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 101–125 of 158 papers

TitleStatusHype
Few-Shot Novel Concept Learning for Semantic Parsing—0
CoSe-Co: Sentence Conditioned Generative CommonSense Contextualizer for Language Models—0
Designing Rotationally Invariant Neural Networks from PDEs and Variational Methods—0
Decision Making Using Rough Set based Spanning Sets for a Decision System—0
Smoothed Bernstein Online Aggregation for Day-Ahead Electricity Demand Forecasting—0
Open-Set Representation Learning through Combinatorial Embedding—0
Neural Concept Formation in Knowledge GraphsCode0
A Clustering-based Framework for Classifying Data StreamsCode0
How Should Agents Ask Questions For Situated Learning? An Annotated Dialogue CorpusCode0
Bridging Few-Shot Learning and Adaptation: New Challenges of Support-Query ShiftCode1
DER: Dynamically Expandable Representation for Class Incremental LearningCode1
A Commonsense Reasoning Framework for Explanatory Emotion Attribution, Generation and Re-classificationCode0
Linguistically Routing Capsule Network for Out-of-Distribution Visual Question Answering—0
Enhancing Balanced Graph Edge Partition with Effective Local Search—0
Bongard-LOGO: A New Benchmark for Human-Level Concept Learning and ReasoningCode1
SketchEmbedNet: Learning Novel Concepts by Imitating DrawingsCode0
Dialog Policy Learning for Joint Clarification and Active Learning Queries—0
Characterizing an Analogical Concept Memory for Architectures Implementing the Common Model of Cognition—0
XtarNet: Learning to Extract Task-Adaptive Representation for Incremental Few-Shot LearningCode1
Revisit Systematic Generalization via Meaningful LearningCode0
Contextual Blocking Bandits—0
Exploring Partial Intrinsic and Extrinsic Symmetry in 3D Medical Imaging—0
FLAT: Few-Shot Learning via Autoencoding Transformation Regularizers—0
Direct and indirect transactions and requirements—0
Simple and Lightweight Human Pose EstimationCode0
Show:102550
← PrevPage 5 of 7Next →

No leaderboard results yet.