We present Pelican-Unified 1.0, the first embodied foundation model trained according to the principle of unification. Pelican-Unified 1.0 uses a single VLM as a unified understanding module, mapping scenes, instructions, visual contexts, and action histories into a shared semantic space. The same VLM also serves as a unified reasoning module, autoregressively producing task-, action-, and future-oriented chains of thought in a single forward pass and projecting the final hidden state into a dense latent variable. A Unified Future Generator (UFG) then conditions on this latent variable and jointly generates future videos and future actions through two modality-specific output heads within the same denoising process. The language, video, and action losses are all backpropagated into the shared representation, enabling the model to jointly optimize understanding, reasoning, imagination, and action during training, rather than training three isolated expert systems. Experiments demonstrate that unification does not imply compromise. With a single checkpoint, Pelican-Unified 1.0 achieves strong performance across all three capabilities: 64.7 on eight VLM benchmarks, the best among comparable-scale models; 66.03 on WorldArena, ranking first; and 93.5 on RoboTwin, the second-best average among compared action methods. These results show that the unified paradigm succeeds in preserving specialist strength while bringing understanding, reasoning, imagination, and action into one model.

翻译：我们提出Pelican-Unified 1.0，这是首个依据统一化原则训练的具身基础模型。Pelican-Unified 1.0采用单一视觉语言模型（VLM）作为统一理解模块，将场景、指令、视觉上下文及动作历史映射至共享语义空间。该VLM同时作为统一推理模块，在一次前向传播中自回归地生成面向任务、动作及未来的思维链，并将最终隐状态投影为稠密潜变量。随后，统一未来生成器（UFG）以该潜变量为条件，在同一去噪过程中通过两个模态专用输出头联合生成未来视频与未来动作。语言、视频及动作损失均反向传播至共享表征，使模型在训练中能联合优化理解、推理、想象与行动，而非训练三个孤立的专家系统。实验表明，统一化并不意味着性能妥协。基于单一检查点，Pelican-Unified 1.0在全部三种能力上均取得强劲表现：在八项VLM基准测试中达64.7，为同规模模型最优；在WorldArena上以66.03分排名第一；在RoboTwin上达93.5，为所比较动作方法中第二佳均值。这些结果表明，统一范式成功保留了专家级性能，并将理解、推理、想象与行动融于单一模型。