← Search

Pratyusha Kalluri

2 accepted papers

2023

When and Why Vision-Language Models Behave like Bags-Of-Words, and What to Do About It?

ICLR 2023top-5%

Despite the success of large vision and language models (VLMs) in many downstream applications, it is unclear how well they encode the compositional relationships between objects and attributes. Here, we create the Attribution, Relation, and Order (ARO) benchmark to systematically evaluate the abili…

2019

Learning Controllable Fair Representations

AISTATS 2019poster

Learning data representations that are transferable and are fair with respect to certain protected attributes is crucial to reducing unfair decisions while preserving the utility of the data. We propose an information-theoretically motivated objective for learning maximally expressive representation…