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
Training Compute-Optimal Large Language ModelsCode6
Locate Anything on Earth: Advancing Open-Vocabulary Object Detection for Remote Sensing CommunityCode3
Attention Calibration for Disentangled Text-to-Image PersonalizationCode2
PaLM: Scaling Language Modeling with PathwaysCode2
Scaling Language Models: Methods, Analysis & Insights from Training GopherCode2
SAM-Assisted Remote Sensing Imagery Semantic Segmentation with Object and Boundary ConstraintsCode2
Is CLIP the main roadblock for fine-grained open-world perception?Code2
Learning Instance and Task-Aware Dynamic Kernels for Few Shot LearningCode1
CroSSL: Cross-modal Self-Supervised Learning for Time-series through Latent MaskingCode1
Link-Context Learning for Multimodal LLMsCode1
Dynamic Few-Shot Visual Learning without ForgettingCode1
AFANet: Adaptive Frequency-Aware Network for Weakly-Supervised Few-Shot Semantic SegmentationCode1
A Language Model's Guide Through Latent SpaceCode1
EDIN: An End-to-end Benchmark and Pipeline for Unknown Entity Discovery and IndexingCode1
Bridging Few-Shot Learning and Adaptation: New Challenges of Support-Query ShiftCode1
Happy: A Debiased Learning Framework for Continual Generalized Category DiscoveryCode1
Language-Informed Visual Concept LearningCode1
Bongard-LOGO: A New Benchmark for Human-Level Concept Learning and ReasoningCode1
LEDetection: A Simple Framework for Semi-Supervised Few-Shot Object DetectionCode1
Extract Free Dense Labels from CLIPCode1
Bongard-HOI: Benchmarking Few-Shot Visual Reasoning for Human-Object InteractionsCode1
IFSeg: Image-free Semantic Segmentation via Vision-Language ModelCode1
Few-Shot Class-Incremental Learning via Class-Aware Bilateral DistillationCode1
DreamCreature: Crafting Photorealistic Virtual Creatures from ImaginationCode1
CODA-Prompt: COntinual Decomposed Attention-based Prompting for Rehearsal-Free Continual LearningCode1
Show:102550
← PrevPage 1 of 7Next →

No leaderboard results yet.