News for hackers. Stuff that matters.
Re:LLaVA-O1: Let Vision Language Models Reason Step-by-Step by resource_waste on Monday November 18, 2024 @01:55PM (#42175636)
What are options to fine tune?

For instance, if I have a CAD model of a screw fastened to a wall, can I teach it that its a screw fastened to a wall?

I have years worth of potential training data.

Consider this a multi-million dollar problem.

Re:LLaVA-O1: Let Vision Language Models Reason Step-by-Step by abdussamit on Monday November 18, 2024 @02:02PM (#42175720)
This is quite an interesting problem. Hope you find a solution to this, and wish I had the right knowledge to work on it
Re:LLaVA-O1: Let Vision Language Models Reason Step-by-Step by heyitsguay on Monday November 18, 2024 @11:49PM (#42180165)
What is your training data? Does it have both vision and descriptive components?
Re:LLaVA-O1: Let Vision Language Models Reason Step-by-Step by resource_waste on Tuesday November 19, 2024 @05:59AM (#42182122)
yes
Re:LLaVA-O1: Let Vision Language Models Reason Step-by-Step by htrp on Tuesday November 19, 2024 @08:53AM (#42183428)
There are numerous companies in the construction space working on these types of problems. I'm sure some of them will reach out to you (if they haven't already).