Trimming the Long-Tail of Visual World Modeling Evaluation

• URL: http://arxiv.org/abs/2606.24256v1
• Date: Tue, 23 Jun 2026 07:43:41 GMT
• Title: Trimming the Long-Tail of Visual World Modeling Evaluation
• Abstract summary: We introduce Tailor-Bench, a benchmark that challenges world models to simulate irregular physical interactions.<n>Regular scenarios reflect common tool-task pairs, Unconventional scenarios replace conventional tools with attribute-compatible substitutes, and Impossible scenarios introduce attribute-violating tools.<n>Our experimental results reveal a clear long-tail gap in physical world modeling, indicating limited generalization beyond common interactions.
• Score: 67.17191772079316
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Physical interactions follow a long-tailed distribution: a set of common and regular interactions dominates human experience and visual data, while a broad spectrum of rare and irregular interactions remains underrepresented. Although recent visual world models, including image and video generation models, achieve impressive realism on existing benchmarks, they primarily focus on simulating common physical interactions. This raises a central question: Do current visual world models internalize and generalize physical principles? In this work, we introduce Tailor-Bench, a benchmark that challenges world models to simulate irregular physical interactions. To enable systematic evaluation, we design three scenario modes that progressively challenge model reasoning: Regular scenarios reflect common tool-task pairs, Unconventional scenarios replace conventional tools with attribute-compatible substitutes to test affordance generalization, and Impossible scenarios introduce attribute-violating tools to probe constraint awareness. Additionally, we design two complementary settings under a unified evaluation protocol: predictive generation requires inferring outcomes without guidance, while descriptive generation specifies the target outcome for faithful realization. Our experimental results reveal a clear long-tail gap in physical world modeling: performance degrades from Regular to Unconventional and Impossible scenarios, indicating limited generalization beyond common interactions. Failure analysis further shows that models rely on superficial visual patterns: image models fail to realize correct state changes, while video models further suffer from temporal inconsistencies.

Related papers

• PlayWorld: Benchmarking World Models with Agent Players over Long-Horizon Objectives [86.3073067035531]
  Video world models simulate future states conditioned on current observations and user actions.<n>Recent systems have demonstrated impressive video consistency and action controllability over long sequences.<n>But fairly comparing these interactive models remains challenging.<n>We employ multi-modal Agent Players to interact with world models toward specified long-horizon objectives.
  arXiv  Detail & Related papers  (2026-08-13T17:59:30Z)
• XEWorld: Can Action-Conditioned World Models Generalize to Unseen Robot Embodiments? [19.1327734399886]
  Action-conditioned world models are promising learned simulators for robotic manipulation.<n>But evaluating them exclusively on training robots fails to reveal whether they capture physical dynamics or merely visual patterns.<n>We introduce XEWorld, a controlled cross-embodiment testbed for world models that isolates embodiments by evaluating held-out robots within physically identical scenes.
  arXiv  Detail & Related papers  (2026-08-06T09:35:33Z)
• From World Action Models to Embodied Brains: A Roadmap for Open-World Physical Intelligence [54.62791372989525]
  Action models, vision-language--action policies, and world models have advanced this goal.<n>World Action Models (WAMs) are particularly promising because they connect candidate interventions with predicted consequences.<n>We review the evolution toward WAMs and organize these limitations into three coupled gaps: model roles and representations, objectives and standardization, and system composition.
  arXiv  Detail & Related papers  (2026-07-13T15:22:56Z)
• SurgVista: Long-Horizon Surgical World Modeling with Plausible Instrument-Tissue Dynamics [49.771521708359955]
  SurgVista is a surgical world model that mitigates spatial interaction incoherence and temporal fidelity collapse.<n>It consistently outperforms state-of-the-art methods across visual quality, temporal consistency, and interaction fidelity.
  arXiv  Detail & Related papers  (2026-06-18T07:47:28Z)
• HarmoWAM: Harmonizing Generalizable and Precise Manipulation via Adaptive World Action Models [58.191567345416836]
  World Action Models (WAMs) have emerged as a promising paradigm for robot control by modeling physical dynamics.<n>HarmoWAM fully leverages a world model to unify predictive and reactive control, enabling both general transit and precise manipulation.<n>We construct three training-unseen test environments across six real-world robotic tasks, covering variations in background, position, and object semantics.
  arXiv  Detail & Related papers  (2026-05-11T17:59:56Z)
• AGWM: Affordance-Grounded World Models for Environments with Compositional Prerequisites [18.635313325437664]
  We propose AGWM (Affordance-Grounded World Model), which learns an abstract affordance structure represented as a DAG of prerequisite dependencies to explicitly track the dynamic executability of actions.<n> Experiments on game-based simulated environments demonstrate the effectiveness of our method by achieving lower multi-step prediction error, better generalization to novel configurations, and improved interpretability.
  arXiv  Detail & Related papers  (2026-05-07T18:46:44Z)
• Towards Real-world Human Behavior Simulation: Benchmarking Large Language Models on Long-horizon, Cross-scenario, Heterogeneous Behavior Traces [81.41397370235102]
  We introduce OmniBehavior, the first user simulation benchmark constructed entirely from real-world data.<n>We show that current models struggle to accurately simulate complex behaviors, with performance plateauing even as context windows expand.<n>This results in the loss of individual differences and long-tail behaviors, highlighting critical directions for future high-fidelity simulation research.
  arXiv  Detail & Related papers  (2026-04-09T15:26:21Z)
• 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)
• Evaluating Gemini Robotics Policies in a Veo World Simulator [69.23071832313246]
  We introduce a generative evaluation system built upon a frontier video foundation model (Veo)<n>The system is optimized to support robot action conditioning and multi-view consistency.<n>We validate these capabilities through 1600+ real-world evaluations of eight Gemini Robotics policy checkpoints and five tasks for a bimanual manipulator.
  arXiv  Detail & Related papers  (2025-12-11T14:22:14Z)
• A Reliable Framework for Human-in-the-Loop Anomaly Detection in Time Series [17.08674819906415]
  We introduce HILAD, a novel framework designed to foster a dynamic and bidirectional collaboration between humans and AI.<n>Through our visual interface, HILAD empowers domain experts to detect, interpret, and correct unexpected model behaviors at scale.
  arXiv  Detail & Related papers  (2024-05-06T07:44:07Z)

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.