publications

2025

1. Accelerating Vision Transformers with Adaptive Patch Sizes

   Rohan Choudhury, JungEun Kim, Jinhyung Park, and 3 more authors

   arXiv preprint, 2025

   arXiv Bib Project Page Code

   @article{choudhury2025apt,
     title = {Accelerating Vision Transformers with Adaptive Patch Sizes},
     author = {Choudhury, Rohan and Kim, JungEun and Park, Jinhyung and Yang, Eunho and Jeni, László A. and Kitani, Kris M.},
     journal = {arXiv preprint},
     year = {2025},
     site = {/apt/}
   }

2. MAVERIX: Multimodal Audio-Visual Evaluation Reasoning IndeX

   Liuyue Xie, George Z. Wei, Avik Kuthiala, and 12 more authors

   2025

   arXiv Bib HTML

   @misc{xie2025maverix,
     title = {MAVERIX: Multimodal Audio-Visual Evaluation Reasoning IndeX},
     author = {Xie, Liuyue and Wei, George Z. and Kuthiala, Avik and Zheng, Ce and Bal, Ananya and Dabhi, Mosam and Wen, Liting and Rustagi, Taru and Lai, Ethan and Khyalia, Sushil and Choudhury, Rohan and Ziyadi, Morteza and Zhang, Xu and Yang, Hao and Jeni, László A.},
     abbr_author = {L. Xie*, R. Choudhury*, et al.},
     year = {2025},
   }

2024

1. 

   Don’t Look Twice: Faster Video Transformers with Run-Length Tokenization

   Rohan Choudhury, Guanglei Zhu, Sihan Liu, and 3 more authors

   NeurIPS, 2024 (spotlight, top 3%)

   arXiv Bib Project Page Code

   @article{choudhury2024rlt,
     title = {Don't Look Twice: Faster Video Transformers with Run-Length Tokenization},
     author = {Choudhury, Rohan and Zhu, Guanglei and Liu, Sihan and Niinuma, Koichiro and Kitani, Kris M. and Jeni, László A.},
     journal = {NeurIPS},
     year = {2024},
     site = {/rlt/},
     spotlight = true
   }

2. ECCV

   Video Question Answering with Procedural Programs

   Rohan Choudhury, Koichiro Niinuma, Kris M. Kitani, and 1 more author

   ECCV, 2024

   arXiv Bib HTML

   @article{choudhury2024proviq,
     title = {Video Question Answering with Procedural Programs},
     author = {Choudhury, Rohan and Niinuma, Koichiro and Kitani, Kris M. and Jeni, László A.},
     journal = {ECCV},
     year = {2024},
   }

3. ICRA

   JaywalkerVR: A VR System for Collecting Safety-Critical Pedestrian-Vehicle Interactions

   Kenta Mukoya, Erica Weng, Rohan Choudhury, and 1 more author

   ICRA, 2024

   arXiv Bib

   @article{mukoya2024jaywalker,
     title = {JaywalkerVR: A VR System for Collecting Safety-Critical Pedestrian-Vehicle Interactions},
     author = {Mukoya, Kenta and Weng, Erica and Choudhury, Rohan and Kitani, Kris M.},
     journal = {ICRA},
     year = {2024},
   }

2023

1. ICCV

   TEMPO: Efficient Multi-View Pose Estimation, Tracking, and Forecasting

   Rohan Choudhury, Kris M. Kitani, and László A. Jeni

   ICCV, 2023

   arXiv Bib HTML Code

   @article{choudhury2023tempo,
     title = {TEMPO: Efficient Multi-View Pose Estimation, Tracking, and Forecasting},
     author = {Choudhury, Rohan and Kitani, Kris M. and Jeni, László A.},
     journal = {ICCV},
     year = {2023},
   }