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 31–40 of 158 papers

TitleStatusHype
Learning Instance and Task-Aware Dynamic Kernels for Few Shot LearningCode1
Extract Free Dense Labels from CLIPCode1
Bridging Few-Shot Learning and Adaptation: New Challenges of Support-Query ShiftCode1
DER: Dynamically Expandable Representation for Class Incremental LearningCode1
Bongard-LOGO: A New Benchmark for Human-Level Concept Learning and ReasoningCode1
XtarNet: Learning to Extract Task-Adaptive Representation for Incremental Few-Shot LearningCode1
Dynamic Few-Shot Visual Learning without ForgettingCode1
Explaining deep neural network models for electricity price forecasting with XAI—0
What happens when generative AI models train recursively on each others' generated outputs?—0
From Data to Modeling: Fully Open-vocabulary Scene Graph Generation—0
Show:102550
← PrevPage 4 of 16Next →

No leaderboard results yet.