Physical World Models
WorldString
warning
The Missing Link
Video Gen
Pixels in → Pixels out
Identity ✗ Dynamics ✗
Identity ✗ Dynamics ✗
VS
Scene Recon
Geometry → Geometry
Dynamics ✗ States ✗
Dynamics ✗ States ✗
Missing: Actionable Object State
No primitive to model "how objects change" based on intrinsic properties.
No primitive to model "how objects change" based on intrinsic properties.
hub
WorldString: Object as State Manifold
Treats objects as continuous state spaces (manifolds) learned from observation.
input
Encoder
Obs → Latent Code
→
gradient
Latent Space
(State Manifold / DNA)
→
view_in_ar
Decoder
Code → Geometry
psychology
Core Properties
timeline State Manifold
Latent space encodes all valid configurations. Interpolation = Physical motion.
difference Diff. Twin
Fully differentiable structure enables gradient-based policy learning.
touch_app Actionable
Prescriptive, not just descriptive. Encodes "how to change" the object.
healing Robustness
Auto-completes occluded geometry & fills sensory gaps (Material Completion).
swap_horiz
Paradigm Shift
Before
After
analytics
Experimental Insights
-
check_circle
Interpretable Tokens
Latent queries specialize in object parts (e.g., thumb, palm) consistently across poses.
-
check_circle
Real-World Soft Bodies
Successfully models high-DoF non-linear manifolds (Rope, Cloth) preserving volume consistency.