WAM-OPD: Sharpening World Action Models via On-Policy Distillation
cs.RO, cs.AI
Submitted: 2026-09-28
Updated: 2026-09-28
Terminology
Sources
- Flash-WAM: Modality-Aware Distillation for World Action Models
- $\pi_\texttt{RL}$: Online RL Fine-tuning for Flow-based Vision-Language-Action Models
- RoboTwin 2.0: A Scalable Data Generator and Benchmark with Strong Domain Randomization for Robust Bimanual Robotic Manipulation
- Flow-OPD: On-Policy Distillation for Flow Matching Models
- Causal World Modeling for Robot Control
- DiffusionOPD: A Unified Perspective of On-Policy Distillation in Diffusion Models
- Multi-Turn On-Policy Distillation with Prefix Replay
- STEAM: Self-Supervised Temporal Ensemble Advantage Modeling for Real-World Robot Learning
- An Empirical Study of Catastrophic Forgetting in Large Language Models During Continual Fine-tuning
- WAM-RL: World-Action Model Reinforcement Learning with Reconstruction Rewards and Online Video SFT
- Self-Distillation Enables Continual Learning
- Interactive Post-Training for Vision-Language-Action Models
- Lightning OPD: Efficient Post-Training for Large Reasoning Models with Offline On-Policy Distillation
- World Action Models are Zero-shot Policies
- Fast-WAM: Do World Action Models Need Test-time Future Imagination?
- VLA-OPD: Bridging Offline SFT and Online RL for Vision-Language-Action Models via On-Policy Distillation
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