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 1–25 of 158 papers

TitleStatusHype
Explaining deep neural network models for electricity price forecasting with XAI—0
What happens when generative AI models train recursively on each others' generated outputs?—0
From Data to Modeling: Fully Open-vocabulary Scene Graph Generation—0
Neuro-Symbolic Concepts—0
Exploring internal representation of self-supervised networks: few-shot learning abilities and comparison with human semantics and recognition of objects—0
Contrastive Visual Data Augmentation—0
Efficient Transmission of Radiomaps via Physics-Enhanced Semantic Communications—0
Towards A Litmus Test for Common Sense—0
Open Ad-hoc Categorization with Contextualized Feature Learning—0
AFANet: Adaptive Frequency-Aware Network for Weakly-Supervised Few-Shot Semantic SegmentationCode1
NeSyCoCo: A Neuro-Symbolic Concept Composer for Compositional GeneralizationCode0
PersonaMagic: Stage-Regulated High-Fidelity Face Customization with Tandem EquilibriumCode1
Rehearsal-Free Continual Federated Learning with Synergistic Synaptic Intelligence—0
CALA: A Class-Aware Logit Adapter for Few-Shot Class-Incremental Learning—0
Grounding Descriptions in Images informs Zero-Shot Visual RecognitionCode1
Knowledge Transfer Across Modalities with Natural Language Supervision—0
Word reuse and combination support efficient communication of emerging concepts—0
Few-Shot Task Learning through Inverse Generative Modeling—0
SAFE: Slow and Fast Parameter-Efficient Tuning for Continual Learning with Pre-Trained ModelsCode1
Human-Object Interaction Detection Collaborated with Large Relation-driven Diffusion Models—0
Large Language Models for Autonomous Driving (LLM4AD): Concept, Benchmark, Experiments, and Challenges—0
Happy: A Debiased Learning Framework for Continual Generalized Category DiscoveryCode1
SECURE: Semantics-aware Embodied Conversation under Unawareness for Lifelong Robot Learning—0
Can Vision Language Models Learn from Visual Demonstrations of Ambiguous Spatial Reasoning?Code0
Complex Emotion Recognition System using basic emotions via Facial Expression, EEG, and ECG Signals: a review—0
Show:102550
← PrevPage 1 of 7Next →

No leaderboard results yet.