Current World Models Lack a Persistent State Core

• URL: http://arxiv.org/abs/2606.20545v1
• Date: Thu, 18 Jun 2026 17:55:15 GMT
• Title: Current World Models Lack a Persistent State Core
• Abstract summary: World models are increasingly regarded as a decisive step toward artificial general intelligence.<n>They require an internal world state that keeps evolving over time, decoupled from observation.<n>We introduce textbfWRBench, the first systematic diagnostic benchmark that treats camera motion as an intervention on observability.
• Score: 18.34296893231955
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: World models are increasingly regarded as a decisive step toward artificial general intelligence, yet modeling the physical world demands more than rendering convincing frames on demand: it requires an internal world state that keeps evolving over time, decoupled from observation, so that objects endure and events run to their conclusions whether or not a camera is watching, much as the moon holds to its orbit when no one is looking. This requirement is a blind spot of existing benchmarks, which reward surface properties such as fidelity, motion, and camera controllability while never asking whether a generated world keeps evolving once it is unobserved. We introduce \textbf{WRBench}, the first systematic diagnostic benchmark that treats camera motion as an intervention on observability and resolves evaluation into a human-calibrated chain that asks whether the camera executes the requested interaction, whether the scene stays continuous and identifiable while in view, and whether a returning target remains consistent with the event that was set in motion. Across 9{,}600 videos from 23 models spanning four control paradigms, one finding proves stubborn: current systems maintain the observed world as a tracking shot, resuming a returning target in the state at which it was abandoned rather than advancing the event while it went unseen. Because this failure recurs across control paradigms, model families, and increments of scale, robust world-state evolution does not follow from cleaner imagery, tighter control, richer geometric priors, or sheer parameter count We therefore argue that the stability of the physical state kernel and the consistency of worldlines under viewpoint intervention should become first-class objectives of world-model design, so that a world model captures how the world will unfold rather than how the next frame appears.

Related papers

• WorldExam: Benchmarking World Models from Apparent Appearance to Inherent Reactivity [75.96851880065331]
  We introduce WorldExam, a diagnostic benchmark spanning four levels: Visual Quality, Control Adherence, Spatial Consistency, and World Reactivity.<n>It comprises 1,474 cases across eight dedicated tasks and supports unified evaluation of camera-, action-, and language-driven model paradigms.<n> Evaluation of 20 representative models reveals a clear capability split. Camera-driven models excel at camera control, but their interfaces do not support dynamic interaction.
  arXiv  Detail & Related papers  (2026-08-03T17:59:54Z)
• Sensorimotor World Models: Perception for Action via Inverse Dynamics [59.121736411156384]
  We introduce a sensorimotor world model trained end-to-end with inverse dynamics regularization.<n>It prevents representation collapse and induces action-aligned representations.<n>It learns compact, interpretable latent spaces and enables competitive planning performance across simple 2D and 3D control tasks.
  arXiv  Detail & Related papers  (2026-06-18T11:25:16Z)
• DisCo: World Models with Discrete Camera Motion Control [79.86256515640231]
  We propose DisCo, a controllable video world model that conditions generation on a compact set of discrete action primitives to improve action separability.<n>DisCo achieves significantly more reliable action following while preserving visual quality.
  arXiv  Detail & Related papers  (2026-06-06T03:50:45Z)
• AnchorWorld: Embodied Egocentric World Simulation with View-based Evolution Customization [79.26935895370191]
  AnchorWorld is a framework that advances egocentric simulation through enhanced interaction integrity.<n> auxiliary training supervision incorporates viewpoints decoupled from the agent's first-person sensorium.<n>We propose a simple yet effective mechanism for customizing self-evolving worlds.
  arXiv  Detail & Related papers  (2026-06-05T14:43:13Z)
• MetaWorld: Scaling Multi-Agent Video World Model from Single-view Video Data [125.43597497646444]
  MetaWorld is a novel framework that scales multi-agent video world models to open-domain environments directly from single-view videos.<n>It achieves superior cross-view consistency and identity fidelity, establishing a highly scalable, physics-driven paradigm for multi-agent video world modeling.
  arXiv  Detail & Related papers  (2026-06-01T18:20:20Z)
• Physically Native World Models: A Hamiltonian Perspective on Generative World Modeling [5.424198387331309]
  We argue that the bottleneck of world models is no longer only whether they can generate realistic futures, but whether those futures are physically meaningful and useful for action.<n>We propose emphHamiltonian World Models as a physically grounded perspective on world modeling.<n>We discuss how Hamiltonian structure may improve interpretability, data efficiency, and long-horizon stability, while also noting practical challenges in real-world robotic scenes involving friction, contact, non-conservative forces, and deformable objects.
  arXiv  Detail & Related papers  (2026-05-01T05:09:32Z)
• Omni-WorldBench: Towards a Comprehensive Interaction-Centric Evaluation for World Models [39.648000265543445]
  Video-based world models have emerged along two dominant paradigms: video generation and 3D reconstruction.<n>We argue that the future of world modeling lies in 4D generation, which jointly models spatial structure and temporal evolution.<n>We propose Omni--WorldBench, a benchmark specifically designed to evaluate the interactive response capabilities of world models in 4D settings.
  arXiv  Detail & Related papers  (2026-03-23T17:10:29Z)
• LiveWorld: Simulating Out-of-Sight Dynamics in Generative Video World Models [32.92934803081681]
  Recent generative video world models aim to simulate visual environment evolution, allowing an observer to interactively explore the scene via camera control.<n>They implicitly assume that the world only evolves within the observer's field of view.<n>Once an object leaves the observer's view, its state is "frozen" in memory, and revisiting the same region later often fails to reflect events that should have occurred in the meantime.<n>We propose LiveWorld, a novel framework that extends video world models to support persistent world evolution.
  arXiv  Detail & Related papers  (2026-03-07T10:31:39Z)
• Research on World Models Is Not Merely Injecting World Knowledge into Specific Tasks [43.59401259468559]
  We argue that a robust world model should not be a loose collection of capabilities but a normative framework that integrally incorporates interaction, perception, symbolic reasoning, and spatial representation.<n>This work aims to guide future research toward more general, robust, and principled models of the world.
  arXiv  Detail & Related papers  (2026-02-02T04:42:44Z)
• From Generative Engines to Actionable Simulators: The Imperative of Physical Grounding in World Models [4.52033729546524]
  A world model is an AI system that simulates how an environment evolves under actions.<n>Current world models suffer from visual conflation: the mistaken assumption that high-fidelity video generation implies an understanding of physical and causal dynamics.<n>We show that while modern models excel at predicting pixels, they frequently violate invariant constraints, fail under intervention, and break down in safety-critical decision-making.
  arXiv  Detail & Related papers  (2026-01-21T23:35:33Z)
• WorldLens: Full-Spectrum Evaluations of Driving World Models in Real World [100.68103378427567]
  Generative world models are reshaping embodied AI, enabling agents to synthesize realistic 4D driving environments that look convincing but often fail physically or behaviorally.<n>We introduce WorldLens, a full-spectrum benchmark evaluating how well a model builds, understands, and behaves within its generated world.<n>We further construct WorldLens-26K, a large-scale dataset of human-annotated videos with numerical scores and textual rationales, and develop WorldLens-Agent.
  arXiv  Detail & Related papers  (2025-12-11T18:59:58Z)
• GLAMR: Global Occlusion-Aware Human Mesh Recovery with Dynamic Cameras [99.07219478953982]
  We present an approach for 3D global human mesh recovery from monocular videos recorded with dynamic cameras. We first propose a deep generative motion infiller, which autoregressively infills the body motions of occluded humans based on visible motions. In contrast to prior work, our approach reconstructs human meshes in consistent global coordinates even with dynamic cameras.
  arXiv  Detail & Related papers  (2021-12-02T18:59:54Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.