Mundo turns 1 to 12 photos into an interactive 3D world. You can move the camera, push objects, simulate physics and control robots. Unlike pure video generation, the scene stays consistent when the camera changes.

NVIDIA released Foundation4D. Give it multi-camera driving video and a single forward pass returns depth, camera poses, 3D boxes, semantic occupancy and Gaussians you can render. One shared backbone, a decoder per task.

Most video world models try to predict future actions directly in pixel space, which hides internal physics and makes precise control difficult. Adam Abecid and team introduced DeXplicit to fix this by making physical state explicit for dexterous manipulation. The model first forecasts 3D geometry motion for objects and hands, then renders those explicit physical states into future video. It handles joint level hand articulation, keeps track of dynamic object deformations, and runs fast enough with Causal DeXplicit to output four future video frames in 0.54 seconds on a single A800 GPU.

Robots can assemble parts without seeing or feeling anything. “Blind Precise Assembly” from MIT CSAIL shows that joint encoders alone give enough proprioceptive feedback for precise assembly. The tasks include peg insertion, gear meshing, and nut threading. No cameras. No tactile sensors. No object pose knowledge.

Generative models are blind to the physics of complete trajectories. They predict the next step but fail to understand the entire path. Researchers from Harvard and Microsoft just fixed this with LEAP. By treating the stochastic action of a system as the primary learning target, this framework turns raw trajectory observations into a fully reusable objective for scientific control.