GenEx: Generating an Explorable World
Taiming Lu, Tianmin Shu, Alan L. Yuille, Daniel Khashabi, Jieneng Chen
摘要
Understanding, navigating, and exploring the 3D physical real world has long been a central challenge in the development of artificial intelligence. In this work, we take a step toward this goal by introducing GenEx, a system capable of planning complex embodied world exploration, guided by its generative imagination that forms expectations about the surrounding environments. GenEx generates high-quality, continuous 360-degree virtual environments, achieving high loop consistency and active 3D mapping over extended trajectories. Leveraging generative imagination, GPT-assisted agents can undertake complex embodied tasks, including goal-agnostic exploration and goal-driven navigation. Agents utilize imagined observations to update their beliefs, simulate potential outcomes, and enhance their decision-making. Training on the synthetic urban dataset GenEx-DB and evaluation on GenEx-EQA demonstrate that our approach significantly improves agents' planning capabilities, providing a transformative platform toward intelligent, imaginative embodied exploration.
问问这篇 Paper
智能体会读完全文。
Lune 把这篇 Paper 索引到了每一个公式,引用它的顶会 Paper 也一样。你提问,回答直接引用原文。
引用它的顶会 Paper7
- PanoWan: Lifting Diffusion Video Generation Models to 360° with Latitude/Longitude-aware MechanismsYifei Xia, Shuchen Weng, Siqi Yang, Jingqi Liu 等NeurIPS 2025 · 被引用 24 次
- DA2: Depth Anything in Any DirectionHaodong Li, Wangguandong Zheng, Jing He, Yuhao Liu 等ICLR 2026 · 被引用 23 次
- TV2TV: A Unified Framework for Interleaved Language and Video GenerationXiaochuang Han, Youssef Emad, Melissa Hall, John Nguyen 等CVPR 2026 · 被引用 3 次
- Pantheon360: Taming Digital Twin Generation via 3D-Aware 360° Video DiffusionTing-Hsuan Chen, Ying-Huan Chen, Tao Tu, Jie-Ying Lee 等CVPR 2026 · 被引用 2 次
- 360Explorer: Exploring 4D Controllable World in Panoramic VideosXinhua Cheng, Haiyang Zhou, Wangbo Yu, Tanghui Jia 等AAAI 2026
它引用的顶会 Paper24
- Learning Transferable Visual Models From Natural Language SupervisionAlec Radford, Jong Wook Kim, Chris Hallacy, Aditya Ramesh 等ICML 2021 · 被引用 47,906 次
- Denoising Diffusion Probabilistic ModelsJonathan Ho, Ajay Jain, Pieter AbbeelNeurIPS 2020 · 被引用 35,902 次
- High-Resolution Image Synthesis with Latent Diffusion ModelsRobin Rombach, Andreas Blattmann, Dominik Lorenz, Patrick Esser 等CVPR 2022 · 被引用 13,123 次
- Adding Conditional Control to Text-to-Image Diffusion ModelsLvmin Zhang, Anyi Rao, Maneesh AgrawalaICCV 2023 · 被引用 6,759 次
- Depth Anything V2Lihe Yang, Bingyi Kang, Zilong Huang, Zhen Zhao 等NeurIPS 2024 · 被引用 2,305 次
相关 Paper
- Holodeck: Language Guided Generation of 3D Embodied AI EnvironmentsYue Yang, Fan-Yun Sun, Luca Weihs, Eli VanderBilt 等CVPR 2024 · 被引用 47 次
- EmbodiedGPT: Vision-Language Pre-Training via Embodied Chain of ThoughtYao Mu, Qinglong Zhang, Mengkang Hu, Wenhai Wang 等NeurIPS 2023 · 被引用 453 次
- An Embodied Generalist Agent in 3D WorldJiangyong Huang, Silong Yong, Xiaojian Ma, Xiongkun Linghu 等ICML 2024 · 被引用 361 次
- NavGPT: Explicit Reasoning in Vision-and-Language Navigation with Large Language ModelsGengze Zhou, Yicong Hong, Qi WuAAAI 2024 · 被引用 361 次
- Towards Learning a Generalist Model for Embodied NavigationDuo Zheng, Shijia Huang, Lin Zhao, Yiwu Zhong 等CVPR 2024 · 被引用 37 次
