这篇论文发现VLA模型很多层是冗余的，用他们的方法可以白嫖50%层数，微调快一半，推理快30%，效果不降。搞机器人微调的可以试试。
VLA模型（如pi_0、GR00T-N1.5）参数规模达数十亿，微调计算成本高。本文通过中心核对齐（Centered Kernel Alignment）识别冗余层，无需训练即可移除最多50%的层。在LIBERO、RoboCasa、SimplerEnv三个模拟基准和10个真实操作任务、4种机器人本体上验证，压缩后模型性能与完整模型相当。微调时间减少40-50%，实时推理速度提升达30%。结果表明VLA模型实际所需层数远少于现有架构。
Finetuning Vision-Language-Action Models Requires Fewer Layers Than You Think
Vision-Language-Action (VLA) models pre-trained on massive video-robot datasets have revolutionized robotic manipulation, yet their multi-billion parameter architectures impose prohibitive computational burdens during downstream fine-tuning and real-time inference. In this work, we reveal a highly non-trivial architectural characteristic of these continuous control foundation policies (e.g., pi_0, GR00T-N1.5): despite being trained on diverse physical trajectories, they exhibit severe layer-wise representational redundancy. To exploit this, we introduce a structural compression pipeline that is entirely training-free, bypassing the need of existing methods to load full-scale models to learn optimized token reductions or dynamic layer selectors. Instead, using only a single forward pass via Centered Kernel Alignment to identify redundant layer features, we remove twin layers to permanently compress the model depth by up to 50% across both the VLM backbone and the continuous control policy head. Downstream fine-tuning of this streamlined architecture yields a dual acceleration benefit: a 40-50% reduction in training time and up to 30% faster real-time inference, while matching or exceeding full-scale base model performance. We comprehensively validate our method across three simulation benchmarks (LIBERO, RoboCasa, SimplerEnv) and 10 diverse real-world manipulation tasks across 4 unique robotic embodiments. These results prove that advanced VLAs require significantly fewer layers than previously assumed, offering a highly compute-efficient paradigm for scalable robot learning.