Neural Force Field: Few-shot Learning of Generalized Physical Reasoning

TL;DR

Neural Force Field (NFF) introduces a physics-inspired, force-based representation that enables few-shot learning and strong generalization in physical reasoning tasks, surpassing traditional models in out-of-distribution scenarios.

Contribution

NFF extends Neural ODEs with explicit force fields for better physical reasoning and generalization from limited data, a novel approach in AI physics modeling.

Findings

NFF achieves strong generalization with few training examples.

NFF effectively models complex object interactions via continuous force fields.

NFF enables rapid adaptation and planning in physical tasks.

Abstract

Physical reasoning is a remarkable human ability that enables rapid learning and generalization from limited experience. Current AI models, despite extensive training, still struggle to achieve similar generalization, especially in Out-of-distribution (OOD) settings. This limitation stems from their inability to abstract core physical principles from observations. A key challenge is developing representations that can efficiently learn and generalize physical dynamics from minimal data. Here we present Neural Force Field (NFF), a framework extending Neural Ordinary Differential Equation (NODE) to learn complex object interactions through force field representations, which can be efficiently integrated through an Ordinary Differential Equation (ODE) solver to predict object trajectories. Unlike existing approaches that rely on discrete latent spaces, NFF captures fundamental physical concepts such as gravity, support, and collision in continuous explicit force fields. Experiments on three challenging physical reasoning tasks demonstrate that NFF, trained with only a few examples, achieves strong generalization to unseen scenarios. This physics-grounded representation enables efficient forward-backward planning and rapid adaptation through interactive refinement. Our work suggests that incorporating physics-inspired representations into learning systems can help bridge the gap between artificial and human physical reasoning capabilities.