相关论文: Pandora: Towards General World Model with Natural …

A world model enables an intelligent agent to imagine, predict, and reason about how the world evolves in response to its actions, and accordingly to plan and strategize. While recent video generation models produce realistic visual…

Trained on internet-scale video data, generative world models are increasingly recognized as powerful world simulators that can generate consistent and plausible dynamics over structure, motion, and physics. This raises a natural question:…

World models play a crucial role in understanding and predicting the dynamics of the world, which is essential for video generation. However, existing world models are confined to specific scenarios such as gaming or driving, limiting their…

Generative video models, a leading approach to world modeling, face fundamental limitations. They often violate physical and logical rules, lack interactivity, and operate as opaque black boxes ill-suited for building structured, queryable…

The concept of world models has garnered significant attention due to advancements in multimodal large language models such as GPT-4 and video generation models such as Sora, which are central to the pursuit of artificial general…

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,…

World models, which predict future transitions from past observation and action sequences, have shown great promise for improving data efficiency in sequential decision-making. However, existing world models often require extensive…

World models aim to learn action-controlled future prediction and have proven essential for the development of intelligent agents. However, most existing world models rely heavily on substantial action-labeled data and costly training,…

General-purpose robots require decision-making models that generalize across diverse tasks and environments. Recent works build robot foundation models by extending multimodal large language models (MLLMs) with action outputs, creating…

Text-conditioned diffusion models have emerged as a promising tool for neural video generation. However, current models still struggle with intricate spatiotemporal prompts and often generate restricted or incorrect motion. To address these…

Adapting pretrained video generation models into controllable world models via latent actions is a promising step towards creating generalist world models. The dominant paradigm adopts a two-stage approach that trains latent action model…

Recent vision-language-action (VLA) models rely on 2D inputs, lacking integration with the broader realm of the 3D physical world. Furthermore, they perform action prediction by learning a direct mapping from perception to action,…

Large Language Models (LLMs) can serve as world models to enhance agent decision-making in digital environments by simulating future states and predicting action outcomes, potentially eliminating costly trial-and-error exploration. However,…

Large language model (LLM) agents trained using reinforcement learning has achieved superhuman performance in low-cost environments like games, mathematics, and coding. However, these successes have not translated to complex domains where…

Robotic manipulation requires anticipating how the environment evolves in response to actions, yet most existing systems lack this predictive capability, often resulting in errors and inefficiency. While Vision-Language Models (VLMs)…

World models are progressively being employed across diverse fields, extending from basic environment simulation to complex scenario construction. However, existing models are mainly trained on domain-specific states and actions, and…

Being able to simulate the outcomes of actions in varied environments will revolutionize the development of generalist agents at scale. However, modeling these world dynamics, especially for dexterous robotics tasks, poses significant…

World models, which encapsulate the dynamics of how actions affect environments, are foundational to the functioning of intelligent agents. In this work, we explore the potential of Large Language Models (LLMs) to operate as world models.…

The landscape of video generation is shifting, from a focus on generating visually appealing clips to building virtual environments that support interaction and maintain physical plausibility. These developments point toward the emergence…

Video Diffusion Models (VDMs) have emerged as powerful generative tools, capable of synthesizing high-quality spatiotemporal content. Yet, their potential goes far beyond mere video generation. We argue that the training dynamics of VDMs,…