Not All Layers Need Tuning: Diagnosing and Directing Adaptation in Vision-Language-Action Models
cs.RO, cs.CV, cs.LG
Submitted: 2026-09-16
Updated: 2026-09-17
Comments: 9 pages, 7 figures, 7 tables
License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
Terminology
Sources
- On the Efficiency of LoRA Fine-Tuning for Vision-Language-Action Models in Industrial Robotic Manipulation
- Adaptive Capacity Allocation for Vision Language Action Fine-tuning
- VLA-Trace: Diagnosing Vision-Language-Action Models through Representation and Behavior Tracing
- Fine-Tuning Vision-Language-Action Models: Optimizing Speed and Success
- Diffusion Transformer Policy
- $\pi_0$: A Vision-Language-Action Flow Model for General Robot Control
- SmolVLA: A Vision-Language-Action Model for Affordable and Efficient Robotics
- Intrinsic Dimensionality Explains the Effectiveness of Language Model Fine-Tuning
- LoRA Learns Less and Forgets Less
- ARD-LoRA: Dynamic Rank Allocation for Parameter-Efficient Fine-Tuning of Foundation Models with Heterogeneous Adaptation Needs
- RSRA: Training-Free Probing of Representation Sensitivity for Efficient LoRA Rank Allocation
- DoRA: Weight-Decomposed Low-Rank Adaptation
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