New: the Timeline is live. Track world model releases, papers, and benchmark updates in real time.
world-models.io
The Knowledge Hub for AI World Models

WHAM

WHAM is Microsoft Research's explicit world model for generating interactive game worlds and human actions.

robotics model-based-rl simulation embodied-ai

Key Attributes

Static HTML snapshot of the model record for crawlers and no-JS readers.

AttributeValue
ModelWHAM
Lab / OrganizationMSR
CategoryGenerative World Model
SubtypeWorld and Human Action Model
World Model TypeGenerative model of game worlds and human controller actions
Primary DomainInteractive Media
ArchitectureGenerative action-conditioned world model
ModalityGame Video + Controller Actions → Future Video + Actions
Training MethodGenerative modeling of gameplay video and human controller traces
Statusactive
Year2025

About WHAM

Main editorial body preserved directly in static HTML.

WHAM is Microsoft Research's first World and Human Action Model, developed with Ninja Theory as part of the Muse research program. It jointly generates coherent game-world visuals and controller actions, making it an explicit world-model entry for interactive-media research.

WHAM is a generative model of game worlds and human controller actions developed by Microsoft Research / Ninja Theory in 2025 for interactive media.

Editorial Snapshot

Short extractable facts for answer engines and no-JS readers.

SignalValue
DefinitionWHAM is a generative model of game worlds and human controller actions developed by Microsoft Research / Ninja Theory in 2025 for interactive media.
Short DescriptionMicrosoft Research's World and Human Action Model, explicitly designed to model game environments together with human actions.
Benchmark Rows0
FAQ Entries1
Related Models3
Related Guides0
Related Research Topics0
Last Updated2026-07-19

Notable Features

Key capabilities associated with this model.

  • Explicit World and Human Action Model designation
  • Joint world and action generation
  • Developed with Xbox Game Studios' Ninja Theory

Use Cases

Representative applications attached to this model record.

Game ideationInteractive-media prototypingGameplay simulation

Strengths and Limitations

Balanced assessment surfaced in static HTML.

Strengths

  • Primary-source world-model designation
  • Models both environment and actions

Limitations

  • Research-focused
  • Limited public technical and benchmark detail

References and Citations

Primary references preserved in static HTML for citation extraction.

ReferenceLink
Microsoft Research, 2025. WHAM: World and Human Action Models.Open source

Related Models

Nearby models linked from the current editorial record.

ModelCategoryWorld Model TypeIndex v1.1
WHAM-RTGenerative World ModelReal-time generative world model for interactive mediaN/A
Genie 3Generative World ModelReal-time interactive 3D environment generation89/100
OASISGenerative World ModelReal-time playable world model66/100

Frequently Asked Questions

FAQ answers rendered directly into static HTML for extractable responses.

Why is WHAM included?

Microsoft Research explicitly calls WHAM a World and Human Action Model, which models both the environment and actions.

Quick Answer

Short extractable summary preserved directly in static HTML.

  • WHAM is a generative model of game worlds and human controller actions developed by Microsoft Research / Ninja Theory in 2025 for interactive media.
  • Use this page when you need a fast read on how WHAM fits into the generative world model landscape, then validate the details in the benchmarks, citations, and related pages.
  • A key strength surfaced in the editorial record is primary-source world-model designation.

Editorial Trust Signals

Editorial provenance and refresh policy preserved directly in static HTML.

Published by world-models.io editorial board.

Lead editor Tyler D. - Technical editor, methodology and benchmark analysis.

This model page synthesizes primary papers, official model pages, benchmark evidence, and related world-models.io context into a reference resource.

Each editorial page is assembled from primary sources, normalized into extractable summaries, checked for factual drift, and reviewed before publication or major refreshes. Last reviewed: 2026-07-19.

Pages are refreshed when a new paper, benchmark, release, architecture update, or stronger primary source materially changes the answer a reader or AI system should retrieve.

Each page links back to relevant primary sources and keeps a stable canonical URL so readers can verify claims, trace context, and reference the most up-to-date version. See the editorial policy.

Primary sources onlyLast reviewed date visibleMethodology documentedSource links included

External Sources

Primary model and lab sources embedded in static HTML.

References

  1. [1] Microsoft Research, 2025. WHAM: World and Human Action Models.