Research map / 3D vision / 3D generation
RoboFlow4D: A Lightweight Flow World Model Toward Real-Time Flow-Guided Robotic Manipulation
Sixu Lin, Junliang Chen, Huaiyuan Xu, Zhuohao Li, Guangming Wang, Yixiong Jing, Sheng Xu, Runyi Zhao, Brian Sheil, Lap-Pui Chau, Guiliang Liu
Read the paperCheck your idea against 137,217 papers
AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Measured effects reported in the paper
| What was changed | Where | Measured | Effect |
|---|---|---|---|
| add RoboFlow4D flow guidance | DP · LIBERO (average) | success rate (%): 78.9 -> 85.1 | Improved |
| add RoboFlow4D flow guidance | DiT · LIBERO (average) | success rate (%): 83.7 -> 87.7 | Improved |
| add RoboFlow4D flow guidance | DP · ManiSkill3 (average) | success rate (%): 12.3 -> 22.0 | Improved |
| add RoboFlow4D flow guidance | DiT · ManiSkill3 (average) | success rate (%): 12.7 -> 23.7 | Improved |
| add RoboFlow4D flow guidance | DP · real-world (average) | success rate (%): 27.5 -> 40.0 | Improved |
| add RoboFlow4D flow guidance | DiT · real-world (average) | success rate (%): 32.5 -> 43.8 | Improved |
| add RoboFlow4D flow guidance | DP · real-world (average) | completion time (s): 38.2 -> 36.8 | Improved |
| add RoboFlow4D flow guidance | DiT · real-world (average) | completion time (s): 39.5 -> 38.3 | Improved |
| add context token (ablation) | RoboFlow4D · LIBERO evaluation set | 3D l2 error: 0.0152 -> 0.0142 | Improved |
| add query points (ablation) | RoboFlow4D · LIBERO evaluation set | 3D l2 error: 0.0158 -> 0.0142 | Improved |
| add 3D alignment with VGGT (ablation) | RoboFlow4D · LIBERO evaluation set | 3D l2 error: 0.0160 -> 0.0142 | Improved |
| vary slow-fast ratio r from 4 to 1 (ablation) | DP + RoboFlow4D · LIBERO-10 | success rate (%): 71.0 -> 72.0 | No clear effect |
Closest papers by meaning
- FLIP: Flow-Centric Generative Planning as General-Purpose Manipulation World Model (ICLR 2025 · similarity 0.89)
- FlowPolicy: Enabling Fast and Robust 3D Flow-Based Policy via Consistency Flow Matching for Robot Manipulation (AAAI 2025 · similarity 0.89)
- FlowRAM: Grounding Flow Matching Policy with Region-Aware Mamba Framework for Robotic Manipulation (CVPR 2025 · similarity 0.89)
- RoboScape: Physics-informed Embodied World Model (NeurIPS 2025 · similarity 0.88)
- PIVOT-R: Primitive-Driven Waypoint-Aware World Model for Robotic Manipulation (NeurIPS 2024 · similarity 0.88)
- DynaRend: Learning 3D Dynamics via Masked Future Rendering for Robotic Manipulation (NeurIPS 2025 · similarity 0.88)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.
