Knowledge Graph

Graph explorer

Search resolved entities, walk their edges, and read the sentence behind every one.

Entities25 of 207,987

Entity

3D visual pretraining

technology1 mentionslast seen Oct 26, 2026

Existing methods that model state transitions at the scene level, which DynaSlots improves upon.

Relationships 1

DynaSlotssupersedes3D visual pretraining75% confidence1 source

3D visual pretraining

Relationship

DynaSlotssupersedes3D visual pretraining

75% confidence1 supporting mentions

Either name opens that entity’s relationships.

Sources 1

preprintarXivOct 23, 2026DynaSlots: Slot-Centric 3D Dynamics Pretraining for Robot Manipulation
existing 3D visual pretraining methods, including recent dynamics-aware variants, model state transitions at the scene level, compressing the motion of everything in a scene into a single global latent action. This conflates semantically distinct transitions in scenes with multiple moving parts, obscures dependencies between changing regions, and leaves the learned representation vulnerable to task-irrelevant scene content. We introduce DynaSlots