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

Showing 101150 of 158 papers

TitleStatusHype
A Closer Look at Rehearsal-Free Continual Learning0
FALCON: Fast Visual Concept Learning by Integrating Images, Linguistic descriptions, and Conceptual Relations0
Emergence of hierarchical reference systems in multi-agent communicationCode0
Statistical Depth Functions for Ranking Distributions: Definitions, Statistical Learning and Applications0
Generative Pre-Trained Transformer for Design Concept Generation: An Exploration0
Few-Shot Novel Concept Learning for Semantic Parsing0
CoSe-Co: Sentence Conditioned Generative CommonSense Contextualizer for Language Models0
Designing Rotationally Invariant Neural Networks from PDEs and Variational Methods0
Decision Making Using Rough Set based Spanning Sets for a Decision System0
Smoothed Bernstein Online Aggregation for Day-Ahead Electricity Demand Forecasting0
Open-Set Representation Learning through Combinatorial Embedding0
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
A Commonsense Reasoning Framework for Explanatory Emotion Attribution, Generation and Re-classificationCode0
Linguistically Routing Capsule Network for Out-of-Distribution Visual Question Answering0
Enhancing Balanced Graph Edge Partition with Effective Local Search0
SketchEmbedNet: Learning Novel Concepts by Imitating DrawingsCode0
Dialog Policy Learning for Joint Clarification and Active Learning Queries0
Characterizing an Analogical Concept Memory for Architectures Implementing the Common Model of Cognition0
Revisit Systematic Generalization via Meaningful LearningCode0
Contextual Blocking Bandits0
Exploring Partial Intrinsic and Extrinsic Symmetry in 3D Medical Imaging0
FLAT: Few-Shot Learning via Autoencoding Transformation Regularizers0
Direct and indirect transactions and requirements0
Simple and Lightweight Human Pose EstimationCode0
Knowledge Graph Transfer Network for Few-Shot RecognitionCode0
Structure Matters: Towards Generating Transferable Adversarial Images0
Meta-Learning to Detect Rare Objects0
Prototype Recalls for Continual Learning0
Meta-Learning by Hallucinating Useful Examples0
Learning 3D-aware Egocentric Spatial-Temporal Interaction via Graph Convolutional Networks0
Resonant Machine Learning Based on Complex Growth Transform Dynamical Systems0
Task-Aware Feature Generation for Zero-Shot Compositional LearningCode0
Variational Prototype Replays for Continual LearningCode0
Task-Driven Modular Networks for Zero-Shot Compositional LearningCode0
A Provable Defense for Deep Residual NetworksCode0
25 years of criticality in neuroscience -- established results, open controversies, novel concepts0
Situational Grounding within Multimodal Simulations0
Understanding MCMC Dynamics as Flows on the Wasserstein SpaceCode0
Beyond imitation: Zero-shot task transfer on robots by learning concepts as cognitive programs0
From Known to the Unknown: Transferring Knowledge to Answer Questions about Novel Visual and Semantic Concepts0
Characterizing the Influence of Features on Reading Difficulty Estimation for Non-native Readers0
Can Machines Design? An Artificial General Intelligence Approach0
Multi-level Semantic Feature Augmentation for One-shot LearningCode0
Decoupled Novel Object CaptionerCode0
Zero-Shot Object Detection: Learning to Simultaneously Recognize and Localize Novel ConceptsCode0
Privacy-Enabled Biometric Search0
Zero-Shot Learning by Generating Pseudo Feature Representations0
Sequential Local Learning for Latent Graphical Models0
Show:102550
← PrevPage 3 of 4Next →

No leaderboard results yet.