PhysLDM: Latent Diffusion for High-Fidelity Deformable Simulation

Hugging Face Daily Papers Papers
latent-diffusion physics-simulation deformable-bodies computer-graphics spatiotemporal-vae physical-ai zero-shot-generalization

Summary

PhysLDM 提出了一种用于高保真可变形体物理模拟的时空隐空间扩散框架，采用整体式 VAE 实现约 78 倍 token 压缩与 ~2.48 mm 重建精度，并证明扩散模型比确定性回归更能建模混沌动力学，实现零样本泛化与逆问题求解。

Neural simulation of high-fidelity deformable bodies is a foundational challenge in computer graphics and physical AI. Long-horizon prediction for high-resolution 3D volumetric meshes is hard: autoregressive methods are prone to error accumulation, while direct multi-frame prediction at native resolution is computationally prohibitive. This motivates a compact spatiotemporal latent representation, which is largely unexplored for mesh-based volumetric physics. Meanwhile, it remains unclear whether deterministic regression or generative diffusion is the more suitable predictive paradigm. To address these coupled challenges, we introduce PhysLDM, a unified latent-diffusion paradigm for one-shot deformable simulation. Its core is a holistic spatiotemporal VAE that avoids the "staircase" artifacts of standard temporal compression (e.g., video VAEs), achieving ~2.48 mm reconstruction precision on meter-scale scenes at up to 78x token compression. Based on this reliable latent space, we systematically compare regression and diffusion methods. Our experiments uncover a key modeling insight: complex deformable dynamics are often chaotic, and in this regime deterministic regression tends to produce non-physical averages, whereas diffusion better models their distribution. Accordingly, we employ a latent diffusion model that effectively learns from chaotic data to generate physically plausible trajectories. Trained purely kinematically on an Objaverse-scale dataset, a single PhysLDM generalizes zero-shot to unseen OOD datasets. Its differentiability further enables efficient solution of inverse problems and higher-order design optimization. To our knowledge, PhysLDM is the first high-fidelity spatiotemporal autoencoder and latent-diffusion paradigm for volumetric deformable dynamics, offering a scalable and robust approach to neural simulation. Project Page: https://yucrazing.github.io/physldm/
Original Article
View Cached Full Text

Cached at: 10/21/26, 10:20 AM

Paper page - PhysLDM: Latent Diffusion for High-Fidelity Deformable Simulation

Source: https://huggingface.co/papers/2610.07609

Abstract

PhysLDM introduces a spatiotemporal latent diffusion framework for high-fidelity deformable body simulation, using a holistic VAE and diffusion to model chaotic dynamics and enable zero-shot generalization.

Neural simulation of high-fidelity deformable bodies is a foundational challenge in computer graphics and physical AI. Long-horizon prediction for high-resolution 3Dvolumetric meshesis hard: autoregressive methods are prone to error accumulation, while direct multi-frame prediction at native resolution is computationally prohibitive. This motivates a compact spatiotemporal latent representation, which is largely unexplored for mesh-based volumetric physics. Meanwhile, it remains unclear whether deterministic regression or generative diffusion is the more suitable predictive paradigm. To address these coupled challenges, we introduce PhysLDM, a unified latent-diffusion paradigm for one-shot deformable simulation. Its core is a holisticspatiotemporal VAEthat avoids the “staircase” artifacts of standard temporal compression (e.g., video VAEs), achieving ~2.48 mm reconstruction precision on meter-scale scenes at up to 78x token compression. Based on this reliable latent space, we systematically compare regression and diffusion methods. Our experiments uncover a key modeling insight: complexdeformable dynamicsare often chaotic, and in this regime deterministic regression tends to produce non-physical averages, whereas diffusion better models their distribution. Accordingly, we employ alatent diffusion modelthat effectively learns from chaotic data to generate physically plausible trajectories. Trained purely kinematically on an Objaverse-scale dataset, a single PhysLDM generalizes zero-shot to unseen OOD datasets. Its differentiability further enables efficient solution ofinverse problemsand higher-order design optimization. To our knowledge, PhysLDM is the first high-fidelity spatiotemporal autoencoder and latent-diffusion paradigm for volumetricdeformable dynamics, offering a scalable and robust approach to neural simulation. Project Page: https://yucrazing.github.io/physldm/

View arXiv pageView PDFProject pageAdd to collection

Get this paper in your agent:

hf papers read 2610\.07609

Don’t have the latest CLI?curl \-LsSf https://hf\.co/cli/install\.sh \| bash

Models citing this paper0

No model linking this paper

Cite arxiv.org/abs/2610.07609 in a model README.md to link it from this page.

Datasets citing this paper0

No dataset linking this paper

Cite arxiv.org/abs/2610.07609 in a dataset README.md to link it from this page.

Spaces citing this paper0

No Space linking this paper

Cite arxiv.org/abs/2610.07609 in a Space README.md to link it from this page.

Collections including this paper0

No Collection including this paper

Add this paper to acollectionto link it from this page.

Similar Articles

ALoDLM: Adaptively Looped Diffusion Language Models

Hugging Face Daily Papers

ALoDLM introduces token-adaptive latent recurrence for diffusion language models, allocating extra computation to difficult tokens and using a conditional negative ELBO to jointly learn prediction and compute allocation, outperforming other DLMs and AR baselines at 1.7B and 8B scales across eleven benchmarks.

Representation-Space MMD for Diffusion Language Models

Hugging Face Daily Papers

This paper introduces a post-training method for diffusion language models that minimizes Maximum Mean Discrepancy between generated and reference distributions in the feature space of a frozen pretrained DLM, achieving lower generative perplexity and better accuracy-compute trade-offs on OpenWebText and GSM8K, with improved decoding parallelism on 16B LLaDA-2.0 models.