publications

2026

1. COLM W

   

   Playing with Fire: What Transfers When RL Trains a Language Agent?

   Mahesh Ramesh, Kaousheik Jayakumar, Hemanth Ram, Pavan Thodima, Ramani Duraiswami, Dinesh Manocha, Aniket Rege†, and Manolis Vlatakis†

   In COLM 2026 Workshop on Efficient Reasoning, 2026

   🚨 Spotlight

   Bib PDF

   @inproceedings{ramesh2026playing,
     title = {Playing with Fire: What Transfers When {RL} Trains a Language Agent?},
     author = {Ramesh, Mahesh and Jayakumar, Kaousheik and Ram, Hemanth and Thodima, Pavan and Duraiswami, Ramani and Manocha, Dinesh and Rege†, Aniket and Vlatakis†, Manolis},
     booktitle = {COLM 2026 Workshop on Efficient Reasoning},
     year = {2026},
   }

2. ICML

   

   Sparks of Cooperative Reasoning: LLMs as Strategic Hanabi Agents

   Mahesh Ramesh, Kaousheik Jayakumar, Aswinkumar Ramkumar, Pavan Thodima, Aniket Rege†, and Manolis Vlatakis†

   In Forty-third International Conference on Machine Learning (ICML), 2026

   arXiv Bib Blog Code

   Citations 6

   @inproceedings{ramesh2026sparks,
     title = {Sparks of Cooperative Reasoning: {LLM}s as Strategic Hanabi Agents},
     author = {Ramesh, Mahesh and Jayakumar, Kaousheik and Ramkumar, Aswinkumar and Thodima, Pavan and Rege†, Aniket and Vlatakis†, Manolis},
     booktitle = {Forty-third International Conference on Machine Learning (ICML)},
     year = {2026},
   }

3. ACL

   

   Agentic Very Long Video Understanding

   Aniket Rege, Arka Sadhu, Yuliang Li, Kejie Li, Ramya Korlakai Vinayak, Yuning Chai, Yong Jae Lee, and Hyo Jin Kim

   In Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (ACL), 2026

   🚨 Recommended Spotlight

   arXiv Bib Blog Code

   Citations 20

   @inproceedings{rege2025agentic,
     title = {Agentic Very Long Video Understanding},
     author = {Rege, Aniket and Sadhu, Arka and Li, Yuliang and Li, Kejie and Korlakai Vinayak, Ramya and Chai, Yuning and Lee, Yong Jae and Kim, Hyo Jin},
     booktitle = {Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (ACL)},
     year = {2026},
   }

2025

1. ICCV

   

   CuRe: Cultural Gaps in the Long Tail of Text-to-Image Systems

   Aniket Rege, Zinnia Nie, Mahesh Ramesh, Unmesh Raskar, Zhuoran Yu, Aditya Kusupati†, Yong Jae Lee†, and Ramya Korlakai Vinayak†

   In Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV), 2025

   arXiv Bib Blog Code

   Citations 5

   @inproceedings{rege2025cure,
     title = {CuRe: Cultural Gaps in the Long Tail of Text-to-Image Systems},
     author = {Rege, Aniket and Nie, Zinnia and Ramesh, Mahesh and Raskar, Unmesh and Yu, Zhuoran and Kusupati†, Aditya and Lee†, Yong Jae and Korlakai Vinayak†, Ramya},
     booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)},
     year = {2025},
   }

2. ICLR

   

   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 (ICLR), 2025

   arXiv Bib Blog Code

   Citations 121

   @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 (ICLR)},
     year = {2025},
   }

3. Patent

   

   Method and electronic device for detecting candid moment in image frame

   Aniket Rege*, Gaurav Ramola*, Nikhar Maheshwari*, Sudha Velusamy, Girish Kulkarni, Sai Pranav Mathivanan, Swadha Jaiswal, and Pradeep Kumar Vegireddi

   2025

   US Patent 12,299,959

2023

1. NeurIPS

   

   AdANNS: A Framework for Adaptive Semantic Search

   Aniket Rege*, Aditya Kusupati*, Sharan Ranjit S, Alan Fan, Qingqing Cao, Sham Kakade, Prateek Jain, and Ali Farhadi

   In Advances in Neural Information Processing Systems (NeurIPS), 2023

   arXiv Bib Code

   Citations 23

   @inproceedings{rege2023adanns,
     title = {AdANNS: A Framework for Adaptive Semantic Search},
     author = {Rege*, Aniket and Kusupati*, Aditya and Ranjit S, Sharan and Fan, Alan and Cao, Qingqing and Kakade, Sham and Jain, Prateek and Farhadi, Ali},
     booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
     year = {2023},
   }

2022

1. NeurIPS

   

   Matryoshka Representation Learning

   Aditya Kusupati*, Gantavya Bhatt*, Aniket Rege*, 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 Talk

   Citations 720

   @inproceedings{kusupati2022matryoshka,
     title = {Matryoshka Representation Learning},
     author = {Kusupati*, Aditya and Bhatt*, Gantavya and Rege*, Aniket 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},
   }

2. Patent

   

   Method and electronic device for processing facial images

   Sudha Velusamy, Rahul Varna, Raviprasad Kini, Aniket Rege, Rishubh Parihar, and Daeyoung Hyun

   2022

   US Patent 11,335,122

   Citations 5

2021

1. ICCV W

   

   Spatio-temporal video representation learning for AI-based video playback style prediction

   Rishubh Parihar*, Gaurav Ramola*, Ranajit Saha, Raviprasad Kini, Aniket Rege, and Sudha Velusamy

   IEEE/CVF International Conference on Computer Vision (ICCV) Workshops, 2021

   arXiv Bib

   Citations 1

   @article{parihar2021spatio,
     title = {Spatio-temporal video representation learning for AI-based video playback style prediction},
     author = {Parihar*, Rishubh and Ramola*, Gaurav and Saha, Ranajit and Kini, Raviprasad and Rege, Aniket and Velusamy, Sudha},
     journal = {IEEE/CVF International Conference on Computer Vision (ICCV) Workshops},
     year = {2021},
   }

2020

1. CVPR W

   

   FabSoften: Face beautification via dynamic skin smoothing, guided feathering, and texture restoration

   Sudha Velusamy, Rishubh Parihar, Raviprasad Kini, and Aniket Rege

   In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) Workshops, 2020

   Bib PDF Code

   Citations 25

   @inproceedings{velusamy2020fabsoften,
     title = {FabSoften: Face beautification via dynamic skin smoothing, guided feathering, and texture restoration},
     author = {Velusamy, Sudha and Parihar, Rishubh and Kini, Raviprasad and Rege, Aniket},
     booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) Workshops},
     pages = {530--531},
     year = {2020},
   }

2018

1. 

   QUIC protocol performance in wireless networks

   Prashant K Kharat*, Aniket Rege*, Aneesh Goel*, and Muralidhar Kulkarni

   In 2018 International Conference on Communication and Signal Processing (ICCSP), 2018

   Bib

   Citations 22

   @inproceedings{kharat2018quic,
     title = {QUIC protocol performance in wireless networks},
     author = {Kharat*, Prashant K and Rege*, Aniket and Goel*, Aneesh and Kulkarni, Muralidhar},
     booktitle = {2018 International Conference on Communication and Signal Processing (ICCSP)},
     pages = {0472--0476},
     year = {2018},
     organization = {IEEE},
   }