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 121–130 of 158 papers

TitleStatusHype
What happens when generative AI models train recursively on each others' generated outputs?—0
Word reuse and combination support efficient communication of emerging concepts—0
Zero-Shot Learning by Generating Pseudo Feature Representations—0
Malware Detection and Prevention using Artificial Intelligence Techniques—0
Memorizing Complementation Network for Few-Shot Class-Incremental Learning—0
Meta-Learning by Hallucinating Useful Examples—0
Meta-Learning to Detect Rare Objects—0
Neuro-Symbolic Concepts—0
Open Ad-hoc Categorization with Contextualized Feature Learning—0
Open-Set Representation Learning through Combinatorial Embedding—0
Show:102550
← PrevPage 13 of 16Next →

No leaderboard results yet.