Dr. Jun Jin | Publications | University of Alberta

Publications

For a full metric profile, please visit my Google Scholar profile.

Journals & Conference Proceedings

K. Sun, H. Zhang, J. Jin, C. Gao, X. Chen, W. Liu, and L. Kong, “Principled Fast and Meta Knowledge Learners for Continual Reinforcement Learning,” in International Conference on Learning Representations (ICLR), 2026.
X. Ge, M. Lu, and J. Jin, “Applying deep reinforcement learning for construction labour dispatching in a union hall setting,” Automation in Construction, vol. 184, 106838, April 2026.
R. H. Yang, X. Zhao, L. M. Brunswic, M. Alban, M. Clemente, T. Cao, J. Jin, and A. Rasouli, “CAPE: Context-Aware Diffusion Policy Via Proximal Mode Expansion for Collision Avoidance,” in IEEE International Conference on Robotics and Automation (ICRA), 2026.
Y. Hu, Y. Ou, A. Sieben, Z. Samadikhoshkho, B. Zheng, J. Jin, and M. Tavakoli, “Learning from imperfect demonstrations in a surgical training task,” Biomedical Signal Processing and Control, vol. 112, 108487, Feb 2026.
D. Shi and J. Jin, “FRMD: Fast Robot Motion Diffusion with Consistency-Distilled Movement Primitives for Smooth Action Generation,” in Robotics & Intelligent Systems Expo (RISEx), Selected for Oral Presentation, 2025.
Y. Hu, M. Tavakoli, and J. Jin, “Transferring Human Daily Activity Skills to Surgical Robots via Deep Successor Features,” in Robotics & Intelligent Systems Expo (RISEx), 2025.
Y. Hu, M. Tavakoli, and J. Jin, “Pretraining using comparable human activities of daily living dataset in robotic surgical task learning,” IEEE Transactions on Medical Robotics and Bionics, 2025. Accepted May 2025, published June 2025.
X. Ye, R. H. Yang, J. Jin, Y. Li, and A. Rasouli, “Ra-dp: Rapid adaptive diffusion policy for training-free high-frequency robotics replanning,” in Proceedings of the IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), 2025. Accepted June 2025, to appear July 2025.
Y. Hu, Z. Samadikhoshkho, J. Jin, and M. Tavakoli, “Label-free adaptive gaussian sample consensus framework for learning from perfect and imperfect demonstrations,” IEEE Transactions on Medical Robotics and Bionics, 2024.
Y. Hu, J. Jin, and M. Tavakoli, “Learning medical skills by a robot from imperfect demonstrations,” in Alberta Robotics & Intelligent Systems Expo (RISE), (Edmonton, AB), 2024.
Y. Mu, Q. Zhang, M. Hu, W. Wang, M. Ding, J. Jin, B. Wang, J. Dai, Y. Qiao, and P. Luo, “Embodiedgpt: Vision-language pre-training via embodied chain of thought,” in Advances in Neural Information Processing Systems (NeurIPS), Spotlight Paper, 2023.
H. Zhang, C. Xiao, H. Wang, J. Jin, B. Xu, and M. Muller, “Replay memory as an empirical mdp: Combining conservative estimation with experience replay,” in International Conference on Learning Representations (ICLR), 2023. Presented on May 1st, 2023, Kigali, Rwanda.
A. Karimi, J. Jin, J. Luo, A. R. Mahmood, M. Jagersand, and S. Tosatto, “Variable decision-frequency option critic,” in 2023 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), IEEE, 2023.
B. Rafiee, S. Ghiassian, J. Jin, R. Sutton, J. Luo, and A. White, “Auxiliary task discovery through generate and test,” in Second Conference on Lifelong Learning Agents (CoLLAs), 2023.
J. Jin, D. Graves, C. Haigh, J. Luo, and M. Jagersand, “Offline learning of counterfactual predictions for real-world robotic reinforcement learning,” in 2022 IEEE International Conference on Robotics and Automation (ICRA) Oustanding Student Paper Award Finalist, pp. 3616–3623, IEEE, 2022.
J. Jin and M. Jagersand, “Generalizable task representation learning from human demonstration videos: a geometric approach,” in 2022 IEEE International Conference on Robotics and Automation (ICRA), pp. 2504–2510, IEEE, 2022.
L. Petrich, J. Jin, M. Dehghan, and M. Jagersand, “A quantitative analysis of activities of daily living: Insights into improving functional independence with assistive robotics,” in 2022 International Conference on Robotics and Automation (ICRA), pp. 6999–7006, IEEE, 2022.
J. Jin, H. Zhang, and J. Luo, “Build generally reusable agent-environment interaction models,” in Advances in neural information processing systems (NeurIPS) 2022 Workshop: Foundation Models for Decision Making, 2022.
Z. Zhang, J. Jin, M. Jagersand, J. Luo, and D. Schuurmans, “A simple decentralized cross-entropy method,” in Advances in neural information processing systems (NeurIPS), vol. 34, pp. 29304–29320, 2022.
B. Rafiee, J. Jin, J. Luo, and A. White, “What makes useful auxiliary tasks in reinforcement learning: investigating the effect of the target policy,” in The 5th Multidisciplinary Conference on Reinforcement Learning and Decision Making, RLDM, 2022.
D. Graves, N. M. Nguyen, K. Hassanzadeh, J. Jin, and J. Luo, “Learning robust driving policies without online exploration,” in 2021 IEEE International Conference on Robotics and Automation (ICRA), pp. 13186–13193, IEEE, 2021.
B. Xie, M. Han, J. Jin, M. Barczyk, and M. Jagersand, “A generative model-based predictive display for robotic teleoperation,” in 2021 IEEE International Conference on Robotics and Automation (ICRA), pp. 2407–2413, IEEE, 2021.
J. Jin, N. M. Nguyen, N. Sakib, D. Graves, H. Yao, and M. Jagersand, “Mapless navigation among dynamics with social-safety-awareness: a reinforcement learning approach from 2d laser scans,” in 2020 IEEE international conference on robotics and automation (ICRA), pp. 6979–6985, IEEE, 2020.
J. Jin, L. Petrich, M. Dehghan, and M. Jagersand, “A geometric perspective on visual imitation learning,” in 2020 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), pp. 5194–5200, IEEE, 2020.
J. Jin, L. Petrich, Z. Zhang, M. Dehghan, and M. Jagersand, “Visual geometric skill inference by watching human demonstration,” in 2020 IEEE International Conference on Robotics and Automation (ICRA), pp. 8985–8991, IEEE, 2020.
J. Jin, L. Petrich, M. Dehghan, Z. Zhang, and M. Jagersand, “Robot eye-hand coordination learning by watching human demonstrations: a task function approximation approach,” in 2019 International Conference on Robotics and Automation (ICRA), pp. 6624–6630, IEEE, 2019.
M. Dehghan, Z. Zhang, M. Siam, J. Jin, L. Petrich, and M. Jagersand, “Online object and task learning via human robot interaction,” in 2019 IEEE International Conference on Robotics and Automation (ICRA), pp. 2132–2138, IEEE, 2019.
X. Qin, S. He, Z. Zhang, M. Dehghan, J. Jin, and M. Jagersand, “Real-time edge template tracking via homography estimation,” in 2018 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), pp. 607–612, IEEE, 2018.

Workshop Papers & Extended Abstracts

A. Ebrahimi and J. Jin, “Retrospective and structurally informed exploration via cross-task successor feature similarity,” in ICML Workshop on Exploration in AI Today, 2025. Accepted May 2025, published July 2025.
K. Sun, J. Jin, X. Chen, W. Liu, and L. Kong, “Reweighted bellman targets for continual reinforcement learning,” in ICML Workshop on Aligning Reinforcement Learning Experimentalists and Theorists, 2024. Accepted June 2024, published July 2024.
Q. Li, Y. Cao, J. Kang, T. Yang, X. Chen, J. Jin, and M. Taylor, “Laffi: Leveraging hybrid natural language feedback for fine-tuning language models,” in The 38th Annual AAAI Conference on Artificial Intelligence (AAAI 2024) Workshop: Human-Centric Representation Learning, Best Paper Runner-up, 2024. Accepted Dec 2023, published Feb 2024.