Pith. sign in

REVIEW 10 cited by

WorldLens: Full-Spectrum Evaluations of Driving World Models in Real World

Not yet reviewed by Pith; the record is open.

This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.

SPECIMEN: schema-true, not a live event

T0 review · schema-true

One-sentence machine reading of the paper's core claim.

pith:XXXXXXXX · record.json · timestamp

arxiv 2512.10958 v2 pith:5PSTYZAH submitted 2025-12-11 cs.CV

WorldLens: Full-Spectrum Evaluations of Driving World Models in Real World

classification cs.CV
keywords worldmodelmodelsrealbenchmarkdatasetdrivingfidelity
verification ladder T0 review T1 audit T2 compute T3 formal T4 reserved
0 comments
read the original abstract

Generative world models are reshaping embodied AI, enabling agents to synthesize realistic 4D driving environments that look convincing but often fail physically or behaviorally. Despite rapid progress, the field still lacks a unified way to assess whether generated worlds preserve geometry, obey physics, or support reliable control. We introduce WorldLens, a full-spectrum benchmark evaluating how well a model builds, understands, and behaves within its generated world. It spans five aspects -- Generation, Reconstruction, Action-Following, Downstream Task, and Human Preference -- jointly covering visual realism, geometric consistency, physical plausibility, and functional reliability. Across these dimensions, no existing world model excels universally: those with strong textures often violate physics, while geometry-stable ones lack behavioral fidelity. To align objective metrics with human judgment, we further construct WorldLens-26K, a large-scale dataset of human-annotated videos with numerical scores and textual rationales, and develop WorldLens-Agent, an evaluation model distilled from these annotations to enable scalable, explainable scoring. Together, the benchmark, dataset, and agent form a unified ecosystem for measuring world fidelity -- standardizing how future models are judged not only by how real they look, but by how real they behave.

discussion (0)

Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.

Forward citations

Cited by 10 Pith papers

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score.

  1. WorldRoamBench: An Open-World Benchmark for Long-Horizon Stability of Interactive World Models

    cs.CV 2026-06 unverdicted novelty 7.0

    WorldRoamBench is a new benchmark for interactive world models that evaluates four stability dimensions with custom metrics and finds no tested model performs reliably across all.

  2. WorldRoamBench: An Open-World Benchmark for Long-Horizon Stability of Interactive World Models

    cs.CV 2026-06 accept novelty 7.0

    A 600+ case open-world benchmark finds no interactive world model is simultaneously action-faithful, visually stable, physically plausible, and memory-consistent over long WASD interaction.

  3. WBench: A Comprehensive Multi-turn Benchmark for Interactive Video World Model Evaluation

    cs.CV 2026-05 unverdicted novelty 7.0

    WBench is a benchmark with 289 test cases and 1,058 turns for evaluating interactive world models using 22 automated metrics validated against human judgments.

  4. World Models as Group Actions

    cs.CV 2026-05 unverdicted novelty 7.0

    Formalizes video world models as group actions on states and uses latent regularization with synthesized supervision to enforce consistency, introducing GAC and GAR metrics that improve structural correctness in SOTA models.

  5. From Articulated Kinematics to Routed Visual Control for Action-Conditioned Surgical Video Generation

    cs.CV 2026-05 unverdicted novelty 7.0

    A kinematic-to-visual lifting paradigm combined with hierarchically routed control generates action-conditioned surgical videos with better faithfulness, fidelity, and efficiency.

  6. WorldRoamBench: An Open-World Benchmark for Long-Horizon Stability of Interactive World Models

    cs.CV 2026-06 unverdicted novelty 6.0

    WorldOdysseyBench introduces four new evaluation dimensions and metrics for interactive world models and shows that none of 10+ tested models reliably pass all of them.

  7. StressDream: Steering Video World Models for Robust Policy Evaluation and Improvement

    cs.CV 2026-05 unverdicted novelty 6.0

    StressDream optimizes initial noise in diffusion video world models using VLM semantic and plausibility objectives to steer generations toward specified high-impact outcomes for improved policy evaluation.

  8. OmniLiDAR: A Unified Diffusion Framework for Multi-Domain 3D LiDAR Generation

    cs.CV 2026-05 conditional novelty 6.0

    A unified text-conditioned diffusion model generates high-fidelity LiDAR scans across eight domains spanning weather, sensor, and platform shifts using cross-domain training and feature modeling.

  9. Human Cognition in Machines: A Unified Perspective of World Models

    cs.RO 2026-04 unverdicted novelty 6.0

    The paper introduces a unified framework for world models that fully incorporates all cognitive functions from Cognitive Architecture Theory, highlights under-researched areas in motivation and meta-cognition, and pro...

  10. IRIS: A Real-World Benchmark for Inverse Recovery and Identification of Physical Dynamic Systems from Monocular Video

    cs.CV 2026-03 accept novelty 6.0

    IRIS releases 220 real 4K videos of eight dynamical systems with ground-truth parameters plus a protocol that measures parameter recovery, equation selection, and multi-body failure modes of unsupervised video-to-phys...