Junyin Ye

6 papers · 2023–2025 · 3 venues · across top CS/AI venues

Authors are matched by name, so researchers who share a name ("Yang Liu", "Wei Wang") appear as a single profile and their paper counts, venues and achievements are combined. How identity is handled.

Achievements

Jump to papers ↓

🌍 Conference Polyglot · Bronze 🌉 Interdisciplinary Bridge · Silver 🗺️ Taxonomy Completionist (14) 🐣 Hot Topic Early Bird

Venues

ICML (3) ICLR (2) AAAI (1)

Top co-authors

Yang Yu (6) Yihao Sun (4) Jiaji Zhang (4) Zhilong Zhang (3) Haoxin Lin (3) Yi-Chen Li (2) Chengxing Jia (2) Yu-Yan Xu (2) Zongzhang Zhang (1) Kai Xu (1)

Research topics

Machine Learning (5) Reinforcement Learning (5) Methods (5) Artificial Intelligence (2) Deep Learning (2) Robotics (2) Capabilities (2) Learning Types (2) Optimization & Theory (2) Application Areas (1) Architectures (1) Core AI (1) Learning Paradigms (1) Models (1)

Keywords

offline reinforcement learning (3) dynamics model (2) model-based reinforcement learning (2) imitation learning (2) sample efficiency (2) diffusion model (1) ensemble method (1) meta-reinforcement learning (1) trajectory generation (1) credit assignment (1) imperfect demonstration (1) dynamic environment (1) compounding error (1) delayed reward (1) episodic return decomposition (1) proxy reward (1) single demonstration (1) reweighting (1) policy (1) demonstration transformer (1)

Papers

Any-step Dynamics Model Improves Future Predictions for Online and Offline Reinforcement Learning ICLR 2025 Deep Demonstration Tracing: Learning Generalizable Imitator Policy for Runtime Imitation from a Single Demonstration ICML 2024 Episodic Return Decomposition by Difference of Implicitly Assigned Sub-trajectory Reward AAAI 2024 Flow to Better: Offline Preference-based Reinforcement Learning via Preferred Trajectory Generation ICLR 2024 Limited Preference Aided Imitation Learning from Imperfect Demonstrations ICML 2024 Model-Bellman Inconsistency for Model-based Offline Reinforcement Learning ICML 2023