Aniket Rege

WAIV Lab

PhD Student, University

of Wisconsin-Madison

I’m a Ph.D student in Computer Sciences at the University of Wisconsin-Madison, where I spend most of time thinking about heterogeneous preference learning and demographically diverse multimodal generative models. I am fortunate to be jointly advised by Ramya Vinayak and Yong Jae Lee.

Update: I’m spending Summer ‘25 at Meta Reality Labs, working on multimodal contextual AI under Hyo Jin Kim!

Previously, I was an masters student at the University of Washington, Seattle where I worked with the RAIVN Lab advised by Prof. Ali Farhadi and mentored by Aditya Kusupati. My MS research focused on large-scale efficient and deployable machine learning, visual representation learning, and web-scale search.

I am also generally interested in computer vision, information retrieval, efficient+deployable ML, and personalization for generative models. If you are an undergrad or masters student interested in working with me, send me an email (I’ll do my best to reply)!

Reach me: aniketr[at]cs[dot]wisc[dot]edu

news

Mar 21, 2025	I’ll be joining Meta Reality Labs this summer to work on multimodal contextual AI! Excited to be back in Seattle
Jun 18, 2024	PAL is accepted at ICML workshops: TF2M and MHFAIA (oral)! Update (01/22/2025): PAL is accepted at ICLR 2025!
Apr 29, 2024	I gave an hour-long talk about Matryoshka Representation Learning at UW-Madison’s MLOPT Idea Seminar!
Feb 7, 2024	I published a beginner-friendly blog about MRL following OpenAI’s training their new Matryoshka embedding models!
Aug 21, 2023	AdANNS is accepted at NeurIPS 2023! A previous version was also accepted at ICLR ‘23 PML4DC Workshop.

selected publications

PAL: Sample-Efficient Personalized Reward Modeling for Pluralistic Alignment

Daiwei Chen, Yi Chen, Aniket Rege, Zhi Wang, and Ramya Korlakai Vinayak

In The Thirteenth International Conference on Learning Representations, 2025

arXiv Bib Blog Code

@inproceedings{chen2025pal,
  title = {PAL: Sample-Efficient Personalized Reward Modeling for Pluralistic Alignment},
  author = {Chen, Daiwei and Chen, Yi and Rege, Aniket and Wang, Zhi and Korlakai Vinayak, Ramya},
  booktitle = {The Thirteenth International Conference on Learning Representations},
  year = {2025},
}

Matryoshka Representation Learning

Aniket Rege*, Aditya Kusupati*, Gantavya Bhatt*, Matthew Wallingford, Aditya Sinha, Vivek Ramanujan, William Howard-Snyder, Kaifeng Chen, Sham Kakade, Prateek Jain, and Ali Farhadi

In Advances in Neural Information Processing Systems (NeurIPS), 2022

arXiv Bib Blog Code

@inproceedings{kusupati2022matryoshka,
  title = {Matryoshka Representation Learning},
  author = {Rege*, Aniket and Kusupati*, Aditya and Bhatt*, Gantavya and Wallingford, Matthew and Sinha, Aditya and Ramanujan, Vivek and Howard-Snyder, William and Chen, Kaifeng and Kakade, Sham and Jain, Prateek and Farhadi, Ali},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2022},
}