/AI19h ago

Žiga Kovačič releases MPMWorlds to benchmark how vision-language and diffusion models predict physical dynamics from video clips

The benchmark utilizes 2D Material Point Method simulations.

--0--
Original posts
Quote posts
Žiga Kovačič@zzigakovacic

How well can a model watch a short video of some physical dynamics and actually predict what happens next?

Introducing MPMWorlds: a new dataset and benchmark to evaluate how well models can reconstruct and extrapolate physical dynamics from video.

https://zzigak.github.io/mpmworlds/

🧵👇 (1/n)

10:55 AM · Jun 3, 2026 · 9.3K Views
Sentiment
Sentiment building, check back later.
Cluster Engagement
-
Views
-
Comments
-
Reposts
-
Bookmarks
Expand data
Posts from X
Most Activity
Most ActivityTimeline
VIEWS2.2KBOOKMARKS4LIKES11RETWEETS2REPLIES5
Ofir Press@OfirPress

Really creative work comparing VLMs and diffusion models on predicting the future of physical simulations!

Žiga Kovačič@zzigakovacic

How well can a model watch a short video of some physical dynamics and actually predict what happens next?

Introducing MPMWorlds: a new dataset and benchmark to evaluate how well models can reconstruct and extrapolate physical dynamics from video.

https://zzigak.github.io/mpmworlds/

🧵👇 (1/n)

16hViews 2.2KLikes 11Bookmarks 4