arXiv Machine Learning
Not All Layers Need Tuning: Diagnosing and Directing Adaptation in Vision-Language-Action Models
Read the original on arXiv Machine Learning →The Flow has not summarised this story yet — read it at arXiv Machine Learning.
Related stories
arXiv AI
Oct 21
VLA-Retain: Benchmarking Cross-Dimension Effects of Vision Tuning in VLAs
arXiv:2610.27698v1 Announce Type: cross Abstract: Vision-language-action (VLA) models transfer knowledge from large-scale pretraining into robot control, but their manipulation performance remains se...
arXiv AI
Jun 9
CrossVLA: Cross-Paradigm Post-Training and Inference Optimization for Vision-Language-Action Models
arXiv:2605. 21854v2 Announce Type: replace-cross Abstract: Vision-Language-Action (VLA) models have rapidly converged on a small set of architectural patterns: discrete-token autoregression (e.
arXiv Machine Learning
Jul 14
On the Efficiency of LoRA Fine-Tuning for Vision-Language-Action Models in Industrial Robotic Manipulation
arXiv:2607. 10172v1 Announce Type: cross Abstract: Deploying billion-parameter Vision-Language-Action (VLA) models on industrial hardware requires fine-tuning to bridge the embodiment gap.
arXiv AI
Sep 15
Pre-PEFT Probing: Weight Statistics and Perturbation Robustness for Layer Selection in VLM Vision Encoders
arXiv:2609.15229v1 Announce Type: cross Abstract: We propose a pre-fine-tuning probing method for Parameter-Efficient Fine-Tuning (PEFT) layer selection, aiming to obtain more stable and higher gains...
arXiv Computer Vision
Sep 7
Cross-Domain Tracker Adaptation Without Target-Domain Labels via Vision-Language Agents
The paper introduces a Vision‑Language Model (VLM) that acts as a diagnostic agent to adapt a detect‑to‑track system to new domains without target‑domain labels. By inspecting rendered tracking outputs, the VLM identifies failure modes and iteratively recommends parameter updates, recovering a significant portion of performance lost when transferring hyperparameters from a source domain. Experiments on MOT17→MOT20 show the VLM tuner restores 67.8% of the lost headroom, while Bayesian optimization with proxy objectives performs poorly under large domain shifts.
arXiv AI
Oct 15
VLA-GAUGE: Systematically Evaluating Generalization and Robustness in Vision-Language-Action Models
arXiv:2610.16567v1 Announce Type: cross Abstract: Vision-Language-Action models (VLAs) have achieved high success rates on familiar manipulation tasks, yet it remains unclear whether such scores refl...