9 papers
Diagnosing Compositional Generalization in Sequential Robot Tasks
Yixiao Wang, Cheng-En Wu, Lingfeng Sun +5
Sequential robot manipulation requires policies to execute novel combinations of familiar instruction components. However, collecting demonstrations for all possible instruction tu…
CLIFT: Turning Gemini Robotics On-Device into Humanoid Specialists via Non-Invasive Closed-Loop Iterative Fine-Tuning
Yuxin Chen, Hari Srikanth, Nathan Jew +7
While robot foundation models are growing increasingly capable, the strongest models are typically trained on proprietary data and remain closed-source, limiting downstream users'…
REAR: Test-time Preference Realignment through Reward Decomposition
Fuxiang Zhang, Pengcheng Wang, Chenran Li +6
Aligning large language models (LLMs) with diverse user preferences is a critical yet challenging task. While post-training methods can adapt models to specific needs, they often r…
DADP: Domain Adaptive Diffusion Policy
Pengcheng Wang, Qinghang Liu, Haotian Lin +4
Learning domain adaptive policies that can generalize to unseen transition dynamics, remains a fundamental challenge in learning-based control. Substantial progress has been made t…
DiscreteRTC: Discrete Diffusion Policies are Natural Asynchronous Executors
Pengcheng Wang, Kaiwen Hong, Chensheng Peng +4
Unlike chatbots, physical AI must act while the world keeps evolving. Therefore, the inter-chunk pause of synchronous executors are fatal for dynamic tasks regardless of how fast t…
Mean Flow Policy with Instantaneous Velocity Constraint for One-step Action Generation
Guojian Zhan, Letian Tao, Pengcheng Wang +6
Learning expressive and efficient policy functions is a promising direction in reinforcement learning (RL). While flow-based policies have recently proven effective in modeling com…