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 101–150 of 158 papers

TitleStatusHype
Reaction Network Analysis of Metabolic Insulin Signaling—0
Rehearsal-Free Continual Federated Learning with Synergistic Synaptic Intelligence—0
Resonant Machine Learning Based on Complex Growth Transform Dynamical Systems—0
Rockafellian Relaxation and Stochastic Optimization under Perturbations—0
Schema Independent Relational Learning—0
SECURE: Semantics-aware Embodied Conversation under Unawareness for Lifelong Robot Learning—0
Sequential Local Learning for Latent Graphical Models—0
Situational Grounding within Multimodal Simulations—0
Sketch-Plan-Generalize: Learning and Planning with Neuro-Symbolic Programmatic Representations for Inductive Spatial Concepts—0
Smoothed Bernstein Online Aggregation for Day-Ahead Electricity Demand Forecasting—0
Statistical Depth Functions for Ranking Distributions: Definitions, Statistical Learning and Applications—0
Statistical QoS Provisioning Analysis and Performance Optimization in xURLLC-enabled Massive MU-MIMO Networks: A Stochastic Network Calculus Perspective—0
Strategy Synthesis in Markov Decision Processes Under Limited Sampling Access—0
Structure Matters: Towards Generating Transferable Adversarial Images—0
Surprisal Driven k-NN for Robust and Interpretable Nonparametric Learning—0
Theoretical and Empirical Analysis of Adaptive Entry Point Selection for Graph-based Approximate Nearest Neighbor Search—0
The Price of Cognition and Replicator Equations in Parallel Neural Networks—0
Tinkering Under the Hood: Interactive Zero-Shot Learning with Net Surgery—0
Toward enriched Cognitive Learning with XAI—0
Towards A Litmus Test for Common Sense—0
Weakly Supervised Open-Vocabulary Object Detection—0
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
Learning like a Child: Fast Novel Visual Concept Learning from Sentence Descriptions of ImagesCode0
L3DMC: Lifelong Learning using Distillation via Mixed-Curvature SpaceCode0
Revisit Systematic Generalization via Meaningful LearningCode0
Task-Aware Feature Generation for Zero-Shot Compositional LearningCode0
Task-Driven Modular Networks for Zero-Shot Compositional LearningCode0
Simple and Lightweight Human Pose EstimationCode0
Multi-level Semantic Feature Augmentation for One-shot LearningCode0
NeSyCoCo: A Neuro-Symbolic Concept Composer for Compositional GeneralizationCode0
Neural Concept Formation in Knowledge GraphsCode0
WDiscOOD: Out-of-Distribution Detection via Whitened Linear Discriminant AnalysisCode0
Knowledge Graph Transfer Network for Few-Shot RecognitionCode0
SketchEmbedNet: Learning Novel Concepts by Imitating DrawingsCode0
A Commonsense Reasoning Framework for Explanatory Emotion Attribution, Generation and Re-classificationCode0
A Clustering-based Framework for Classifying Data StreamsCode0
How Should Agents Ask Questions For Situated Learning? An Annotated Dialogue CorpusCode0
Emergence of hierarchical reference systems in multi-agent communicationCode0
Deep Compositional Captioning: Describing Novel Object Categories without Paired Training DataCode0
Zero-Shot Object Detection: Learning to Simultaneously Recognize and Localize Novel ConceptsCode0
A Provable Defense for Deep Residual NetworksCode0
Variational Prototype Replays for Continual LearningCode0
Show:102550
← PrevPage 3 of 4Next →

No leaderboard results yet.