Acting Through Registers
cs.RO
Submitted: 2026-10-13
Updated: 2026-10-13
Code: https://github.com/Z1zyw/RegisterWAM
License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
Sources
- Gen2Act: Human Video Generation in Novel Scenarios enables Generalizable Robot Manipulation
- Motus: A Unified Latent Action World Model
- GR-2: A Generative Video-Language-Action Model with Web-Scale Knowledge for Robot Manipulation
- RoboTwin 2.0: A Scalable Data Generator and Benchmark with Strong Domain Randomization for Robust Bimanual Robotic Manipulation
- Vision Transformers Need Registers
- Learning Universal Policies via Text-Guided Video Generation
- LIBERO-Plus: In-depth Robustness Analysis of Vision-Language-Action Models
- Vidar: Embodied Video Diffusion Model for Generalist Manipulation
- Video Prediction Policy: A Generalist Robot Policy with Predictive Visual Representations
- Cosmos Policy: Fine-Tuning Video Models for Visuomotor Control and Planning
- Driving on Registers
- Efficient-WAM: A 1B-Parameter World-Action Model with Low-Cost Future Imagination
- Causal World Modeling for Robot Control
- Unified Video Action Model
- Light-WAM: Efficient World Action Models with State-Fusion Action Decoding
- Video Generators are Robot Policies
- Genie Envisioner: A Unified World Foundation Platform for Robotic Manipulation
- LIBERO: Benchmarking Knowledge Transfer for Lifelong Robot Learning
- Faster-WAM: Do World Action Models Need Deep Action Modules?
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