms, goes there and acts, or asks which one if there are two. - It follows a short plan in one sentence: "open the cabinet, put the book and the alarm clock in it, then close it". On test sets we sealed before training and ran once, the new abilities score 93 to 100%, where 1.0 scores 33 to 87%. On sentences written by people (the ALFRED set) the two versions are level, at 83.2% and 83.8%. Where it still falls short: in unfamiliar situations it tends to act when it should ask, and a remote speaker can act in the scene with no permission check, so your app has to enforce that. The article goes through the rest. Same 4B model and licence (Apache-2.0), the same 11 tools plus `undo`, still offline on a 4 GB laptop GPU. The Unity package update for the new scene format is not released yet; in the original format 1.1 is a drop-in replacement for 1.0. Model: https://huggingface.co/ErenAta00/Maverick-4B-Unity-XR-Agent-1.1 Article, with charts and a demo video: https://huggingface.co/blog/ErenAta00/maverick-1-1-undo-pointing-other-rooms Built at the Extended Reality Laboratory (XRLab), Manisa Celal Bayar University: https://huggingface.co/ExtendedRealityLabMCBU

reacted to ErenAta00's post with 🔥 about 1 hour ago

Maverick 1.1 is out. When we released the first version, the feedback was clear: real people do not give one clean command at a time. They change their minds, they point and say "put that on the shelf", they ask for a lamp that is in another room, and sometimes the one speaking is a remote expert helping someone on site. 1.1 is built around exactly that. - Say "no, the other one" and it undoes the last action and repeats it on the other object. If the effect can't be undone, like a button that was already pressed, it tells you. - It sees what people are looking at or pointing at, and who is speaking. - It finds objects in other rooms, goes there and acts, or asks which one if there are two. - It follows a short plan in one sentence: "open the cabinet, put the book and the alarm clock in it, then close it". On test sets we sealed before training and ran once, the new abilities score 93 to 100%, where 1.0 scores 33 to 87%. On sentences written by people (the ALFRED set) the two versions are level, at 83.2% and 83.8%. Where it still falls short: in unfamiliar situations it tends to act when it should ask, and a remote speaker can act in the scene with no permission check, so your app has to enforce that. The article goes through the rest. Same 4B model and licence (Apache-2.0), the same 11 tools plus `undo`, still offline on a 4 GB laptop GPU. The Unity package update for the new scene format is not released yet; in the original format 1.1 is a drop-in replacement for 1.0. Model: https://huggingface.co/ErenAta00/Maverick-4B-Unity-XR-Agent-1.1 Article, with charts and a demo video: https://huggingface.co/blog/ErenAta00/maverick-1-1-undo-pointing-other-rooms Built at the Extended Reality Laboratory (XRLab), Manisa Celal Bayar University: https://huggingface.co/ExtendedRealityLabMCBU

new activity about 1 hour ago

XHToken/Spark-X2.6-4B:is it possible to add vision?

View all activity

Organizations

None yet

carlos-async 's datasets

None public yet