JAMB: Joint Action-Motion Diffusion for Bimanual Manipulation

arXiv:2609.25322 · cs.RO · Submitted 2026-09-21 · Read on arXiv

cs.RO

Submitted: 2026-09-21

Updated: 2026-10-01

Project page: https://jam-bimanual.github.io

Terminology

• Generalization — 14× in this paper · explained in 13 episodes
• Ablation — 13× in this paper · explained in 1 episode
• Grounding — 8× in this paper · explained in 3 episodes
• Transformer — 7× in this paper · explained in 2 episodes
• Accuracy — 5× in this paper · explained in 1 episode
• Benchmark — 3× in this paper · explained in 2 episodes
• Fine-Tuning — 3× in this paper · explained in 5 episodes
• World Model — 3× in this paper · explained in 7 episodes
• Actor — 2× in this paper · explained in 3 episodes
• Embeddings — 2× in this paper · explained in 2 episodes
• Ablation Studies — 1× in this paper · explained in 1 episode
• Ablation study — 1× in this paper · explained in 1 episode
• Cross-Embodiment Transfer — 1× in this paper · explained in 2 episodes
• Diffusion Model — 1× in this paper · explained in 8 episodes
• Diffusion Models — 1× in this paper · explained in 6 episodes
• Feature Extraction — 1× in this paper · explained in 2 episodes
• Optical Flow — 1× in this paper · explained in 2 episodes
• Robustness — 1× in this paper · explained in 5 episodes
• Trace — 1× in this paper · explained in 2 episodes
• Variational Autoencoder (VAE) — 1× in this paper · explained in 3 episodes

Sources

• Action-Geometry Prediction with 3D Geometric Prior for Bimanual Manipulation
• Prediction with Action: Visual Policy Learning via Joint Denoising Process
• Geometric Action Model for Robot Policy Learning
• Point Tracking Improves World Action Models
• RoboTwin 2.0: A Scalable Data Generator and Benchmark with Strong Domain Randomization for Robust Bimanual Robotic Manipulation
• 3D Diffusion Policy: Generalizable Visuomotor Policy Learning via Simple 3D Representations
• MonoDuo: Using One Robot Arm to Learn Bimanual Policies
• EnergyAction: Unimanual to Bimanual Composition with Energy-Based Models
• 3D FlowMatch Actor: Unified 3D Policy for Single- and Dual-Arm Manipulation
• 3D Diffuser Actor: Policy Diffusion with 3D Scene Representations
• Unified Video Action Model
• DiT4DiT: Jointly Modeling Video Dynamics and Actions for Generalizable Robot Control
• Motubrain: An Advanced World Action Model for Robot Control
• Fast-WAM: Do World Action Models Need Test-time Future Imagination?
• Future Optical Flow Prediction Improves Robot Control & Video Generation
• AMPLIFY: Actionless Motion Priors for Robot Learning from Videos
• Any-point Trajectory Modeling for Policy Learning
• Track2Act: Predicting Point Tracks from Internet Videos enables Generalizable Robot Manipulation

Related papers

• FMT x: An Efficient and Asymptotically Optimal Extension of the Fast Marching Tree for Dynamic Replanning
• MPCFormer: A physics-informed data-driven approach for explainable socially-aware autonomous driving
• RoboLab: A High-Fidelity Simulation Benchmark for Analysis of Task Generalist Policies
• HRDexDB: A 4D Dexterous Grasping Dataset Across Human and Multiple Robot Embodiments
• APT: Action Expert Pretraining Improves Instruction Generalization of Vision-Language-Action Policies
• Fine-tuning is Not Enough: A Parallel Framework for Collaborative Imitation and Reinforcement Learning in End-to-end Autonomous Driving