Data-Free Continual Learning for World Action Model with Rectified Generative Replay
cs.RO, cs.CV
Submitted: 2026-10-13
Updated: 2026-10-14
Code: https://github.com/nvidia-cosmos/cosmos-predict2
Project page: https://kaipengfang.github.io/r2-wam
License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
Terminology
Sources
- Qwen3-VL Technical Report
- Stable Video Diffusion: Scaling Latent Video Diffusion Models to Large Datasets
- World Action Models Enable Continual Imitation Learning with Recurrent Generative Replays
- RoboCurate: Harnessing Diversity with Action-Verified Neural Trajectory for Robot Learning
- Causal World Modeling for Robot Control
- The World Model Remembers, the Actor Forgets: Dream Rehearsal for Continual Model-Based RL
- Is the Future Compatible? Diagnosing Dynamic Consistency in World Action Models
- Progressive Neural Networks
- Wan: Open and Advanced Large-Scale Video Generative Models
- SC3-Eval: Evaluating Robot Foundation Models via Self-Consistent Video Generation
- Continually Evolving Skill Knowledge in Vision Language Action Model
- World Action Models are Zero-shot Policies
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
- ARC: A Reasoning Recipe for Robot Foundation Models
- HRDexDB: A 4D Dexterous Grasping Dataset Across Human and Multiple Robot Embodiments
- APT: Action Expert Pretraining Improves Instruction Generalization of Vision-Language-Action Policies