MaskHarness-WAM: Instance-Grounded Harnessing for Long-Horizon Robot Manipulation

arXiv:2609.19974 · cs.RO, cs.AI · Submitted 2026-09-17 · Read on arXiv

cs.RO, cs.AI

Submitted: 2026-09-17

Updated: 2026-09-17

License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/

Terminology

• Grounding — 19× in this paper · explained in 3 episodes
• Generalization — 16× in this paper · explained in 13 episodes
• Verification — 7× in this paper · explained in 2 episodes
• Task Planning — 6× in this paper · explained in 2 episodes
• Affordance — 5× in this paper · explained in 1 episode
• Zero-Shot Generalization — 5× in this paper · explained in 5 episodes
• Success Rate — 3× in this paper
• Distribution Shift — 2× in this paper · explained in 6 episodes
• Fine-Tuning — 2× in this paper · explained in 5 episodes
• Flow Matching — 2× in this paper · explained in 8 episodes
• Foundation Model — 2× in this paper · explained in 3 episodes
• Mask Generation — 2× in this paper · explained in 2 episodes
• State Management — 2× in this paper · explained in 3 episodes
• World Model — 2× in this paper · explained in 7 episodes
• Adaptation — 1× in this paper · explained in 1 episode
• Conference on Computer Vision and Pattern Recognition — 1× in this paper
• International Conference on Robotics and Automation — 1× in this paper
• Latent Representation — 1× in this paper · explained in 2 episodes
• Latent Representations — 1× in this paper · explained in 3 episodes
• Progress Rate — 1× in this paper
• Robustness — 1× in this paper · explained in 5 episodes
• Semantic Understanding — 1× in this paper · explained in 2 episodes
• Steering — 1× in this paper · explained in 2 episodes
• Task Decomposition — 1× in this paper · explained in 2 episodes
• Vision-Language-Action (VLA) Models — 1× in this paper · explained in 2 episodes

Sources

• $\pi_0$: A Vision-Language-Action Flow Model for General Robot Control
• Fast-WAM: Do World Action Models Need Test-time Future Imagination?
• World Action Models are Zero-shot Policies
• Motubrain: An Advanced World Action Model for Robot Control
• DeMaVLA: A Vision-Language-Action Foundation Model for Generalizable Deformable Manipulation
• Harness VLA: Steering Frozen VLAs into Reliable Manipulation Primitives via Memory-Guided Agents
• HarnessWAM: Bridging Prediction and Deliberation in World Action Models
• RoboHarness: Memory-Driven Orchestration of Heterogeneous Robot Policies for Long-Horizon Planning
• Towards the Harness of Embodied Agents
• Self-Evolving Embodied Agents via Skill-Harness Evolution
• Show-Harness: Just a VLM Agent Can Play Robots
• Open-World Object Manipulation using Pre-trained Vision-Language Models
• KITE: Keypoint-Conditioned Policies for Semantic Manipulation
• MOKA: Open-World Robotic Manipulation through Mark-Based Visual Prompting
• ControlVLA: Few-shot Object-centric Adaptation for Pre-trained Vision-Language-Action Models
• MaskWAM: Unifying Mask Prompting and Prediction for World-Action Models
• GR-2: A Generative Video-Language-Action Model with Web-Scale Knowledge for Robot Manipulation
• Gen2Act: Human Video Generation in Novel Scenarios enables Generalizable Robot Manipulation
• RoboDreamer: Learning Compositional World Models for Robot Imagination

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