Picture for Usha Bhalla

Usha Bhalla

Towards Unifying Interpretability and Control: Evaluation via Intervention

Add code
Nov 07, 2024
Viaarxiv icon

All Roads Lead to Rome? Exploring Representational Similarities Between Latent Spaces of Generative Image Models

Add code
Jul 18, 2024
Viaarxiv icon

Operationalizing the Blueprint for an AI Bill of Rights: Recommendations for Practitioners, Researchers, and Policy Makers

Add code
Jul 11, 2024
Viaarxiv icon

Interpreting CLIP with Sparse Linear Concept Embeddings (SpLiCE)

Add code
Feb 16, 2024
Viaarxiv icon

Verifiable Feature Attributions: A Bridge between Post Hoc Explainability and Inherent Interpretability

Add code
Jul 27, 2023
Viaarxiv icon

Do Vision-Language Pretrained Models Learn Primitive Concepts?

Add code
Mar 31, 2022
Figure 1 for Do Vision-Language Pretrained Models Learn Primitive Concepts?
Figure 2 for Do Vision-Language Pretrained Models Learn Primitive Concepts?
Figure 3 for Do Vision-Language Pretrained Models Learn Primitive Concepts?
Figure 4 for Do Vision-Language Pretrained Models Learn Primitive Concepts?
Viaarxiv icon