Vision-Language-Action (VLA) models built upon Chain-of-Thought (CoT) have achieved remarkable success in advancing general-purpose robotic agents, owing to its significant perceptual comprehension. Recently, since text-only CoT struggles to adequately capture scene details in complex spatial environments, a highly promising strategy involves leveraging visual priors to guide robotic action generation. Nevertheless, these strategies face two inherent challenges: (i) a modality gap between visual observations and low-level actions, and (ii) unstable training due to competing objectives between visual prediction and action generation. To address these challenges, we propose a Vision-Integrated Trajectory Alignment (VITA) framework that learns a shared discrete latent space for vision and action, enabling joint modeling of perception and motor control. VITA introduces a implicit visual CoT: autoregressively generated tokens is simultaneously decoded into future frames predictions and robot actions, thereby internalizing visual dynamics as an inductive bias for motion planning. Extensive experiments on simulated and real-world environments demonstrate state-of-the-art performance. VITA improves 14.5\%, 9.6\% and 12.1\% over existing baselines on CALVIN, LIBERO and SimplerEnv. Furthermore, VITA attains an average success rate of 80.5\% across six real-world tasks, demonstrating its potential as a generalist robotic manipulation model.

翻译：基于思维链（CoT）构建的视觉-语言-动作（VLA）模型凭借其卓越的感知理解能力，在推进通用机器人智能体方面取得了显著成功。近期，由于纯文本CoT难以充分捕捉复杂空间环境中的场景细节，一种极具前景的策略是利用视觉先验来引导机器人动作生成。然而，这些策略面临两个固有挑战：（i）视觉观测与底层动作之间的模态鸿沟；（ii）视觉预测与动作生成目标相互竞争导致训练不稳定。为应对这些挑战，我们提出视觉集成轨迹对齐（VITA）框架，该框架学习视觉与动作共享的离散潜空间，实现对感知与运动控制的联合建模。VITA引入隐式视觉CoT机制：自回归生成的令牌可同时解码为未来帧预测与机器人动作，从而将视觉动态内化为运动规划的归纳偏置。在仿真与真实环境中的大量实验证明了其最先进的性能。VITA在CALVIN、LIBERO和SimplerEnv基准上分别超越现有基线14.5%、9.6%和12.1%。此外，VITA在六项真实世界任务中平均成功率高达80.5%，展现了其作为通用机器人操作模型的潜力。