arXiv:2601.07823v2 Announce Type: cross Abstract: Video world models have emerged as promising candidates for high-fidelity world models, offering the potential to synthesize high-quality videos capt...
PhysPlan is a training‑free guidance framework that enhances video diffusion models by incorporating physical awareness through agentic physics simulation. It uses a vision‑language model to generate a Chain‑of‑Visual‑Thought representation of kinematic trajectories and 3D depth, which then drives an object‑centric test‑time optimization that isolates kinematic changes and locks the passive environment. The framework also employs Kinetic Intensity Profiling to adapt hyperparameters to varying physical deformations, and demonstrates superior performance on PhyGenBench and Physics‑IQ benchmarks compared to existing VDM baselines.
Modern generative world models render increasingly realistic action-controllable futures, yet they frequently hallucinate: rollouts remain visually fluent while drifting from the ground-truth dynamics. We hypothesize that hallucination concentrates in low-coverage regions of the state-action space, where lightweight data-centric signals can both detect it and guide mitigation.
arXiv:2606. 27326v1 Announce Type: new Abstract: Modern generative world models render increasingly realistic action-controllable futures, yet they frequently hallucinate: rollouts remain visually fluent while drifting from the ground-truth dynamics.
MotionHalluc is a benchmark designed to evaluate motion hallucinations in cross‑video comparison tasks, consisting of 1,540 fine‑grained questions over 553 video pairs. It assesses hallucinations across three dimensions—directional, attributional, and temporal—and reveals that current large multimodal models are highly susceptible to these errors. The authors also introduce a training‑free Perceive‑Parse‑Verify baseline that injects explicit kinematic measurements, achieving an average 10.6% performance improvement across models.
arXiv:2510. 08073v2 Announce Type: replace-cross Abstract: AI-generated videos have achieved near-perfect visual realism (e.
arXiv:2608. 16829v1 Announce Type: cross Abstract: Video world models approximate the stochastic distribution of physical outcomes through generative sampling, but existing benchmarks score individual generations or compare distributions coarsely over a whole dataset, leaving the fine-grained aleatoric uncertainty of specific phenomena untested.
arXiv:2511.18991v2 Announce Type: replace Abstract: Camera-controlled video generation has attracted increasing interest for its applications in simulation, gaming, and world modeling. However, curre...
arXiv:2610.31429v2 Announce Type: replace Abstract: World action models increasingly rely on pretrained diffusion/flow-based video generators assumed to capture physical dynamics for prediction, plan...
arXiv:2601. 22574v2 Announce Type: replace-cross Abstract: Although Video Large Multimodal Models have achieved strong performance in video understanding, they still suffer from hallucination.
Neural Voxel Dynamics introduces a self‑supervised framework that learns 3D latent dynamics from monocular video by unprojecting V‑JEPAs features into a voxel grid using depth priors. It then applies Volumetric Feature Advection, an action‑conditioned transition model, to predict the evolution of these latent features directly in 3D, without relying on privileged physics‑engine states. The method is evaluated on synthetic and real datasets, demonstrating predictive fidelity, 3D geometric consistency, and physical plausibility via Physics‑IQ metrics.
Fluid-Gen-Zero is a training-free framework that generates physics-aware fluid-object interaction videos by separating physical reasoning from appearance synthesis. It uses a physics simulator for motion dynamics and a pretrained video generator for visual quality, coordinated through a two-level agentic workflow involving a vision-language model for planning and latent-space guidance for simulation signals. The method improves simulation alignment and fluid flow accuracy across multiple backbones while maintaining perceptual quality, as shown by quantitative metrics and human preference studies.