☆ Yσɠƚԋσʂ ☆@lemmy.ml to Technology@lemmy.mlEnglish · 10 days agoHuman-like object concept representations emerge naturally in multimodal large language modelswww.nature.comexternal-linkmessage-square21fedilinkarrow-up114arrow-down13
arrow-up111arrow-down1external-linkHuman-like object concept representations emerge naturally in multimodal large language modelswww.nature.com☆ Yσɠƚԋσʂ ☆@lemmy.ml to Technology@lemmy.mlEnglish · 10 days agomessage-square21fedilink
minus-squareMCasq_qsaCJ_234@lemmy.ziplinkfedilinkEnglisharrow-up1·10 days agoIn your opinion, is this a good thing, a bad thing, or is it just a curiosity that LLMs currently have?
minus-square☆ Yσɠƚԋσʂ ☆@lemmy.mlOPlinkfedilinkarrow-up3arrow-down1·10 days agoIt’s a good thing in a sense that it means the models are creating stable representations of objects across modalities. It means that there is potential for extending LLM approach to building actual world models in the future.
In your opinion, is this a good thing, a bad thing, or is it just a curiosity that LLMs currently have?
It’s a good thing in a sense that it means the models are creating stable representations of objects across modalities. It means that there is potential for extending LLM approach to building actual world models in the future.