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

Lyra 2.0

Lyra 2.0 is a native interactive world model evaluated by WBench.

robotics model-based-rl simulation embodied-ai

Key Attributes

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

AttributeValue
ModelLyra 2.0
Lab / OrganizationNVIDIA
CategoryGenerative World Model
SubtypeAutoregressive Interactive World Model
World Model TypeAutoregressive Interactive World Model
Primary DomainInteractive Video
ArchitectureFour-step autoregressive camera-conditioned world model
ModalityImage + Camera Poses -> Interactive Video
Training MethodAutoregressive interactive world modeling
Statusemerging
Year2026

About Lyra 2.0

Main editorial body preserved directly in static HTML.

Lyra 2.0 generates an evolving environment conditioned on camera input. It is included as a native interactive system rather than a text-to-video model wrapped in WBench's chained-context protocol.

Lyra 2.0 is an autoregressive interactive world model developed by NVIDIA in 2026 for interactive video.

Editorial Snapshot

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

SignalValue
DefinitionLyra 2.0 is an autoregressive interactive world model developed by NVIDIA in 2026 for interactive video.
Short DescriptionLyra 2.0 is a native camera-conditioned interactive world model evaluated by WBench.
Benchmark Rows1
FAQ Entries1
Related Models2
Related Guides0
Related Research Topics0
Last Updated2026-08-31

Notable Features

Key capabilities associated with this model.

  • Camera control
  • Four-step autoregression
  • NVIDIA research release

Use Cases

Representative applications attached to this model record.

Interactive environment simulationWorld-model evaluationInteractive Video

Strengths and Limitations

Balanced assessment surfaced in static HTML.

Strengths

  • Camera control
  • Four-step autoregression

Limitations

  • Navi-only WBench comparison
  • Not a Cosmos variant

Benchmarks

Published benchmark evidence attached to this model record.

BenchmarkMetricResultSource
WBenchFive-dimension average 76.4 /10076.4Source

References and Citations

Primary references preserved in static HTML for citation extraction.

ReferenceLink
NVIDIA. Lyra 2.0. Primary project source.Open source
Ying et al., 2026. WBench: A Comprehensive Multi-turn Benchmark for Interactive Video World Model Evaluation.Open source

Related Models

Nearby models linked from the current editorial record.

ModelCategoryWorld Model TypeIndex v1.1
SANA-WMGenerative World ModelMinute-Scale Interactive World ModelN/A
NVIDIA CosmosFoundation World ModelVideo world foundation model87/100

Frequently Asked Questions

FAQ answers rendered directly into static HTML for extractable responses.

Why is Lyra 2.0 included?

Lyra 2.0 exposes native camera conditioning and generates an evolving interactive environment; WBench evaluates that interface directly.

Quick Answer

Short extractable summary preserved directly in static HTML.

  • Lyra 2.0 is an autoregressive interactive world model developed by NVIDIA in 2026 for interactive video.
  • Use this page when you need a fast read on how Lyra 2.0 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 camera control.

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: 2026-08-31.

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] NVIDIA. Lyra 2.0. Primary project source.
  2. [2] Ying et al., 2026. WBench: A Comprehensive Multi-turn Benchmark for Interactive Video World Model Evaluation.