提出可任意条件化时间与物体的物理推理扩散模型
Object-centric Denoising Diffusion Models for Physical Reasoning
- 基于对象中心的扩散模型，支持任意时间点条件输入
- 能同时处理多物体交互轨迹，支持不同物体数量和长度推理
- 适合需要灵活条件控制的强化学习规划任务
机器学习中的物理推理任务需分析多个相互作用物体的运动轨迹，通常依赖初始状态等时间点条件。现有方法多采用自回归建模，仅能基于初始状态进行条件控制，无法处理后期状态约束。在强化学习规划等领域，去噪扩散模型已展现潜力。本文提出一种面向物理推理的对象中心去噪扩散模型架构，具备时间平移等变性、物体排列等变性，且可对任意时间点、任意物体进行条件控制。实验验证该模型可解决多条件任务，并在推理阶段改变物体数量与轨迹长度时仍保持良好性能。
原文摘要 · Abstract (English)
Reasoning about the trajectories of multiple, interacting objects is integral to physical reasoning tasks in machine learning. This involves conditions imposed on the objects at different time steps, for instance initial states or desired goal states. Existing approaches in physical reasoning generally rely on autoregressive modeling, which can only be conditioned on initial states, but not on later states. In fields such as planning for reinforcement learning, similar challenges are being addressed with denoising diffusion models. In this work, we propose an object-centric denoising diffusion model architecture for physical reasoning that is translation equivariant over time, permutation equivariant over objects, and can be conditioned on arbitrary time steps for arbitrary objects. We demonstrate how this model can solve tasks with multiple conditions and examine its performance when changing object numbers and trajectory lengths during inference.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。