Noise Space Learning for VLA Adaptation
cs.RO
Submitted: 2026-10-09
Updated: 2026-10-09
Comments: 26 pages
License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
Terminology
Sources
- $\pi_0$: A Vision-Language-Action Flow Model for General Robot Control
- $\pi_\texttt{RL}$: 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
- Where Should Action Generation Begin? A Learnable Source Prior for Generative Robot Policies
- EXPO-FT: Sample-Efficient Reinforcement Learning Finetuning for Vision-Language-Action Models
- Soft Actor-Critic: Off-Policy Maximum Entropy Deep Reinforcement Learning with a Stochastic Actor
- LoRA: Low-Rank Adaptation of Large Language Models
- Simple Recipe Works: Vision-Language-Action Models are Natural Continual Learners with Reinforcement Learning
- Breaking Lock-In: Preserving Steerability under Low-Data VLA Post-Training
- VLA-GSE: Boosting Parameter-Efficient Fine-Tuning in VLA with Generalized and Specialized Experts
- OpenVLA: An Open-Source Vision-Language-Action Model
- Fine-Tuning Vision-Language-Action Models: Optimizing Speed and Success
- Reinforcement Learning and Control as Probabilistic Inference: Tutorial and Review
- UniSteer: Unified Noise Steering for Efficient Human-Guided VLA Adaptation
- Octo: An Open-Source Generalist Robot Policy
- You've Got a Golden Ticket: Improving Generative Robot Policies With A Single Noise Vector
- $\pi_{0.5}$: a Vision-Language-Action Model with Open-World Generalization
- Diffusion Policy Policy Optimization
- QPILOTS: Efficient Test-Time Q-Steering for Flow Policies
- Proximal Policy Optimization Algorithms
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