1 code implementation • 3 Oct 2023 • Weixin Liang, Yuhui Zhang, Hancheng Cao, Binglu Wang, Daisy Ding, Xinyu Yang, Kailas Vodrahalli, Siyu He, Daniel Smith, Yian Yin, Daniel McFarland, James Zou
We first quantitatively compared GPT-4's generated feedback with human peer reviewer feedback in 15 Nature family journals (3, 096 papers in total) and the ICLR machine learning conference (1, 709 papers).
1 code implementation • 13 Jun 2023 • Kailas Vodrahalli, James Zou
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 target.
1 code implementation • 12 Sep 2022 • Kailas Vodrahalli, Justin Ko, Albert S. Chiou, Roberto Novoa, Abubakar Abid, Michelle Phung, Kiana Yekrang, Paige Petrone, James Zou, Roxana Daneshjou
To address this issue, we developed TrueImage 2. 0, an artificial intelligence (AI) model for assessing patient photo quality for telemedicine and providing real-time feedback to patients for photo quality improvement.
no code implementations • 15 Mar 2022 • Roxana Daneshjou, Kailas Vodrahalli, Roberto A Novoa, Melissa Jenkins, Weixin Liang, Veronica Rotemberg, Justin Ko, Susan M Swetter, Elizabeth E Bailey, Olivier Gevaert, Pritam Mukherjee, Michelle Phung, Kiana Yekrang, Bradley Fong, Rachna Sahasrabudhe, Johan A. C. Allerup, Utako Okata-Karigane, James Zou, Albert Chiou
To ascertain potential biases in algorithm performance in this context, we curated the Diverse Dermatology Images (DDI) dataset-the first publicly available, expertly curated, and pathologically confirmed image dataset with diverse skin tones.
1 code implementation • 12 Feb 2022 • Kailas Vodrahalli, Tobias Gerstenberg, James Zou
In this paper, we present an initial exploration that suggests showing AI models as more confident than they actually are, even when the original AI is well-calibrated, can improve human-AI performance (measured as the accuracy and confidence of the human's final prediction after seeing the AI advice).
no code implementations • 15 Nov 2021 • Roxana Daneshjou, Kailas Vodrahalli, Weixin Liang, Roberto A Novoa, Melissa Jenkins, Veronica Rotemberg, Justin Ko, Susan M Swetter, Elizabeth E Bailey, Olivier Gevaert, Pritam Mukherjee, Michelle Phung, Kiana Yekrang, Bradley Fong, Rachna Sahasrabudhe, James Zou, Albert Chiou
AI diagnostic tools may aid in early skin cancer detection; however most models have not been assessed on images of diverse skin tones or uncommon diseases.
1 code implementation • 14 Jul 2021 • Kailas Vodrahalli, Roxana Daneshjou, Tobias Gerstenberg, James Zou
In decision support applications of AI, the AI algorithm's output is framed as a suggestion to a human user.
no code implementations • NeurIPS 2021 • Zhun Deng, Linjun Zhang, Kailas Vodrahalli, Kenji Kawaguchi, James Zou
Recent works empirically demonstrate that adversarial training in the source data can improve the ability of models to transfer to new domains.
no code implementations • 26 Nov 2020 • Ke Li, Shichong Peng, Kailas Vodrahalli, Jitendra Malik
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.
no code implementations • 1 Oct 2020 • Kailas Vodrahalli, Roxana Daneshjou, Roberto A Novoa, Albert Chiou, Justin M Ko, James Zou
These promising results suggest that our solution is feasible and can improve the quality of teledermatology care.
no code implementations • 21 Oct 2019 • Anant Sahai, Joshua Sanz, Vignesh Subramanian, Caryn Tran, Kailas Vodrahalli
We investigate whether learning is possible under different levels of information sharing between distributed agents which are not necessarily co-designed.
no code implementations • 21 Mar 2019 • Vidya Muthukumar, Kailas Vodrahalli, Vignesh Subramanian, Anant Sahai
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 is noisy and there are more parameters than data points.
no code implementations • 30 Nov 2018 • Kailas Vodrahalli, Ke Li, Jitendra Malik
Modern computer vision algorithms often rely on very large training datasets.