Knowledge Graph

Graph explorer

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

Entities25 of 207,987

Entity

Future REpresentation learning via self-Distillation with temporal context

technology1 mentionslast seen Oct 23, 2026

Framework that trains World Action Models to improve quality of future video representations from noise in a single denoising step.

Relationships 4

Future REpresentation learning via self-Distillation with temporal contextdepends onself-distillation93% confidence1 source
Future REpresentation learning via self-Distillation with temporal contextdepends onworld-action model92% confidence1 source
Future REpresentation learning via self-Distillation with temporal contextapplies tohuman-to-robot skill transfer90% confidence1 source
Future REpresentation learning via self-Distillation with temporal contextapplies torobot manipulation88% confidence1 source

Future REpresentation learning via self-Distillation with temporal context

Relationship

Future REpresentation learning via self-Distillation with temporal contextapplies torobot manipulation

88% confidence1 supporting mentions

Either name opens that entity’s relationships.

Sources 1

preprintarXivOct 21, 2026Self-Distilling Future Video Representations for World Action Models
Across diverse real-world manipulation scenarios, FRED consistently outperforms competing WAMs