Haoxiang Ren — accepted AI-conference papers

2026

Speedup Patch: Learning a Plug-and-Play Policy to Accelerate Embodied Manipulation

Zhichao Wu, Junyin Ye, Zhilong Zhang, Yihao Sun, Haoxin Lin, Jiaheng Luo +3

ICML 2026poster

While current embodied policies exhibit remarkable manipulation skills, their execution remains unsatisfactorily slow as they inherit the tardy pacing of human demonstrations. Existing acceleration methods typically require policy retraining or costly online interactions, limiting their scalability …

Cited by 0 Source ↗Scholar ↗

2026

Towards Practical World Model-based Reinforcement Learning for Vision-Language-Action Models

Zhilong Zhang, Haoxiang Ren, Yihao Sun, Yifei Sheng, Haonan Wang, Zhichao Wu +3

ICML 2026poster

Vision-Language-Action (VLA) models show strong generalization for robotic control, but finetuning them with reinforcement learning (RL) is constrained by the high cost and safety risks of real-world interaction. Training VLA models in interactive world models avoids these issues but introduces seve…

Cited by 0 Source ↗Scholar ↗