This paper introduces GS-Agent, an end-to-end multi-agent framework that generates realistic, dynamic, and controllable 4D physical worlds from natural language descriptions by emulating human creatio…

The paper introduces WorldCoder-Bench, a comprehensive benchmark and evaluation protocol for testing LLMs' ability to autonomously generate complex, physically grounded, and interactive 3D web worlds.

The paper introduces U4D, an uncertainty-aware framework that synthesizes 4D LiDAR scenes by prioritizing the reconstruction of geometrically difficult and uncertain regions first, leading to state-of…

The paper introduces SPAWN, a training-free method that allows users to inject specified visual concepts into existing autoregressive world models, enabling controllable scene composition beyond the i…

PhyGenHOI introduces a novel framework that generates physically accurate and visually faithful 4D Human-Object Interactions by coupling generative human motion with explicit physical object simulatio…

This paper introduces Align4D, a framework for generating coherent video-3D pairs using any-modal input, achieving state-of-the-art quality and consistency in X-to-4D generation.

The paper introduces DreamForge-World 0.1 Preview, a low-compute real-time interactive world simulation system using a residual action pathway and open video backbones.

This paper introduces FutureSurf, a benchmark and dataset for evaluating dynamic-scene reconstruction methods' ability to predict future surface geometry.

MORPHOS is a novel autoregressive framework that generates dynamic 3D assets (like meshes and radiance fields) from videos by using a unified 4D representation to ensure temporal consistency and handl…

CubePart is a generative framework that enables the creation of complex 3D meshes by explicitly controlling and generating individual, semantically defined parts based on open-vocabulary text prompts.

The paper introduces SynCity 3000, a framework for generating large, coherent 3D scenes using a convolutional generator, addressing the scarcity of 3D scene data for training.

HandMade is a workflow that combines VR 3D sketching and language for open-domain 3D asset generation, allowing users to specify object layout and part relationships through 3D sketching and language.

Introduces Looped World Models, a looped architecture for world modelling that iteratively refines latent environment states for up to 100x parameter efficiency.

The paper introduces LingBot-World 2.0, an advanced version of a language model with unbounded interaction horizon, rapid response time, diverse interactive elements, and agentic harness integration.

The paper introduces WorldDirector, a framework for creating controllable video worlds with persistent dynamic object memory and exact visual identities.

The paper proposes Astra, an agentic framework that equips Vision-Language Models (VLMs) with the ability to perform spatial reasoning by actively generating and utilizing imagined visual evidence fro…

GeM-NR proposes a novel, training-free framework to achieve general multi-view image editing, enabling consistent edits that drastically change both the geometry and appearance of a nonrigid scene.

This paper investigates the robustness of world models in vision-based quadrotor navigation and identifies factors governing their quality.