InternVLA-A1.5：统一理解、潜在预判与行动以实现组合泛化

摘要

面向机器人操作领域的统一模型旨在为单一策略同时赋予预训练视觉语言模型（VLM）的语义先验以及通过未来预测学习到的物理动态。然而在实践中，现有设计往往会侵蚀预训练骨干网络的语义能力，遭受异构目标之间的相互干扰，并且需从零开始在像素空间中学习未来预测，从而未能充分利用预训练视频生成器的动态先验。为此，我们提出InternVLA-A1.5，该模型以原生VLM骨干网络为基础，持续进行视觉问答（VQA）与子任务预测训练，并附加轻量级统一专家模块用于连续动作生成。我们将未来预测重新定义为潜在查询问题：通过一组可学习的前瞻标记，在冻结的预训练视频生成模型监督下，将任务相关的未来信息压缩为紧凑的潜在编码，从而使策略在不学习像素级生成的前提下继承世界模型的动态先验。推理阶段丢弃视频分支，保持实时控制能力。在120万条机器人操作数据与300万条多模态样本上完成预训练后，InternVLA-A1.5在所有六个仿真基准测试中取得了最佳综合表现。在真实世界中，保留的语义能力在未见过的指令绑定任务上展现出最强的组合泛化性能，而上述两种设计共同支撑了长时域的执行能力。

English

Unified models for robot manipulation aim to equip one policy with both the semantic priors of pretrained VLMs and the physical dynamics learned through future prediction. In practice, existing designs tend to erode the semantics of the pretrained backbone, suffer interference among heterogeneous objectives, and learn future prediction from scratch in pixel space, leaving the dynamics priors of pretrained video generators unexploited. We present InternVLA-A1.5, which builds the policy on a native VLM backbone that keeps training on VQA and subtask prediction, and attaches a lightweight unified expert for continuous action generation. Future prediction is recast as a latent-querying problem, where a small set of learnable foresight tokens condenses the task-relevant future into a compact latent code under the supervision of a frozen pretrained video generation model, so the policy inherits world-model dynamics priors without ever learning pixel-level generation. The video branch is discarded at inference, keeping real-time control. Pretrained on 1.2M robot episodes and 3M multimodal samples, InternVLA-A1.5 achieves the best overall results on all six simulation benchmarks. In the real world, the preserved semantics deliver the strongest compositional generalization on held-out instruction bindings, and the two designs together sustain long-horizon execution.