Unisoma: A Unified Transformer-based Solver for Multi-Solid Systems

TL;DR

Unisoma is a Transformer-based model that explicitly captures physical interactions in multi-solid systems, improving accuracy and interpretability over implicit methods across diverse datasets.

Contribution

The paper introduces Unisoma, a novel explicit modeling framework with structured modules for handling variable numbers of solids in multi-solid systems.

Findings

Achieves state-of-the-art performance on seven datasets

Handles complex multi-solid interactions effectively

Provides a flexible, interpretable modeling approach

Abstract

Multi-solid systems are foundational to a wide range of real-world applications, yet modeling their complex interactions remains challenging. Existing deep learning methods predominantly rely on implicit modeling, where the factors influencing solid deformation are not explicitly represented but are instead indirectly learned. However, as the number of solids increases, these methods struggle to accurately capture intricate physical interactions. In this paper, we introduce a novel explicit modeling paradigm that incorporates factors influencing solid deformation through structured modules. Specifically, we present Unisoma, a unified and flexible Transformer-based model capable of handling variable numbers of solids. Unisoma directly captures physical interactions using contact modules and adaptive interaction allocation mechanism, and learns the deformation through a triplet relationship. Compared to implicit modeling techniques, explicit modeling is more well-suited for multi-solid systems with diverse coupling patterns, as it enables detailed treatment of each solid while preventing information blending and confusion. Experimentally, Unisoma achieves consistent state-of-the-art performance across seven well-established datasets and two complex multi-solid tasks. Code is avaiable at https://github.com/therontau0054/Unisoma.