Related papers: SIMA 2: A Generalist Embodied Agent for Virtual Wo…
The advent of Chat-GPT has led to a surge of interest in Embodied AI. However, many existing Embodied AI models heavily rely on massive interactions with training environments, which may not be practical in real-world situations. To this…
The scalability of embodied intelligence is fundamentally constrained by the scarcity of real-world interaction data. While simulation platforms provide a promising alternative, existing approaches often suffer from a substantial visual and…
A key feature differentiating artificial general intelligence (AGI) from traditional AI is that AGI can perform composite tasks that require a wide range of capabilities. Although embodied agents powered by multimodal large language models…
Agent-based modeling has been around for decades, and applied widely across the social and natural sciences. The scope of this research method is now poised to grow dramatically as it absorbs the new affordances provided by Large Language…
The recent development on large multimodal models (LMMs), especially GPT-4V(ision) and Gemini, has been quickly expanding the capability boundaries of multimodal models beyond traditional tasks like image captioning and visual question…
The rapid progress in embodied artificial intelligence has highlighted the necessity for more advanced and integrated models that can perceive, interpret, and predict environmental dynamics. In this context, World Models (WMs) have been…
Large language models (LLMs) have achieved impressive pro-gress on several open-world tasks. Recently, using LLMs to build embodied agents has been a hotspot. This paper proposes STEVE, a comprehensive and visionary embodied agent in the…
Recent advances in vision-language models (VLMs) have shown promise for human-level embodied intelligence. However, existing benchmarks for VLM-driven embodied agents often rely on high-level commands or discretized action spaces, which are…
We present Game-TARS, a generalist game agent trained with a unified, scalable action space anchored to human-aligned native keyboard-mouse inputs. Unlike API- or GUI-based approaches, this paradigm enables large-scale continual…
Simulations, although powerful in accurately replicating real-world systems, often remain inaccessible to non-technical users due to their complexity. Conversely, large language models (LLMs) provide intuitive, language-based interactions…
Mobile Graphical User Interface (GUI) agents aim to autonomously complete tasks within or across apps based on user instructions. While recent Multimodal Large Language Models (MLLMs) enable these agents to interpret UI screens and perform…
We study lifelong visual perception in an embodied setup, where we develop new models and compare various agents that navigate in buildings and occasionally request annotations which, in turn, are used to refine their visual perception…
While most machine translation systems to date are trained on large parallel corpora, humans learn language in a different way: by being grounded in an environment and interacting with other humans. In this work, we propose a communication…
A common vision from science fiction is that robots will one day inhabit our physical spaces, sense the world as we do, assist our physical labours, and communicate with us through natural language. Here we study how to design artificial…
Game environments provide rich, controllable settings that stimulate many aspects of real-world complexity. As such, game agents offer a valuable testbed for exploring capabilities relevant to Artificial General Intelligence. Recently, the…
In robot learning, it is common to either ignore the environment semantics, focusing on tasks like whole-body control which only require reasoning about robot-environment contacts, or conversely to ignore contact dynamics, focusing on…
This paper introduces the concept of Language-Guided World Models (LWMs) -- probabilistic models that can simulate environments by reading texts. Agents equipped with these models provide humans with more extensive and efficient control,…
In Embodied Question Answering (EmbodiedQA), an agent interacts with an environment to gather necessary information for answering user questions. Existing works have laid a solid foundation towards solving this interesting problem. But the…
In the context of autonomous navigation of terrestrial robots, the creation of realistic models for agent dynamics and sensing is a widespread habit in the robotics literature and in commercial applications, where they are used for model…
Incremental decision making in real-world environments is one of the most challenging tasks in embodied artificial intelligence. One particularly demanding scenario is Vision and Language Navigation~(VLN) which requires visual and natural…