Interactive and embodied tasks pose at least two fundamental challenges to existing Vision & Language (VL) models, including 1) grounding language in trajectories of actions and observations, and 2) referential disambiguation. To tackle these challenges, we propose an Embodied MultiModal Agent (EMMA): a unified encoder-decoder model that reasons over images and trajectories, and casts action prediction as multimodal text generation. By unifying all tasks as text generation, EMMA learns a language of actions which facilitates transfer across tasks. Different to previous modular approaches with independently trained components, we use a single multitask model where each task contributes to goal completion. EMMA performs on par with similar models on several VL benchmarks and sets a new state-of-the-art performance (36.81% success rate) on the Dialog-guided Task Completion (DTC), a benchmark to evaluate dialog-guided agents in the Alexa Arena

我们提出了一种统一的编码-解码模型，称为Embodied MultiModal Agent (EMMA)，可以处理交互和具身任务，其中每个任务对目标完成做出贡献，取得了与类似模型相当的性能并在Dialog-guided Task Completion (DTC)中取得了新的最佳结果（36.81%的成功率）用于评估Alexa Arena中的对话引导代理。

多任务多模态提示训练用于交互式具象任务完成