相关论文: How Mobile World Model Guides GUI Agents?

World Action Models (WAMs) have emerged as a promising alternative to Vision-Language-Action (VLA) models for embodied control because they explicitly model how visual observations may evolve under action. Most existing WAMs follow an…

Autonomous inspection in hazardous environments requires AI agents that can interpret high-level goals and execute precise control. A key capability for such agents is spatial grounding, for example when a drone must center a detected…

General world models represent a crucial pathway toward achieving Artificial General Intelligence (AGI), serving as the cornerstone for various applications ranging from virtual environments to decision-making systems. Recently, the…

The advancement of mobile GUI agents has opened new opportunities for automating tasks on mobile devices. Training these agents requires large-scale high-quality data, which is prohibitively expensive when relying on human labor. Given the…

World Models (WMs) have emerged as a promising approach for post-training Vision-Language-Action (VLA) policies to improve robustness and generalization under environmental changes. However, most WM-based post-training methods rely on…

Robot action planning in the real world is challenging as it requires not only understanding the current state of the environment but also predicting how it will evolve in response to actions. Vision-language-action (VLA), which repurpose…

Recent research in language-guided visual navigation has demonstrated a significant demand for the diversity of traversable environments and the quantity of supervision for training generalizable agents. To tackle the common data scarcity…

Edge General Intelligence (EGI) represents a transformative evolution of edge computing, where distributed agents possess the capability to perceive, reason, and act autonomously across diverse, dynamic environments. Central to this vision…

Infants are experts at playing, with an amazing ability to generate novel structured behaviors in unstructured environments that lack clear extrinsic reward signals. We seek to mathematically formalize these abilities using a neural network…

Scalable and reliable evaluation is increasingly critical in the end-to-end era of autonomous driving, where vision--language--action (VLA) policies directly map raw sensor streams to driving actions. Yet, current evaluation pipelines still…

Agents capable of reasoning and planning in the real world require the ability of predicting the consequences of their actions. While world models possess this capability, they most often require action labels, that can be complex to obtain…

We present the Multi-Agent Transformer World Model (MATWM), a novel transformer-based world model designed for multi-agent reinforcement learning in both vector- and image-based environments. MATWM combines a decentralized imagination…

Addressing the challenge of a digital assistant capable of executing a wide array of user tasks, our research focuses on the realm of instruction-based mobile device control. We leverage recent advancements in large language models (LLMs)…

Vision-Language-Action (VLA) models are promising for generalist robot manipulation but remain brittle in out-of-distribution (OOD) settings, especially with limited real-robot data. To resolve the generalization bottleneck, we introduce a…

We provide a dataset that enables the creation of learning agents that can build knowledge graph-based world models of interactive narratives. Interactive narratives -- or text-adventure games -- are partially observable environments…

Despite their tremendous success in many applications, large language models often fall short of consistent reasoning and planning in various (language, embodied, and social) scenarios, due to inherent limitations in their inference,…

Large language models (LLMs) have achieved strong performance in language-centric tasks. However, in agentic settings, LLMs often struggle to anticipate action consequences and adapt to environment dynamics, highlighting the need for…

Offline meta-reinforcement learning seeks to learn policies that generalize across related tasks from fixed datasets. Context-based methods infer a task representation from transition histories, but learning effective task representations…

The evolution of video generation from text, from animating MNIST to simulating the world with Sora, has progressed at a breakneck speed. Here, we systematically discuss how far text-to-video generation technology supports essential…

Large-scale, high-quality interaction trajectories are essential for advancing mobile Graphical User Interface (GUI) agents. While existing methods typically rely on labor-intensive human demonstrations or automated model exploration to…