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 126–150 of 158 papers

TitleStatusHype
Simple and Lightweight Human Pose EstimationCode0
Knowledge Graph Transfer Network for Few-Shot RecognitionCode0
Structure Matters: Towards Generating Transferable Adversarial Images—0
Meta-Learning to Detect Rare Objects—0
Prototype Recalls for Continual Learning—0
Meta-Learning by Hallucinating Useful Examples—0
Learning 3D-aware Egocentric Spatial-Temporal Interaction via Graph Convolutional Networks—0
Resonant Machine Learning Based on Complex Growth Transform Dynamical Systems—0
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 concepts—0
Situational Grounding within Multimodal Simulations—0
Understanding MCMC Dynamics as Flows on the Wasserstein SpaceCode0
Beyond imitation: Zero-shot task transfer on robots by learning concepts as cognitive programs—0
From Known to the Unknown: Transferring Knowledge to Answer Questions about Novel Visual and Semantic Concepts—0
Characterizing the Influence of Features on Reading Difficulty Estimation for Non-native Readers—0
Can Machines Design? An Artificial General Intelligence Approach—0
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 Search—0
Zero-Shot Learning by Generating Pseudo Feature Representations—0
Sequential Local Learning for Latent Graphical Models—0
Show:102550
← PrevPage 6 of 7Next →

No leaderboard results yet.