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 51–60 of 158 papers

TitleStatusHype
Surprisal Driven k-NN for Robust and Interpretable Nonparametric Learning—0
A Robust, Efficient Predictive Safety FilterCode0
Towards Open-Ended Visual Recognition with Large Language ModelCode1
ChatAnything: Facetime Chat with LLM-Enhanced Personas—0
Experiencing Urban Air Mobility: How Passengers evaluate a simulated flight with an Air Taxi—0
OV-VG: A Benchmark for Open-Vocabulary Visual GroundingCode1
Continual Zero-Shot Learning through Semantically Guided Generative Random WalksCode0
Link-Context Learning for Multimodal LLMsCode1
CroSSL: Cross-modal Self-Supervised Learning for Time-series through Latent MaskingCode1
L3DMC: Lifelong Learning using Distillation via Mixed-Curvature SpaceCode0
Show:102550
← PrevPage 6 of 16Next →

No leaderboard results yet.