Mamba Policy: Towards Efficient 3D Diffusion Policy with Hybrid Selective State Models

Original Tweet

---

Mamba Policy: Towards Efficient 3D Diffusion Policy with Hybrid Selective State Models https://github.com/SageCao1125/Mamba-Policy Mamba Policy, a lighter yet stronger policy method based on a hybrid state space model integrated with attention mechanisms. Our extensive experiments demonstrate that Mamba Policy achieves up to a 5% improvement in success rate under a variety of manipulation datasets, while reducing the parameter count by 80%.

🔗 원본 링크

• https://github.com/SageCao1125/Mamba-Policy

미디어

---

🔗 Related

• can-we-bridge-the-sim-to-real-gap-in-complex-manipulation-wi-683188 — 주제: Diffusion, Robotics Manipulation
• can-we-bridge-the-sim-to-real-gap-in-complex-manipulation-without-explicit-syste — 주제: Diffusion, Robotics Manipulation
• first-fully-open-action-reasoning-model-arm-can-think-in-3d- — 주제: Robotics Manipulation
• first-fully-open-action-reasoning-model-arm-can-think-in-3d-turn-your-instructio — 주제: Robotics Manipulation
• the-next-evolution-vla-models — 주제: Robotics Manipulation

Tags

3D-Vision Robotics AI-ML