←back to thread

LLaVA-O1: Let Vision Language Models Reason Step-by-Step

(arxiv.org)
176 points lnyan | 5 comments | 18 Nov 24 09:44 UTC | HN request time: 0.813s | source
1. resource_waste ◴[18 Nov 24 18:55 UTC] No.42175636[source]▶
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.

replies(3): >>42175720 #>>42180165 #>>42183428 #
2. abdussamit ◴[18 Nov 24 19:02 UTC] No.42175720[source]▶
This is quite an interesting problem. Hope you find a solution to this, and wish I had the right knowledge to work on it
3. heyitsguay ◴[19 Nov 24 04:49 UTC] No.42180165[source]▶
What is your training data? Does it have both vision and descriptive components?
replies(1): >>42182122 #
4. resource_waste ◴[19 Nov 24 10:59 UTC] No.42182122[source]▶
yes
5. htrp ◴[19 Nov 24 13:53 UTC] No.42183428[source]▶
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).