research
∙
09/07/2023
A Function Interpretation Benchmark for Evaluating Interpretability Methods
Labeling neural network submodules with human-legible descriptions is us...
share
research
∙
08/25/2023
Unified Concept Editing in Diffusion Models
Text-to-image models suffer from various safety issues that may limit th...
research
∙
03/13/2023
Erasing Concepts from Diffusion Models
Motivated by recent advancements in text-to-image diffusion, we study er...
research
∙
06/15/2022
Disentangling visual and written concepts in CLIP
The CLIP network measures the similarity between natural text and images...
research
∙
12/20/2019
Something-Else: Compositional Action Recognition with Spatial-Temporal Interaction Networks
Human action is naturally compositional: humans can easily recognize and...
research
∙
06/13/2017