Research map / Probabilistic and scientific modeling / Dynamical systems
ElastoGen: 4D Generative Elastodynamics
Yutao Feng, Yintong Shang, Xiang Feng, Lei Lan, Shandian Zhe, Tianjia Shao, Hongzhi Wu, Kun Zhou, Chenfanfu Jiang, Yin Yang
Read the paperCheck your idea against 137,217 papers
AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Measured effects reported in the paper
| What was changed | Where | Measured | Effect |
|---|---|---|---|
| use ElastoGen instead of Gen-2 video generation | 4D elastodynamics · Swinging carnation vs reference | IoU: 64% -> 94% | Improved |
| use ElastoGen instead of PhysDreamer | 4D elastodynamics · Swinging carnation vs reference | IoU: 75% -> 94% | Improved |
| add NeuralMTL neural strain to quadratic local energy | ElastoGen · Cantilever beam (co-rotational, Neo-Hookean, StVK) | strain correlation with ground truth | Improved |
| increase RNN-1 and RNN-2 loop counts (ablation) | ElastoGen · Large-scale Neo-Hookean twisting | convergence to FEM ground truth | Improved |
| add subspace (low-frequency) encoder to initialize inner RNN (ablation) | ElastoGen · stiff materials | number of RNN loops needed | Improved |
Closest papers by meaning
- UniPhy: Learning a Unified Constitutive Model for Inverse Physics Simulation (CVPR 2025 · similarity 0.86)
- PhysGaussian: Physics-Integrated 3D Gaussians for Generative Dynamics (CVPR 2024 · similarity 0.84)
- Discovering Phase Space Structure in Learned Hamiltonian Systems (NeurIPS 2026 · similarity 0.84)
- LEIA: Learned Environment for Interactive Architected Materials (NeurIPS 2026 · similarity 0.84)
- PIE-NeRF: Physics-based Interactive Elastodynamics with NeRF (CVPR 2024 · similarity 0.84)
- Diffusion-Based Hierarchical Graph Neural Networks for Simulating Nonlinear Solid Mechanics (NeurIPS 2025 · similarity 0.83)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.
