PaLM-E: An Embodied Multimodal Language Model: Difference between revisions

{{see also|PaLM-E|Papers}}

The paper talks about a new type of computer program called an embodied language model that can help robots understand language better and interact with the real world. Large language models (LLMs) are computer programs that are really good at understanding and using language, but they have trouble using that language to control robots and interact with the real world. The article proposes an embodied language model that incorporates real-world sensor data, like pictures and sensor readings, into the language model. This helps the program understand how to use language to control a robot and interact with the real world.

==Abstract==

Large language models have been demonstrated to perform complex tasks. However, enabling general inference in the real world, e.g. for robotics problems, raises the challenge of grounding. We propose embodied language models to directly incorporate real-world continuous sensor modalities into language models and thereby establish the link between words and percepts. Input to our embodied language model are multi-modal sentences that interleave visual, continuous state estimation, and textual input encodings. We train these encodings end-to-end, in conjunction with a pre-trained large language model, for multiple embodied tasks, including sequential robotic manipulation planning, visual question answering, and captioning. Our evaluations show that PaLM-E, a single large embodied multimodal model, can address a variety of embodied reasoning tasks, from a variety of observation modalities, on multiple embodiments, and further, exhibits positive transfer: the model benefits from diverse joint training across internet-scale language, vision, and visual-language domains. Our largest model, PaLM-E-562B with 562B parameters, in addition to being trained on robotics tasks, is a visual-language generalist with state-of-the-art performance on OK-VQA, and retains generalist language capabilities with increasing scale.

==Discussion==