TACO: TActile World Model as a Self-COrrector for Scalable Robot Policy Post-Training
cs.RO
Submitted: 2026-07-03
Updated: 2026-09-16
Project page: https://taco-wm.github.io
License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
Terminology
Sources
- $\pi_{0.5}$: a Vision-Language-Action Model with Open-World Generalization
- Video2Act: A Dual-System Video Diffusion Policy with Robotic Spatio-Motional Modeling
- Interactive World Simulator for Robot Policy Training and Evaluation
- Hi-WM: Human-in-the-World-Model for Scalable Robot Post-Training
- TwinRL: Digital Twin-Driven Reinforcement Learning for Real-World Robotic Manipulation
- VLAW: Iterative Co-Improvement of Vision-Language-Action Policy and World Model
- WMPO: World Model-based Policy Optimization for Vision-Language-Action Models
- WoVR: World Models as Reliable Simulators for Post-Training VLA Policies with RL
- DreamGen: Unlocking Generalization in Robot Learning through Video World Models
- WM-DAgger: Enabling Efficient Data Aggregation for Imitation Learning with World Models
- Diffusion Guidance Is a Controllable Policy Improvement Operator
- $\pi^{*}_{0.6}$: a VLA That Learns From Experience
- HarmoWAM: Harmonizing Generalizable and Precise Manipulation via Adaptive World Action Models
- AnyPos: Automated Task-Agnostic Actions for Bimanual Manipulation
- TC-IDM: Grounding Video Generation for Executable Zero-shot Robot Motion
- Robo-Dopamine: General Process Reward Modeling for High-Precision Robotic Manipulation
- A Vision-Language-Action-Critic Model for Robotic Real-World Reinforcement Learning
- STEAM: Self-Supervised Temporal Ensemble Advantage Modeling for Real-World Robot Learning
- World4RL: Diffusion World Models for Policy Refinement with Reinforcement Learning for Robotic 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