Behavioral Steering of Vision-Language-Action Models in the Low-Parameter Regime
cs.RO, cs.LG
Submitted: 2026-10-31
Updated: 2026-10-31
Comments: NeurIPS 2026 RoboPAD Workshop
License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
Terminology
Sources
- OpenVLA: An Open-Source Vision-Language-Action Model
- RT-2: Vision-Language-Action Models Transfer Web Knowledge to Robotic Control
- Open X-Embodiment: Robotic Learning Datasets and RT-X Models
- Mechanistic interpretability for steering vision-language-action models
- Not All Features Are Created Equal: A Mechanistic Study of Vision-Language-Action Models
- RLinf-VLA: A Unified and Efficient Framework for Reinforcement Learning of Vision-Language-Action Models
- Improving Vision-Language-Action Model with Online Reinforcement Learning
- SimpleVLA-RL: Scaling VLA Training via Reinforcement Learning
- Learning to Reason in 13 Parameters
- Fine-Tuning Vision-Language-Action Models: Optimizing Speed and Success
- LIBERO: Benchmarking Knowledge Transfer for Lifelong Robot Learning
- DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models
- ESSA: Evolutionary Strategies for Scalable Alignment
- Evolution Strategies as a Scalable Alternative to Reinforcement Learning
- Matching Accuracy, Different Geometry: Evolution Strategies vs GRPO in LLM Post-Training
- Closed-Loop Neural Activation Control in Vision-Language-Action Models
- LoRA: Low-Rank Adaptation of Large Language Models
- LoRA-XS: Low-Rank Adaptation with Extremely Small Number of Parameters
- Proximal Policy Optimization Algorithms
- Evolution Strategies at Scale: LLM Fine-Tuning Beyond Reinforcement Learning
Related papers
- Rethinking Actions: Continuity-Aware Priors for World-Model Planning
- MOSAIC: Modular Obstacle and Spatial-Aware Framework for Manipulation In Cluttered Scenes
- SAGAS: Semantic-Aware Graph-Assisted Stitching for Offline Temporal Logic Planning
- DexSeed: Expanding Human Hand-Object Interactions into Robot Demonstrations for Dexterous Policy Learning
- LaST0.5: A Generalist World Action Model with Interaction-Centric Latent Reasoning
- CIALLO: Learning Shared Intent Representations for Cross-Embodiment Manipulation