Knowledge Graph

Graph explorer

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

Entities25 of 207,987

Entity

few-shot residual adaptation

technology1 mentionslast seen Nov 12, 2026

Approach that learns self-supervised corrections from latent prediction errors without modifying pretrained weights.

Relationships 2

few-shot residual adaptationdepends onlatent world model90% confidence1 source
few-shot residual adaptationapplies torobotic manipulation and control85% confidence1 source

few-shot residual adaptation

Relationship

few-shot residual adaptationdepends onlatent world model

90% confidence1 supporting mentions

Either name opens that entity’s relationships.

Sources 1

preprintarXivNov 10, 2026Few-Shot Residual Adaptation of Pretrained Latent World Models
few-shot residual adaptation approach that learns self-supervised corrections from latent prediction errors. The corrections are applied both inside the latent predictor and directly to its predicted latent state, while the pretrained world model remains frozen