Related papers: WorldAct: Activating Monolithic 3D Worlds into Int…

Unbounded 3D world generation is emerging as a foundational task for scene modeling in computer vision, graphics, and robotics. In this work, we present WorldFlow3D, a novel method capable of generating unbounded 3D worlds. Building upon a…

We propose a spatial-constraint approach for modeling spatial-based interactions and enabling interactive visualizations, which involves the manipulation of visualizations through selection, filtering, navigation, arrangement, and…

In this work, we propose a framework that creates a lively virtual dynamic scene with contextual motions of multiple humans. Generating multi-human contextual motion requires holistic reasoning over dynamic relationships among human-human…

3D world generation is essential for applications such as immersive content creation or autonomous driving simulation. Recent advances in 3D world generation have shown promising results; however, these methods are constrained by grid…

Multimodal large language models are evolving toward multimodal agents capable of proactively executing tasks. Most agent research focuses on GUI or embodied scenarios, which correspond to agents interacting with 2D virtual worlds or 3D…

LangDriveCTRL is a natural-language-controllable framework for editing real-world driving videos to synthesize diverse traffic scenarios. It represents each video as an explicit 3D scene graph, decomposing the scene into a static background…

Generative world models are reshaping embodied AI, enabling agents to synthesize realistic 4D driving environments that look convincing but often fail physically or behaviorally. Despite rapid progress, the field still lacks a unified way…

This paper presents ShareVerse, a video generation framework enabling multi-agent shared world modeling, addressing the gap in existing works that lack support for unified shared world construction with multi-agent interaction. ShareVerse…

3D simulated environments play a critical role in Embodied AI, but their creation requires expertise and extensive manual effort, restricting their diversity and scope. To mitigate this limitation, we present Holodeck, a system that…

Generating realistic 3D indoor scenes from user inputs remains a challenging problem in computer vision and graphics, requiring careful balance of geometric consistency, spatial relationships, and visual realism. While neural generation…

A plausible scene evolution depends on the maneuver being considered, while a good maneuver depends on how the scene may evolve. Existing World Action Models (WAMs) largely miss this reciprocity, treating world prediction and action…

Recent advances in generative world models have enabled remarkable progress in creating open-ended game environments, evolving from static scene synthesis toward dynamic, interactive simulation. However, current approaches remain limited by…

Despite recent advancements in text-to-image generation, most existing methods struggle to create images with multiple objects and complex spatial relationships in the 3D world. To tackle this limitation, we introduce a generic AI system,…

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…

Generating articulated objects, such as laptops and microwaves, is a crucial yet challenging task with extensive applications in Embodied AI and AR/VR. Current image-to-3D methods primarily focus on surface geometry and texture, neglecting…

We tackle the problem of generating long-term 3D human motion from multiple action labels. Two main previous approaches, such as action- and motion-conditioned methods, have limitations to solve this problem. The action-conditioned methods…

Embodied AI depends on interactive 3D environments that support meaningful activities for diverse users, yet assessing their functional affordances remains a core challenge. We introduce SceneTeract, a framework that verifies 3D scene…

Video--based world models have emerged along two dominant paradigms: video generation and 3D reconstruction. However, existing evaluation benchmarks either focus narrowly on visual fidelity and text--video alignment for generative models,…

Procedurally generating cohesive and interesting game environments is challenging and time-consuming. In order for the relationships between the game elements to be natural, common-sense has to be encoded into arrangement of the elements.…

Learning latent actions from action-free video has emerged as a powerful paradigm for scaling up controllable world model learning. Latent actions provide a natural interface for users to iteratively generate and manipulate videos. However,…