Anastasis Germanidis argues that interactive models should produce equally realistic outcomes for different actions. He sees this as an important gap between video models and world models.
支持这项说法
原始摘录
if you have an interactive model, you want it to be able to generate counterfactuals. Like, if I take this action versus this action, you want it to generate equally realistic outcomes. so that’s, I think, the big gap between video models and world models
Anastasis Germanidis says creatives, artists and marketers tend to rely less on arena scores and can compare outputs from different models visually.
支持这项说法
原始摘录
I think people, generally creatives and artists and marketers, other like people that are using our platforms, I think rely less on, arena scores. And it’s, it’s just so easy to, generate with a bunch of different models and then compare the results visually.
Making models available to artists led Runway toward research
Anastasis Germanidis describes Runway’s early aim of making open-source models easier for artists to use. He says the team soon realized it needed an internal research organization.
支持这项说法
原始摘录
those models are too difficult to use if you’re not a machine learning engineer. Like, what happens when you give them to artists? Very quickly, we realized we needed to build a research org, inside of Runway
nafyi.