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

LWM

LWM (Large World Model) is UC Berkeley's foundation model that processes over 1 million tokens of interleaved video and text, enabling long-horizon world understanding.

robotics model-based-rl simulation embodied-ai

Key Attributes

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

AttributeValue
ModelLarge World Model (LWM)
Lab / OrganizationUC Berkeley
CategoryFoundation World Model
SubtypeLong-Context Multimodal Model
World Model TypeMillion-length video-language world model
Primary DomainVideo Understanding
ArchitectureLLaMA-based transformer with RingAttention for million-token context
ModalityVisual (Video) + Language
Training MethodProgressive context extension on interleaved video-text data
Statusactive
Year2024
Performance Index55/100 (medium confidence, v1.1)

About Large World Model (LWM)

Main editorial body preserved directly in static HTML.

The Large World Model (LWM) extends the context length of multimodal transformers to over one million tokens, enabling processing of long videos interleaved with text. Built on the LLaMA architecture with RingAttention for efficient long-context training, LWM demonstrates that scaling sequence length (not just model size) unlocks emergent world understanding capabilities including long-horizon video comprehension, temporal reasoning, and cross-modal physical dynamics prediction.

Large World Model (LWM) is a million-length video-language world model developed by UC Berkeley in 2024 for video understanding.

Editorial Snapshot

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

SignalValue
DefinitionLarge World Model (LWM) is a million-length video-language world model developed by UC Berkeley in 2024 for video understanding.
Short DescriptionA foundation model trained on 1M+ interleaved video and language tokens for long-horizon world understanding.
Benchmark Rows1
FAQ Entries2
Related Models4
Related Guides0
Related Research Topics0
Last Updated2026-04-07

Notable Features

Key capabilities associated with this model.

  • 1M+ token context length
  • RingAttention for memory-efficient training
  • Interleaved video-text understanding
  • Emergent temporal reasoning

Use Cases

Representative applications attached to this model record.

Long video understandingTemporal event reasoningCross-modal question answeringVideo summarization

Strengths and Limitations

Balanced assessment surfaced in static HTML.

Strengths

  • Unprecedented context length for video
  • Unified video-language architecture
  • Emergent world understanding
  • Open-source weights

Limitations

  • High compute requirements
  • Limited action/planning capabilities
  • Primarily passive understanding, not generation

Benchmarks

Published benchmark evidence attached to this model record.

BenchmarkMetricResultSource
Long Video QAAccuracyState-of-the-artSource

References and Citations

Primary references preserved in static HTML for citation extraction.

ReferenceLink
Liu et al., 2024. World Model on Million-Length Video And Language With RingAttention. arXiv:2402.08855Open source

Related Models

Nearby models linked from the current editorial record.

ModelCategoryWorld Model TypeIndex v1.1
V-JEPASelf-Supervised World ModelSelf-supervised visual world model70/100
SoraGenerative World ModelText-to-video world simulator63/100
NVIDIA CosmosFoundation World ModelVideo world foundation model87/100
AMI World ModelFoundation World ModelMultimodal generative world model38/100

Direct Comparisons

Side-by-side comparisons already connected to this model.

ComparisonMatchupSummary
LWM vs V-JEPALarge World Model (LWM) vs V-JEPATwo approaches to learning world understanding from video. LWM uses autoregressive prediction over million-length sequences, while V-JEPA predicts abstract latent representations without pixel reconstruction.

Frequently Asked Questions

FAQ answers rendered directly into static HTML for extractable responses.

Why is context length important for world models?

Longer context allows models to track persistent objects, understand cause-and-effect over time, and reason about physical dynamics across extended video sequences, essential capabilities for world understanding.

How does LWM achieve 1M+ tokens?

LWM uses RingAttention, a technique that distributes attention computation across multiple devices, enabling linear scaling of context length with available hardware.

Quick Answer

Short extractable summary preserved directly in static HTML.

  • Large World Model (LWM) is a million-length video-language world model developed by UC Berkeley in 2024 for video understanding.
  • Use this page when you need a fast read on how Large World Model (LWM) fits into the foundation world model landscape, then validate the details in the benchmarks, citations, and related pages.
  • A key strength surfaced in the editorial record is unprecedented context length for video.

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: 2026-04-07.

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] Liu et al., 2024. World Model on Million-Length Video And Language With RingAttention. arXiv:2402.08855