PhiZero: A World Model Built Around Physical Language

Hugging Face Daily Papers Papers
world-model physical-language video-generation self-supervised reasoning-then-rendering

Summary

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.

We introduce PhiZero, a physical world model built around physical language, a compact discrete representation of world-state transitions. Existing physical world models typically predict future videos directly in pixel space, leaving the underlying world dynamics implicit within high-dimensional visual predictors. Motivated by humans' ability to abstract predictive structure from visual experience and organize it in natural language for explicit reasoning, we learn physical language from in-the-wild videos through self-supervision and use it to explicitly reason about how the physical world evolves. Accordingly, PhiZero adopts a reason-then-render paradigm: it first infers future world evolution as a physical-language sequence and then renders the inferred transitions into videos. Extensive experiments across generation and understanding benchmarks validate the ability of PhiZero to model physically coherent world evolution. We further show its potential for realistic and interactive world modeling, fine-grained action-conditioned simulation, and zero-shot motion transfer.
Original Article
View Cached Full Text

Cached at: 07/31/26, 05:53 AM

Paper page - PhiZero: A World Model Built Around Physical Language

Source: https://huggingface.co/papers/2607.28624

Abstract

WeintroducePhiZero,aphysicalworldmodelbuiltaroundphysicallanguage,acompactdiscreterepresentationofworld-statetransitions.Existingphysicalworldmodelstypicallypredictfuturevideosdirectlyinpixelspace,leavingtheunderlyingworlddynamicsimplicitwithinhigh-dimensionalvisualpredictors.Motivatedbyhumans’abilitytoabstractpredictivestructurefromvisualexperienceandorganizeitinnaturallanguageforexplicitreasoning,welearnphysicallanguagefromin-the-wildvideosthroughself-supervisionanduseittoexplicitlyreasonabouthowthephysicalworldevolves.Accordingly,PhiZeroadoptsareason-then-renderparadigm:itfirstinfersfutureworldevolutionasaphysical-languagesequenceandthenrenderstheinferredtransitionsintovideos.ExtensiveexperimentsacrossgenerationandunderstandingbenchmarksvalidatetheabilityofPhiZerotomodelphysicallycoherentworldevolution.Wefurthershowitspotentialforrealisticandinteractiveworldmodeling,fine-grainedaction-conditionedsimulation,andzero-shotmotiontransfer.

View arXiv pageView PDFProject pageGitHub2Add to collection

Get this paper in your agent:

hf papers read 2607\.28624

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/2607.28624 in a model README.md to link it from this page.

Datasets citing this paper0

No dataset linking this paper

Cite arxiv.org/abs/2607.28624 in a dataset README.md to link it from this page.

Spaces citing this paper0

No Space linking this paper

Cite arxiv.org/abs/2607.28624 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

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.

PhysiFormer: Learning to Simulate Mechanics in World Space

Hugging Face Daily Papers

PhysiFormer uses coordinate-space diffusion to generate physically-plausible 3D object motions without explicit inductive biases, enabling efficient multi-object reasoning and generalization to complex materials and geometries.

A Tutorial on World Models and Physical AI

arXiv cs.AI

This tutorial presents a coherent framework unifying diverse world modeling approaches for physical AI, covering explicit and implicit world models and their role in prediction, reasoning, and planning.

Apple-π: Benchmarking Thinking with Video Towards Law-Grounded Physical Intelligence

Hugging Face Daily Papers

Apple-π is a benchmark that evaluates video generation models on their ability to reason about physical laws through a three-stage protocol: perception, formulation, deduction. It includes 400 videos covering classical mechanics tasks and reveals current models fall short of reliable law-grounded world simulation.

Qwen's Embodied World Modeling (28 minute read)

TLDR AI

The Qwen-RobotWorld technical report presents a unified language-conditioned video world model for embodied intelligence, enabling future video prediction from current observations across various domains like robotics, autonomous driving, and navigation, with applications in synthetic data generation, policy evaluation, and planning.