Observing and Controlling Features in Vision-Language-Action Models
cs.RO
Submitted: 2026-03-05
Updated: 2026-09-21
Terminology
Sources
- $\pi_0$: A Vision-Language-Action Flow Model for General Robot Control
- Persona Vectors: Monitoring and Controlling Character Traits in Language Models
- LiSeCo: Linear Semantic Control for Language Generation
- LIBERO-Plus: In-depth Robustness Analysis of Vision-Language-Action Models
- Mechanistic interpretability for steering vision-language-action models
- $\pi_{0.5}$: a Vision-Language-Action Model with Open-World Generalization
- VLAs are Confined yet Capable of Generalizing to Novel Instructions
- Probing a Vision-Language-Action Model for Symbolic States and Integration into a Cognitive Architecture
- Mechanistic Finetuning of Vision-Language-Action Models via Few-Shot Demonstrations
- HyperSteer: Activation Steering at Scale with Hypernetworks
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