[2605.15305] WorldParticle: Unified Simulation of Lagrangian Particle Dynamics via Transformer
-->
Computer Science > Graphics
arXiv:2605.15305 (cs)
[Submitted on 14 May 2026 (v1), last revised 19 May 2026 (this version, v3)]
Title:WorldParticle: Unified Simulation of Lagrangian Particle Dynamics via Transformer
Authors:Caoliwen Wang, Minghao Guo, Siyuan Chen, Heng Zhang, Mengdi Wang, Xingyu Ni, Hanson Sun, Kunyi Wang, Zherong Pan, Kui Wu, Lingjie Liu, Yin Yang, Chenfanfu Jiang, Taku Komura, Wojciech Matusik, Peter Yichen Chen<br>View a PDF of the paper titled WorldParticle: Unified Simulation of Lagrangian Particle Dynamics via Transformer, by Caoliwen Wang and 15 other authors
View PDF<br>HTML (experimental)
Abstract:A unified simulator that can model diverse physical phenomena without solver-specific redesign is a long-standing goal across simulation science. We present a learning-based particle simulator built on a single transformer architecture to model cloth, elastic solds, Newtonian and non-Newtonian fluids, granular materials, and molecular dynamics. Our model follows a prediction-correction design on a shared Lagrangian particle representation. An explicit predictor first advances particles under the known external forces, producing an intermediate state that captures externally driven motion but not inter-particle interactions. A learned corrector then predicts the residual position and velocity updates through three stages: a particle tokenizer that encodes local particle-particle, particle-boundary, and topology-guided interactions; a super-token encoder that hierarchically merges particle tokens into a compact set of super tokens via alternating self-attention and token merging; and a super-token decoder that lifts these super tokens back to particle resolution through cross-attention to predict per-particle position and velocity corrections. Progressive token merging reduces the attention cost at successive encoder layers by halving the token count at each level, and the decoder communicates through the compact super-token set rather than full particle-to-particle attention. Across the six dynamics categories, the same architecture generalizes to unseen materials, boundary configurations, initial conditions, and external forces. We further demonstrate downstream interactive control, inverse design, and learning from real-world manipulation data, reducing the need for per-phenomenon solver engineering.
Subjects:
Graphics (cs.GR); Machine Learning (cs.LG)
Cite as:<br>arXiv:2605.15305 [cs.GR]
(or<br>arXiv:2605.15305v3 [cs.GR] for this version)
https://doi.org/10.48550/arXiv.2605.15305
Focus to learn more
arXiv-issued DOI via DataCite
Submission history<br>From: Minghao Guo [view email]<br>[v1]<br>Thu, 14 May 2026 18:18:12 UTC (43,900 KB)
[v2]<br>Mon, 18 May 2026 17:34:36 UTC (43,900 KB)
[v3]<br>Tue, 19 May 2026 03:08:14 UTC (43,900 KB)
Full-text links:<br>Access Paper:
View a PDF of the paper titled WorldParticle: Unified Simulation of Lagrangian Particle Dynamics via Transformer, by Caoliwen Wang and 15 other authors<br>View PDF<br>HTML (experimental)<br>TeX Source
view license
Current browse context:
cs.GR
next >
new<br>recent<br>| 2026-05
Change to browse by:
cs<br>cs.LG
References & Citations
NASA ADS<br>Google Scholar
Semantic Scholar
export BibTeX citation<br>Loading...
BibTeX formatted citation
×
loading...
Data provided by:
Bookmark
Bibliographic Tools
Bibliographic and Citation Tools
Bibliographic Explorer Toggle
Bibliographic Explorer (What is the Explorer?)
Connected Papers Toggle
Connected Papers (What is Connected Papers?)
Litmaps Toggle
Litmaps (What is Litmaps?)
scite.ai Toggle
scite Smart Citations (What are Smart Citations?)
Code, Data, Media
Code, Data and Media Associated with this Article
alphaXiv Toggle
alphaXiv (What is alphaXiv?)
Links to Code Toggle
CatalyzeX Code Finder for Papers (What is CatalyzeX?)
DagsHub Toggle
DagsHub (What is DagsHub?)
GotitPub Toggle
Gotit.pub (What is GotitPub?)
Huggingface Toggle
Hugging Face (What is Huggingface?)
ScienceCast Toggle
ScienceCast (What is ScienceCast?)
Demos
Demos
Replicate Toggle
Replicate (What is Replicate?)
Spaces Toggle
Hugging Face Spaces (What is Spaces?)
Spaces Toggle
TXYZ.AI (What is TXYZ.AI?)
Related Papers
Recommenders and Search Tools
Link to Influence Flower
Influence Flower (What are Influence Flowers?)
Core recommender toggle
CORE Recommender (What is CORE?)
Author
Venue
Institution
Topic
About arXivLabs
arXivLabs: experimental projects with community collaborators
arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website.
Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them.
Have an idea for a project that will add value for arXiv's...