descriptive claim
The speaker says robotics companies pursue different model approaches, including adapting video world models and adapting vision-language models into vision-language-action models.
Jason Ma · Dyna-2: General Purpose Physical Agents with Hour-Long Autonomy — Jason Ma, Dyna Robotics · 13 Oct 2026
In their words
The transcript segments this claim was taken from
“also getting to adapt video world models.”
“There are also companies building vision language action model.”
“So that's like taking vision language models and adapting them to robotics.”54:23Report a misattribution
0.90how strongly it was put, not whether it is true
0.75importance to the conversation
0.97confidence the claim was read correctly