Standard Vision-Language-Action (VLA) models typically fine-tune a monolithic Vision-Language Model (VLM) backbone explicitly for robotic control. However, this approach creates a critical tension between maintaining high-level general semantic understanding and learning low-level, fine-grained sensorimotor skills, often leading to "catastrophic forgetting" of the model's open-world capabilities. To resolve this conflict, we introduce TwinBrainVLA, a novel architecture that coordinates a generalist VLM retaining universal semantic understanding and a specialist VLM dedicated to embodied proprioception for joint robotic control. TwinBrainVLA synergizes a frozen "Left Brain", which retains robust general visual reasoning, with a trainable "Right Brain", specialized for embodied perception, via a novel Asymmetric Mixture-of-Transformers (AsyMoT) mechanism. This design allows the Right Brain to dynamically query semantic knowledge from the frozen Left Brain and fuse it with proprioceptive states, providing rich conditioning for a Flow-Matching Action Expert to generate precise continuous controls. Extensive experiments on SimplerEnv and RoboCasa benchmarks demonstrate that TwinBrainVLA achieves superior manipulation performance compared to state-of-the-art baselines while explicitly preserving the comprehensive visual understanding capabilities of the pre-trained VLM, offering a promising direction for building general-purpose robots that simultaneously achieve high-level semantic understanding and low-level physical dexterity.

翻译：标准的视觉-语言-动作模型通常通过显式微调一个单一的视觉-语言模型主干来实现机器人控制。然而，这种方法在保持高级通用语义理解与学习低级、细粒度感知运动技能之间产生了关键矛盾，常常导致模型对开放世界能力的"灾难性遗忘"。为解决这一冲突，我们提出了TwinBrainVLA，这是一种新颖的架构，它协调一个保持通用语义理解的通用VLM与一个专用于具身本体感知的专用VLM，以实现联合机器人控制。TwinBrainVLA通过一种新颖的非对称混合Transformer机制，将保持强大通用视觉推理能力的冻结"左脑"与专用于具身感知的可训练"右脑"协同起来。这种设计使得右脑能够动态地从冻结的左脑查询语义知识，并将其与本体感知状态融合，为流匹配动作专家提供丰富的条件信息，以生成精确的连续控制。在SimplerEnv和RoboCasa基准测试上进行的大量实验表明，与最先进的基线方法相比，TwinBrainVLA实现了更优越的操作性能，同时明确保留了预训练VLM的全面视觉理解能力，为构建同时实现高级语义理解和低级物理灵巧性的通用机器人提供了一个有前景的方向。