SOTAVerified

Concept Alignment

Concept Alignment aims to align the learned representations or concepts within a model with the intended or target concepts. It involves adjusting the model's parameters or training process to ensure that the learned concepts accurately reflect the underlying patterns in the data.

Papers

Recently AddedMost HypedMost ActiveNeeds VerificationMost Verified

Showing 11–20 of 36 papers

TitleStatusHype
ConceptBed: Evaluating Concept Learning Abilities of Text-to-Image Diffusion ModelsCode1
Concept Extraction Using Pointer-Generator NetworksCode1
Replace in Translation: Boost Concept Alignment in Counterfactual Text-to-Image—0
An Explanation of Intrinsic Self-Correction via Linear Representations and Latent Concepts—0
Handling Imbalanced Pseudolabels for Vision-Language Models with Concept Alignment and Confusion-Aware Calibrated Margin—0
Training-free Dense-Aligned Diffusion Guidance for Modular Conditional Image SynthesisCode0
Enhancing Domain-Specific Retrieval-Augmented Generation: Synthetic Data Generation and Evaluation using Reasoning ModelsCode0
Interpretable Concept-based Deep Learning Framework for Multimodal Human Behavior Modeling—0
Anchor and Broadcast: An Efficient Concept Alignment Approach for Evaluation of Semantic GraphsCode0
Improving Concept Alignment in Vision-Language Concept Bottleneck ModelsCode0
Show:102550
← PrevPage 2 of 4Next →

No leaderboard results yet.