Publications

2026

1. ICCPS
   2026

   LexiSafe: Offline Safe Reinforcement Learning with Lexicographic Safety-Reward Hierarchy

   Hsin-Jung Yang, Zhanhong Jiang, Prajwal Koirala, and 3 more authors

   arXiv preprint arXiv:2602.17312, 2026

   arXiv Bib

   @article{yang2026lexisafe,
     title = {LexiSafe: Offline Safe Reinforcement Learning with Lexicographic Safety-Reward Hierarchy},
     author = {Yang, Hsin-Jung and Jiang, Zhanhong and Koirala, Prajwal and Liu, Qisai and Fleming, Cody and Sarkar, Soumik},
     journal = {arXiv preprint arXiv:2602.17312},
     year = {2026},
   }

2. In
   Submission

   Neural CDEs as Correctors for learned time series models

   Muhammad Bilal Shahid, Zhanhong Jiang, Prajwal Koirala, and 2 more authors

   arXiv preprint arXiv:2512.12116, 2026

   arXiv Bib

   @article{shahid2026neural,
     title = {Neural CDEs as Correctors for learned time series models},
     author = {Shahid, Muhammad Bilal and Jiang, Zhanhong and Koirala, Prajwal and Sarkar, Soumik and Fleming, Cody},
     journal = {arXiv preprint arXiv:2512.12116},
     year = {2026},
   }

3. In
   Submission

   LCLA: Language-Conditioned Latent Alignment for Vision-Language Navigation

   Nitesh Subedi, Adam Haroon, Samuel TK Tetteh, and 3 more authors

   arXiv preprint arXiv:2602.07629, 2026

   arXiv Bib

   @article{subedi2026lcla,
     title = {LCLA: Language-Conditioned Latent Alignment for Vision-Language Navigation},
     author = {Subedi, Nitesh and Haroon, Adam and Tetteh, Samuel TK and Koirala, Prajwal and Fleming, Cody and Sarkar, Soumik},
     journal = {arXiv preprint arXiv:2602.07629},
     year = {2026},
   }

2025

1. RSS
   FM4RoboPlan
   2025

   Can Pretrained Vision-Language Embeddings Alone Guide Robot Navigation?

   Nitesh Subedi^*, Adam Haroon^*, Shreyan Ganguly, and 4 more authors

   arXiv preprint arXiv:2506.14507, 2025

   arXiv Bib

   @article{subedi2025can,
     title = {Can Pretrained Vision-Language Embeddings Alone Guide Robot Navigation?},
     author = {Subedi, Nitesh and Haroon, Adam and Ganguly, Shreyan and Tetteh, Samuel TK and Koirala, Prajwal and Fleming, Cody and Sarkar, Soumik},
     journal = {arXiv preprint arXiv:2506.14507},
     year = {2025},
   }

2. ICLR
   2026

   Flow-Based Single-Step Completion for Efficient and Expressive Policy Learning

   Prajwal Koirala and Cody Fleming

   arXiv preprint arXiv:2506.21427, 2025

   arXiv Bib

   @article{koirala2025flow,
     title = {Flow-Based Single-Step Completion for Efficient and Expressive Policy Learning},
     author = {Koirala, Prajwal and Fleming, Cody},
     journal = {arXiv preprint arXiv:2506.21427},
     year = {2025},
   }

2024

1. ITSC
   2024

   F1tenth Autonomous Racing With Offline Reinforcement Learning Methods

   Prajwal Koirala and Cody Fleming

   In 2024 IEEE 27th International Conference on Intelligent Transportation Systems (ITSC), 2024

   arXiv Bib

   @inproceedings{koirala2024f1tenth,
     title = {F1tenth Autonomous Racing With Offline Reinforcement Learning Methods},
     author = {Koirala, Prajwal and Fleming, Cody},
     booktitle = {2024 IEEE 27th International Conference on Intelligent Transportation Systems (ITSC)},
     pages = {3922--3929},
     year = {2024},
     organization = {IEEE},
   }

2. ICLR
   2025

   Latent Safety-Constrained Policy Approach for Safe Offline Reinforcement Learning

   Prajwal Koirala, Zhanhong Jiang, Soumik Sarkar, and 1 more author

   arXiv preprint arXiv:2412.08794, 2024

   arXiv Bib

   @article{koirala2024latent,
     title = {Latent Safety-Constrained Policy Approach for Safe Offline Reinforcement Learning},
     author = {Koirala, Prajwal and Jiang, Zhanhong and Sarkar, Soumik and Fleming, Cody},
     journal = {arXiv preprint arXiv:2412.08794},
     year = {2024},
   }

3. CDC
   2025

   FAWAC: Feasibility Informed Advantage Weighted Regression for Persistent Safety in Offline Reinforcement Learning

   Prajwal Koirala, Zhanhong Jiang, Soumik Sarkar, and 1 more author

   arXiv preprint arXiv:2412.08880, 2024

   arXiv Bib

   @article{koirala2024fawac,
     title = {FAWAC: Feasibility Informed Advantage Weighted Regression for Persistent Safety in Offline Reinforcement Learning},
     author = {Koirala, Prajwal and Jiang, Zhanhong and Sarkar, Soumik and Fleming, Cody},
     journal = {arXiv preprint arXiv:2412.08880},
     year = {2024},
   }

4. CoRL
   2024

   Solving offline reinforcement learning with decision tree regression

   Prajwal Koirala and Cody Fleming

   In 8th Conference on Robot Learning, 2024

   arXiv Bib

   @inproceedings{koirala2024solving,
     title = {Solving offline reinforcement learning with decision tree regression},
     author = {Koirala, Prajwal and Fleming, Cody},
     booktitle = {8th Conference on Robot Learning},
     year = {2024},
     organization = {PMLR},
   }