English(EN)NeoWorld-Pro: Programming Interactive Scenes from Monocular Images for Embodied Simulation
新框架通过跨具身学习和程序化生成增强具身AI模拟
作者PulseAugur 编辑部·[7 个来源]·
研究人员开发了用于为具身AI创建更真实、更通用的模拟环境的新框架。CLAP通过协调不同的动作空间，能够在不同机器人和人类代理的各种视频数据上进行训练，旨在提高泛化能力并超越单一具身模型。4DSynth从自然语言、蓝图或照片生成可控、可编辑的4D环境，便于创建动态模拟。NeoWorld-Pro使用MLLM将单张图像转换为可执行程序，用于交互式3D环境，并通过物理引擎进行优化以提高真实性，从而能够执行复杂的下游任务。
AI
arXiv:2608.27406v1 Announce Type: cross Abstract: State-of-the-art action-conditioned video models are typically restricted to a single robot embodiment, preventing them from leveraging the vast corpus of heterogeneous video data that contains rich signals for learning generaliza…
State-of-the-art action-conditioned video models are typically restricted to a single robot embodiment, preventing them from leveraging the vast corpus of heterogeneous video data that contains rich signals for learning generalizable physics. To bridge this gap, we introduce CLAP…
Embodied agents need environments that are visually diverse, physically interactive, and changing over time. Procedural simulators can generate large interactive scene collections, and recent 4D generators produce compelling visual dynamics. Combining these properties in one envi…
The advancement of Embodied AI necessitates high-quality simulation assets that faithfully mirror the real world. However, transforming raw visual observations into simulation-ready scenes remains challenging due to the lack of physical grounding and scene-level interactivity in …
arXiv:2608.29881v1 Announce Type: new Abstract: Monocular depth estimation has achieved strong open-domain generalization, yet reliable robotic deployment remains difficult in transparent, reflective, and specular environments, where depth sensors often produce missing or biased …
arXiv:2608.26947v1 Announce Type: cross Abstract: Embodied agents need environments that are visually diverse, physically interactive, and changing over time. Procedural simulators can generate large interactive scene collections, and recent 4D generators produce compelling visua…
arXiv:2608.24212v1 Announce Type: new Abstract: The advancement of Embodied AI necessitates high-quality simulation assets that faithfully mirror the real world. However, transforming raw visual observations into simulation-ready scenes remains challenging due to the lack of phys…
