2025/09/01 by Yan Ge, Yan, Ge, Jiyue Zhu +18 · 6 citations
Computer Science · Engineering · #FOS: Computer and information sciences #Multimodal Machine Learning Applications #Reinforcement Learning in Robotics #Robot Manipulation and Learning #Robotics (cs.RO)
paper · pdf · doi:10.48550/arxiv.2509.01819
openalex publication_date 2025/09/01 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28
This paper introduces ManiFlow, a visuomotor imitation learning policy for general robot manipulation that generates precise, high-dimensional actions conditioned on diverse visual, language and proprioceptive inputs. We leverage flow matching with consistency training to enable high-quality dexterous action generation in just 1-2 inference steps. To handle diverse input modalities efficiently, we propose DiT-X, a diffusion transformer architecture with adaptive cross-attention and AdaLN-Zero conditioning that enables fine-grained feature interactions between action tokens and multi-modal observations. ManiFlow demonstrates consistent improvements across diverse simulation benchmarks and nearly doubles success rates on real-world tasks across single-arm, bimanual, and humanoid robot setups with increasing dexterity. The extensive evaluation further demonstrates the strong robustness and generalizability of ManiFlow to novel objects and background changes, and highlights its strong scaling capability with larger-scale datasets. Our website: maniflow-policy.github.io.