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 81–90 of 158 papers

TitleStatusHype
Encoder-based Domain Tuning for Fast Personalization of Text-to-Image Models—0
Designing Rotationally Invariant Neural Networks from PDEs and Variational Methods—0
Diagnosing and Remedying Shot Sensitivity with Cosine Few-Shot Learners—0
Dialog Policy Learning for Joint Clarification and Active Learning Queries—0
Direct and indirect transactions and requirements—0
Discovering Latent Concepts Learned in BERT—0
DreamArtist++: Controllable One-Shot Text-to-Image Generation via Positive-Negative Adapter—0
DRPT: Disentangled and Recurrent Prompt Tuning for Compositional Zero-Shot Learning—0
Dual-View Data Hallucination with Semantic Relation Guidance for Few-Shot Image Recognition—0
Efficient Transmission of Radiomaps via Physics-Enhanced Semantic Communications—0
Show:102550
← PrevPage 9 of 16Next →

No leaderboard results yet.