Research

I am interested in the human aspects of machine learning, and in particular, theory and general principles for designing algorithms for human interaction. Recently, I have explored these problems in various contexts including (1) medicine, where I have worked on developing machine learning-based algorithms for use in solving healthcare-related problems with an end-goal of deploying our solutions for clinical use; (2) VLMs, where I have investigated how users interact with VLMs over time; and (3) LLMs, where I am working on questions related to user personalization and LLM output confidence and bias.

Selected Research

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

Vodrahalli, K., Zou, J.
arXiv preprint arXiv:2306.08141 (2023)
[ arXiv] [ Code] [ Dataset]

Uncalibrated Models Can Improve Human-AI Collaboration

Vodrahalli, K., Gerstenberg, T., Zou, J.
NeurIPS (2022), Oral Presentation
[ Paper] [ Dataset]

Development and Clinical Evaluation of an Artificial Intelligence Support Tool for Improving Telemedicine Photo Quality

Vodrahalli, K., Ko, J., Chiou, A. S., Novoa, R., Abid, A., Phung, M., Yekrang, K., Petrone, P., Zou, J., Daneshjou, R.
JAMA dermatology (2023)
[ Paper]

All Publications

17. Understanding and Predicting the Effect of Environmental Factors on People With Type 2 Diabetes

Vodrahalli, K., Lyng, G. D., Hill, B. L., Karkkainen, K., Hertzberg, J., Zou, J., Halperin, E.
Proceedings for the Conference on Health, Inference, and Learning (2023)
[ Paper]

16. Development and Clinical Evaluation of an Artificial Intelligence Support Tool for Improving Telemedicine Photo Quality

Vodrahalli, K., Ko, J., Chiou, A. S., Novoa, R., Abid, A., Phung, M., Yekrang, K., Petrone, P., Zou, J., Daneshjou, R.
JAMA dermatology (2023)
[ Paper]

15. Uncalibrated Models Can Improve Human-AI Collaboration

Vodrahalli, K., Gerstenberg, T., Zou, J.
NeurIPS (2022), Oral Presentation
[ Paper] [ Dataset]

14. Disparities in Dermatology AI Performance on a Diverse, Curated Clinical Image Set

Daneshjou, R.*, Vodrahalli, K.*, Novoa, R. A., Jenkins, M., Liang, W., Rotemberg, V., Ko, J., Swetter, S. M., Bailey, E. E., Gevaert, O., Mukherjee, P., Phung, M., Yekrang, K., Fong, B., Sahasrabudhe, R., C, A. J., Okata-Karigane, U., Zou, J., Chiou, A. S.
Science Advances (2022)
[ Paper] [ Project Page] [ Code] [ Dataset]

13. Do Humans Trust Advice More if it Comes From AI? An Analysis of Human-AI Interactions

Vodrahalli, K., Daneshjou, R., Gerstenberg, T., Zou, J.
AIES (2022)
[ Paper] [ Dataset]

12. Adversarial Training Helps Transfer Learning Via Better Representations

Deng, Z.*, Zhang, L.*, Vodrahalli, K., Kawaguchi, K., Zou, J. Y.
NeurIPS (2021)
[ Paper]

11. Predicting Visuo-Motor Diseases From Eye Tracking Data

Vodrahalli, K., Filipkowski, M., Chen, T., Zou, J., Liao, Y. J.
Pacific Symposium on Biocomputing (2022)
[ Paper]

10. TrueImage: A Machine Learning Algorithm to Improve the Quality of Telehealth Photos

Vodrahalli, K.*, Daneshjou, R.*, Novoa, R. A., Chiou, A., Ko, J. M., Zou, J.
Pacific Symposium on Biocomputing (2021)
[ Paper]

9. Serverless Linear Algebra

Shankar, V., Krauth, K., Vodrahalli, K., Pu, Q., Recht, B., Stoica, I., Ragan-Kelley, J., Jonas, E., Venkataraman, S.
ACM Symposium on Cloud Computing (2020)
[ Paper]

8. Blind Interactive Learning of Modulation Schemes: Multi-Agent Cooperation Without Co-Design

Sahai, A.*, Sanz, J.*, Subramanian, V.*, Tran, C.*, Vodrahalli, K.*
IEEE Access (2020)
[ Paper] [ Code]

7. Harmless Interpolation of Noisy Data in Regression

Muthukumar, V., Vodrahalli, K., Subramanian, V., Sahai, A.
IEEE JSAIT (2020)
[ Paper]

6. Some New Numeric Results Concerning the Witsenhausen Counterexample

Subramanian, V., Brink, L., Jain, N., Vodrahalli, K., Jalan, A., Shinde, N., Sahai, A.
Allerton Conference on Communication, Control, and Computing (2018)
[ Paper]

5. 3D Computer Vision Based on Machine Learning With Deep Neural Networks: A Review

Vodrahalli, K., Bhowmik, A. K.
Journal of the Society for Information Display (2017)
[ Paper]

Pre-Prints

4. Can Large Language Models Provide Useful Feedback on Research Papers? A Large-Scale Empirical Analysis

Liang, W., Zhang, Y., Cao, H., Wang, B., Ding, D., Yang, X., Vodrahalli, K., He, S., Smith, D., Yin, Y., Mcfarland, D., Zou, J.
arXiv preprint arXiv:2310.01783 (2023)
[ arXiv]

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

Vodrahalli, K., Zou, J.
arXiv preprint arXiv:2306.08141 (2023)
[ arXiv] [ Code] [ Dataset]

2. Better Knowledge Retention Through Metric Learning

Li, K.*, Peng, S.*, Vodrahalli, K.*, Malik, J.
arXiv preprint arXiv:2011.13149 (2020)
[ arXiv]

1. Are All Training Examples Created Equal? An Empirical Study

Vodrahalli, K., Li, K., Malik, J.
arXiv preprint arXiv:1811.12569 (2018)
[ arXiv]


* = equal contributions