SOTAVerified

Novel Concepts

Measures the ability of models to uncover an underlying concept that unites several ostensibly disparate entities, which hopefully would not co-occur frequently. This provides a limited test of a model's ability to creatively construct the necessary abstraction to make sense of a situation that it cannot have memorized in training.

Source: BIG-bench

Papers

Recently AddedMost HypedMost ActiveNeeds VerificationMost Verified

Showing 151–158 of 158 papers

TitleStatusHype
Tinkering Under the Hood: Interactive Zero-Shot Learning with Net Surgery—0
A Robust Framework for Classifying Evolving Document Streams in an Expert-Machine-Crowd Setting—0
Deep Compositional Captioning: Describing Novel Object Categories without Paired Training DataCode0
Schema Independent Relational Learning—0
Learning like a Child: Fast Novel Visual Concept Learning from Sentence Descriptions of ImagesCode0
Learning to Learn with Compound HD Models—0
Automating string processing in spreadsheets using input-output examples—0
Image Inpainting by Patch Propagation Using Patch Sparsity—0
Show:102550
← PrevPage 4 of 4Next →

No leaderboard results yet.