News

• 26 January, 2026: Our paper Koopman-Assisted Trajectory Synthesis: A Data Augmentation Framework for Offline Imitation Learning has been accepted by The 14th International Conference on Learning Representations (ICLR), Main Track, 2026.
• 26 January, 2026: Our paper Dynamics‑Aligned Diffusion Planning for Offline RL: A Unified Framework with Forward and Inverse Guidance has been accepted by Transactions on Machine Learning Research (TMLR), as a regular paper.
• 8 November, 2025: Our paper Variational OOD State Correction for Offline Reinforcement Learning has been accepted by The 40th Annual AAAI Conference on Artificial Intelligence (AAAI), Main Technical Track, 2026.
• 29 October, 2025: Our paper Beyond Non-Expert Demonstrations: Outcome-Driven Action Constraint for Offline Reinforcement Learning has been accepted by Pattern Recognition, Elsevier, as a regular paper.
• 29 September, 2025: Our paper Towards Reliable Offline Reinforcement Learning via Lyapunov Uncertainty Control has been accepted by IEEE Transactions on Neural Networks and Learning Systems as a regular paper.
• From 14 April, 2025: I started working as a visiting researcher at Machine Learning & Systems Laboratory, Graduate School of Information Science and Technology. My advisor here is Professor Yoshinobu Kawahara.
• 21 March, 2025: Our paper RoGA: Towards Generalizable Deepfake Detection through Robust Gradient Alignment has been accepted by IEEE International Conference on Multimedia & Expo (ICME) 2025 (Oral).
• 25 September, 2023: Our paper Recovering from out-of-sample states via inverse dynamics in offline reinforcement learning has been accepted by The 36th Annual Conference on Neural Information Processing Systems (NeurIPS), Main Track, 2023.

Education

• (B.Sc.) 2015.9-2019.6, School of computer science, Nanjing University of Information Science and Technology.
• (M.Sc.) 2019.9-2022.4, College of Computer Science and Technology, Nanjing University of Aeronautics and Astronautics, Advisor: Prof. Xiaoyang Tan.
• (Ph.d. student) 2022.4-, College of Computer Science and Technology, Nanjing University of Aeronautics and Astronautics, Advisor: Prof. Xiaoyang Tan.

Research Interests

• (Robust & Generalizable & Safe & Offline) Reinforcement learning
• Generative models for long-horizon planning
• Cross-domain classification (Videos & Image)

Publications (†:Equal Contribution)

• Wang J, He P, Jiang K, Tan X. Koopman-Assisted Trajectory Synthesis: A Data Augmentation Framework for Offline Imitation Learning.The 14th International Conference on Learning Representations (ICLR), 2026. [link].
• †Wang Z, †Jiang K, Tan X. Dynamics‑Aligned Diffusion Planning for Offline RL: A Unified Framework with Forward and Inverse Guidance. Transactions on Machine Learning Research (TMLR), 2026.[link].
• †Jiang K, †Jiang W, Tan X. Variational OOD State Correction for Offline Reinforcement Learning. Annual AAAI Conference on Artificial Intelligence (AAAI), 2026, 40.[link].
• Jiang K, Jiang W, Li Y, Tan X. Beyond Non-Expert Demonstrations: Outcome-Driven Action Constraint for Offline Reinforcement Learning. Pattern Recognition, 2025.[link].
• Jiang K, Li Y, Tan X. Towards Reliable Offline Reinforcement Learning via Lyapunov Uncertainty Control. IEEE Transactions on Neural Networks and Learning Systems, 2025.[link].
• Qiu L, Jiang K, Tan X. RoGA: Towards Generalizable Deepfake Detection through Robust Gradient Alignment. IEEE International Conference on Multimedia & Expo (ICME), (Oral), 2025.[link].
• Qiu L, Jiang K, Tan X. Multi-level Distributional Discrepancy Enhancement for Cross Domain Face Forgery Detection. Chinese Conference on Pattern Recognition and Computer Vision (PRCV), 2024, 508-522.
• Jiang K, Yao J, Tan X. Recovering from out-of-sample states via inverse dynamics in offline reinforcement learning. Advances in Neural Information Processing Systems (NeurIPS), 2023, 36.[link].
• Shen J, Jiang K, Tax X. Boundary Data Augmentation for Offline Reinforcement Learning. ZTE Communications, 2023, 21(3): 29.

Project Experiecne

• A Research on Offline Reinforcement Learning Methods and Theories on Complex Real-world Scenarios (National Natural Science Foundation of China, No.6247072715, Leader: Xiaoyang Tan).

Preprints & Under Review (†:Equal Contribution)

• †Qiu L, †Jiang K, Tan X. Contrastive Desensitization Learning for Cross Domain Face Forgery Detection.

Talks

• Reinforcement Learning and Its Applications. (Jan, 2026, Invited Seminar, VeriSilicon, Chengdu, China)
• Safe Data Augmentation for Robust Offline Reinforcement Learning. (Dec, 2025, Personal Seminar, Machine Learning & Systems Laboratory, The University of Osaka, Japan)
• Reliable Long-Horizon Planning Based on Diffusion Model for Offline Reinforcement Learning. (Jul, 2025, Personal Seminar, Machine Learning & Systems Laboratory, The University of Osaka, Japan)
• Application of Koopman Theory in Generalizable Offline Reinforcement Learning. (Jan, 2025, Personal Seminar, Machine Learning & Systems Laboratory, The University of Osaka, Japan)
• Offline reinforcement learning from non-expert data via state-supported boostrapping. (Nov, 2024, A3 Foresight Program, Beijing, China)

Fundings

• December 2025, Doctoral International Academic Exchange Funding, Nanjing University of Aeronautics and Astronautics (No.5).
• April 2025 - October 2025, Short Visit Program, Nanjing University of Aeronautics and Astronautics (No.241206DF16).

Academic & Working Activities

• Reviewer of international conferences, including NeurIPS, ICLR, ICML, AAAI, ICME.
• Teaching Assistant of “Machine learning and its applications 2023” (by Professor Xiaoyang Tan) at Nanjing University of Aeronautics and Astronautics.

Hobbies

Fitness, Food, Traveling