Physis-Lang: Self-Evolving Language as a Physical Representation for Video World Model

Hugging Face Daily Papers Papers
video-generation world-models physical-reasoning language-representation benchmark agents

Summary

The paper introduces Physis-Lang, a self-evolving framework that uses physical language as a shared, optimizable representation across data curation, training, and video generation, alongside the PhysCapBench benchmark and an agentic loop for refining physical captions. With open-source Cosmos-Nano backbones, the enhanced models surpass proprietary Veo3.1 on physical plausibility benchmarks.

Video world models are expected to predict how the physical world evolves, yet they often produce visually plausible videos that violate basic physical principles. Existing approaches commonly assume that natural language is insufficient to represent the physical knowledge required for reliable generation, and therefore introduce additional visual, latent, numerical, or planning-based signals. We revisit this assumption and introduce Physis-Lang, a self-evolving framework that treats physical language as a shared and optimizable representation across data curation, model training, and video generation. Physis-Lang represents physical processes through language that describes their relevant entities, causes, interactions, governing principles, temporal evolution, and effects. To improve this representation, we construct PhysCapBench, which decomposes physical processes into atomic assertions and evaluates captions using recall and precision. An agentic loop iteratively analyzes assertion-level errors and refines the instruction used to produce physical captions. Physis-Lang further converts model deficiencies into textual descriptions and uses language-guided retrieval to identify visually diverse videos that cover missing physical processes. Experiments on four widely used physical video benchmarks with Wan and Cosmos backbones demonstrate consistent improvements in physical plausibility. Notably, starting from open-source Cosmos3-Nano backbones, our Physis-Lang-enhanced models surpass the leading proprietary Veo 3.1 model.
Original Article
View Cached Full Text

Cached at: 10/01/26, 04:21 AM

Paper page - Physis-Lang: Self-Evolving Language as a Physical Representation for Video World Model

Source: https://huggingface.co/papers/2609.40358 Authors:

,

,

,

,

,

,

,

,

,

,

,

,

,

,

,

Abstract

Videoworldmodelsareexpectedtopredicthowthephysicalworldevolves,yettheyoftenproducevisuallyplausiblevideosthatviolatebasicphysicalprinciples.Existingapproachescommonlyassumethatnaturallanguageisinsufficienttorepresentthephysicalknowledgerequiredforreliablegeneration,andthereforeintroduceadditionalvisual,latent,numerical,orplanning-basedsignals.WerevisitthisassumptionandintroducePhysis-Lang,aself-evolvingframeworkthattreatsphysicallanguageasasharedandoptimizablerepresentationacrossdatacuration,modeltraining,andvideogeneration.Physis-Langrepresentsphysicalprocessesthroughlanguagethatdescribestheirrelevantentities,causes,interactions,governingprinciples,temporalevolution,andeffects.Toimprovethisrepresentation,weconstructPhysCapBench,whichdecomposesphysicalprocessesintoatomicassertionsandevaluatescaptionsusingrecallandprecision.Anagenticloopiterativelyanalyzesassertion-levelerrorsandrefinestheinstructionusedtoproducephysicalcaptions.Physis-Langfurtherconvertsmodeldeficienciesintotextualdescriptionsanduseslanguage-guidedretrievaltoidentifyvisuallydiversevideosthatcovermissingphysicalprocesses.ExperimentsonfourwidelyusedphysicalvideobenchmarkswithWanandCosmosbackbonesdemonstrateconsistentimprovementsinphysicalplausibility.Notably,startingfromopen-sourceCosmos3-Nanobackbones,ourPhysis-Lang-enhancedmodelssurpasstheleadingproprietaryVeo3.1model.

View arXiv pageView PDFProject pageAdd to collection

Models citing this paper0

No model linking this paper

Cite arxiv.org/abs/2609.40358 in a model README.md to link it from this page.

Datasets citing this paper0

No dataset linking this paper

Cite arxiv.org/abs/2609.40358 in a dataset README.md to link it from this page.

Spaces citing this paper0

No Space linking this paper

Cite arxiv.org/abs/2609.40358 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

PhiZero: A World Model Built Around Physical Language

Hugging Face Daily Papers

PhiZero is a physical world model that learns a compact discrete representation called 'physical language' from videos and uses it to reason about world state transitions before rendering future videos, improving physical coherence in generation and understanding tasks.

EgoPhys: Learning Generalizable Physics Models of Deformable Objects from Egocentric Video

Hugging Face Daily Papers

EgoPhys introduces a framework to construct deformable physical digital twins from egocentric RGB video using generalizable priors and a compact codebook, enabling zero-shot generalization to unseen objects without per-spring optimization. The system is demonstrated on a real robot, showing that egocentric human play video can serve as internal world representation for deformable-object planning.

PhysBrain 1.0 Technical Report

Hugging Face Daily Papers

PhysBrain 1.0 is a technical report presenting a method that uses human egocentric video to generate physical commonsense supervision for vision-language-action models, achieving state-of-the-art results on embodied control benchmarks including ERQA, PhysBench, SimplerEnv-WidowX, LIBERO, and RoboCasa.