← Search

Kailas Vodrahalli

3 accepted papers

2024

ArtWhisperer: A Dataset for Characterizing Human-AI Interactions in Artistic Creations

ICML 2024poster

In this work, we investigate how people use text-to-image models to generate desired target images. To study this interaction, we created ArtWhisperer, an online game where users are given a target image and are tasked with iteratively finding a prompt that creates a similar-looking image as the tar…

2022

Uncalibrated Models Can Improve Human-AI Collaboration

NeurIPS 2022accept

In many practical applications of AI, an AI model is used as a decision aid for human users. The AI provides advice that a human (sometimes) incorporates into their decision-making process. The AI advice is often presented with some measure of "confidence" that the human can use to calibrate how muc…

2021

Adversarial Training Helps Transfer Learning via Better Representations

NeurIPS 2021poster

Transfer learning aims to leverage models pre-trained on source data to efficiently adapt to target setting, where only limited data are available for model fine-tuning. Recent works empirically demonstrate that adversarial training in the source data can improve the ability of models to transfer to…

Cited by 63SourcePDFScholar