InternW0: A Foundational Physical World Model for Efficient Real-World Interactions

Hugging Face Daily Papers Papers
physical-world-model robotics ai-research real-world-interactions flow-matching egocentric-data manipulation

Summary

InternW0 is a foundational physical world model from Shanghai AI Laboratory that jointly learns visual dynamics and robot control for efficient real-world interactions, trained on heterogeneous data and evaluated on scientific tasks.

Physical intelligence requires more than predicting how the world may evolve: predictions must remain actionable as the world continues to change. We introduce InternW0, the first instantiation of the InternW physical world model series from Shanghai AI Laboratory, built around omnimodal interfaces, asynchronous multi-frequency processing, and local physical modeling under partial observations and external influences. InternW0 jointly learns future visual dynamics and continuous robot control through an asymmetric video--action architecture with flow matching. A high-capacity video expert provides longer-horizon predictive context, while a lightweight action expert operates at a faster timescale. Instead of regenerating the future for every action update, InternW0 reuses layerwise K/V and adapts it to newly observed states through observation-conditioned context routing. Domain-specific interfaces and soft prompts support heterogeneous embodiments, while contact-aware post-training incorporates force and tactile signals for contact-rich manipulation. We train InternW0 on approximately 7,200 hours of heterogeneous robot and egocentric data, including EgoLab, a 275-hour real-laboratory egocentric dataset. Evaluation spans simulation benchmarks and real-world scientific tasks, including a 15-stage metal--organic framework synthesis workflow and 5-stage contact- and force-aware dexterous manipulation for general-purpose quantitative pipetting. These results advance scalable, asynchronous, and science-native physical world models for universal and efficient real-world interactions.
Original Article
View Cached Full Text

Cached at: 09/24/26, 03:39 AM

Paper page - InternW0: A Foundational Physical World Model for Efficient Real-World Interactions

Source: https://huggingface.co/papers/2609.27656 Authors:

,

,

,

,

,

,

,

,

,

,

,

,

,

,

,

,

,

,

,

,

Abstract

Physicalintelligencerequiresmorethanpredictinghowtheworldmayevolve:predictionsmustremainactionableastheworldcontinuestochange.WeintroduceInternW0,thefirstinstantiationoftheInternWphysicalworldmodelseriesfromShanghaiAILaboratory,builtaroundomnimodalinterfaces,asynchronousmulti-frequencyprocessing,andlocalphysicalmodelingunderpartialobservationsandexternalinfluences.InternW0jointlylearnsfuturevisualdynamicsandcontinuousrobotcontrolthroughanasymmetricvideo--actionarchitecturewithflowmatching.Ahigh-capacityvideoexpertprovideslonger-horizonpredictivecontext,whilealightweightactionexpertoperatesatafastertimescale.Insteadofregeneratingthefutureforeveryactionupdate,InternW0reuseslayerwiseK/Vandadaptsittonewlyobservedstatesthroughobservation-conditionedcontextrouting.Domain-specificinterfacesandsoftpromptssupportheterogeneousembodiments,whilecontact-awarepost-trainingincorporatesforceandtactilesignalsforcontact-richmanipulation.WetrainInternW0onapproximately7,200hoursofheterogeneousrobotandegocentricdata,includingEgoLab,a275-hourreal-laboratoryegocentricdataset.Evaluationspanssimulationbenchmarksandreal-worldscientifictasks,includinga15-stagemetal--organicframeworksynthesisworkflowand5-stagecontact-andforce-awaredexterousmanipulationforgeneral-purposequantitativepipetting.Theseresultsadvancescalable,asynchronous,andscience-nativephysicalworldmodelsforuniversalandefficientreal-worldinteractions.

View arXiv pageView PDFProject pageAdd to collection

Get this paper in your agent:

hf papers read 2609\.27656

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/2609.27656 in a model README.md to link it from this page.

Datasets citing this paper0

No dataset linking this paper

Cite arxiv.org/abs/2609.27656 in a dataset README.md to link it from this page.

Spaces citing this paper0

No Space linking this paper

Cite arxiv.org/abs/2609.27656 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

In-Context World Modeling for Robotic Control

Hugging Face Daily Papers

This paper introduces In-Context World Modeling (ICWM), a framework that enables robot policies to infer system variables from self-generated interactions, allowing adaptation to novel configurations without parameter updates by treating system identification as an in-context adaptation problem. It outperforms standard VLA baselines on novel camera viewpoints in simulation and real-world experiments.

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.

τ_0-WM: A Unified Video-Action World Model for Robotic Manipulation

Hugging Face Daily Papers

τ_0-WM is a unified video-action world model for robotic manipulation that integrates policy learning, video prediction, and action evaluation using a shared video diffusion backbone. It shows superior performance on challenging long-horizon and fine-grained tasks.

World in World: Explore the World with World Models

Hugging Face Daily Papers

The paper presents World in World, a training-free interface that enables flexible camera and time control in frozen autoregressive video world models by using correspondence-guided queries and evidence-wise attention guidance.