511 citations · 1.1k across the 13 of their papers we have counts for
14 papers
Learning a Canonical Basis of Human Preferences from Binary Ratings
Kailas Vodrahalli, Wei Wei, James Zou
Recent advances in generative AI have been driven by alignment techniques such as reinforcement learning from human feedback (RLHF). RLHF and related techniques typically involve c…
Can large language models provide useful feedback on research papers? A large-scale empirical analysis
Weixin Liang, Yuhui Zhang, Hancheng Cao +9
Expert feedback lays the foundation of rigorous research. However, the rapid growth of scholarly production and intricate knowledge specialization challenge the conventional scient…
ArtWhisperer: A Dataset for Characterizing Human-AI Interactions in Artistic Creations
Kailas Vodrahalli, James Zou
As generative AI becomes more prevalent, it is important to study how human users interact with such models. In this work, we investigate how people use text-to-image models to gen…
Development and Clinical Evaluation of an AI Support Tool for Improving Telemedicine Photo Quality
Kailas Vodrahalli, Justin Ko, Albert S. Chiou +7
Telemedicine utilization was accelerated during the COVID-19 pandemic, and skin conditions were a common use case. However, the quality of photographs sent by patients remains a ma…
Disparities in Dermatology AI Performance on a Diverse, Curated Clinical Image Set
Roxana Daneshjou, Kailas Vodrahalli, Roberto A Novoa +16
Access to dermatological care is a major issue, with an estimated 3 billion people lacking access to care globally. Artificial intelligence (AI) may aid in triaging skin diseases.…
Uncalibrated Models Can Improve Human-AI Collaboration
Kailas Vodrahalli, Tobias Gerstenberg, James Zou
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…
Disparities in Dermatology AI: Assessments Using Diverse Clinical Images
Roxana Daneshjou, Kailas Vodrahalli, Weixin Liang +14
More than 3 billion people lack access to care for skin disease. AI diagnostic tools may aid in early skin cancer detection; however most models have not been assessed on images of…
Do Humans Trust Advice More if it Comes from AI? An Analysis of Human-AI Interactions
Kailas Vodrahalli, Roxana Daneshjou, Tobias Gerstenberg +1
In decision support applications of AI, the AI algorithm's output is framed as a suggestion to a human user. The user may ignore this advice or take it into consideration to modify…
Adversarial Training Helps Transfer Learning via Better Representations
Zhun Deng, Linjun Zhang, Kailas Vodrahalli +2
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 wor…
Better Knowledge Retention through Metric Learning
Ke Li, Shichong Peng, Kailas Vodrahalli +1
In continual learning, new categories may be introduced over time, and an ideal learning system should perform well on both the original categories and the new categories. While de…
TrueImage: A Machine Learning Algorithm to Improve the Quality of Telehealth Photos
Kailas Vodrahalli, Roxana Daneshjou, Roberto A Novoa +3
Telehealth is an increasingly critical component of the health care ecosystem, especially due to the COVID-19 pandemic. Rapid adoption of telehealth has exposed limitations in the…
Blind interactive learning of modulation schemes: Multi-agent cooperation without co-design
Anant Sahai, Joshua Sanz, Vignesh Subramanian +2
We examine the problem of learning to cooperate in the context of wireless communication. In our setting, two agents must learn modulation schemes that enable them to communicate a…
Harmless interpolation of noisy data in regression
Vidya Muthukumar, Kailas Vodrahalli, Vignesh Subramanian +1
A continuing mystery in understanding the empirical success of deep neural networks is their ability to achieve zero training error and generalize well, even when the training data…
Are All Training Examples Created Equal? An Empirical Study
Kailas Vodrahalli, Ke Li, Jitendra Malik
Modern computer vision algorithms often rely on very large training datasets. However, it is conceivable that a carefully selected subsample of the dataset is sufficient for traini…