The paper introduces IMPLY, a method that evaluates world-model rollouts by inferring the physics implied by each rollout and scoring them based on how well a single object explains all rollouts, anchored to two calibration pushes the model has observed. Unlike traditional self-consistency checks that only compare futures against each other, IMPLY requires physical consistency with known pushes, revealing when a model incorrectly internalises an object. Experiments show that self-consistency alone can misidentify models, whereas anchored disagreement accurately distinguishes correct from incorrect object tracking and can select rollout sets nearly as well as an oracle with ground‑truth knowledge.
By Aman Mehta, Riya Baviskar
OneWorld introduces a shared‑mechanism counterfactual generation framework that jointly models multiple action‑conditioned futures using a common latent physical mechanism. By inferring distributions over latent mechanisms for each action‑outcome branch and aggregating them into shared‑world evidence, the model enforces consistency across interventions while preserving distinct action outcomes. Experiments in controlled environments demonstrate that OneWorld improves cross‑intervention physical consistency without sacrificing single‑rollout prediction quality.
By Ke He, Yichen Ding, Bin Yang
arXiv:2607. 00276v1 Announce Type: cross Abstract: Current large-language-model (LLM) physics benchmarks are usually scored by answer accuracy, which cannot distinguish genuine reasoning from recall of familiar problem patterns and reveals little about where a model's reasoning breaks down.
By Dong Zhang
The paper introduces an event‑anchored evaluation protocol for video world models, using 62 free‑fall recordings and 124 clips with detailed release and impact annotations. It finds that while some models (Runway, Veo) can generate release and impact events with high accuracy, they often start them late, and others (Cosmos‑Predict‑2.5, MAGI‑1) rarely produce measurable consequences. A human study shows that people’s predictions align with recorded futures but also reveal ambiguity in plausible continuations, highlighting that physical foresight requires initiating, timing, and realizing motion correctly.
By Estela Monserrat Arriaga Santana (National Autonomous University of Mexico), Julian Rosas Scull (National Autonomous University of Mexico), Eh\'ecatl Sacamch'en N\'u\~nez Rico (National Autonomous University of Mexico), Hugo Jair Escalante (University of Texas at El Paso)
arXiv:2608. 05670v1 Announce Type: new Abstract: A model's agreement across perturbed inputs is used both as a label-free reliability signal and as a self-training target, on the premise that agreement tracks correctness.
By Rasul Khanbayov, Hasan Kurban
arXiv:2607. 11598v1 Announce Type: new Abstract: There are two standard ways to spend more compute at test time: let a model reason longer, or sample more attempts and keep one.
By Bojie Li, Noah Shi
There are two standard ways to spend more compute at test time: let a model reason longer, or sample more attempts and keep one. Both share a hidden limit: they are internal.
arXiv:2608. 08982v1 Announce Type: new Abstract: Interactive video world models generate rollouts autoregressively under an action stream, yet they are trained and evaluated almost exclusively on factual prediction.
By Yu Ma, Hongli Shi, Xinran Xu
arXiv:2608. 02150v2 Announce Type: replace-cross Abstract: Embodied intelligence and world models require video understanding systems to go beyond recognizing objects and actions and develop an understanding of physical regularities.
By Zhongjie Ba, Shengwang Xu, Peng Cheng, Jinyang Zou, Ting Yu, Zhibo Wang, Zhan Qin
The paper introduces a world model that learns to predict the evolution of physical systems while respecting key physical principles. By hard‑coding a general structure—generating dynamics from the gradient of a learned energy via a fixed reversible operator and imposing constraints on energy, dissipation, and interventions—the model achieves second‑law compatible dissipation, accurate responses to parameter changes, long‑term stability, and robustness to disturbances. Experiments on an electromagnetic cavity, a particle‑in‑cell grid, and shallow‑water fluid demonstrate that the model can recover accurate constitutive functions, distinguish conserving from dissipating regimes, and transfer learned physics to unseen conditions, outperforming unconstrained models.
By Yufeng Wang, Parivesh Priye, Lu Wei, Haibin Ling
The paper investigates how new concepts can be integrated into unified multimodal models (UMMs) by separating generation and understanding objectives through a novel visual entity bound to a single task direction. Experiments show that the effectiveness of cross‑task usability depends on where the concept is injected into the shared computation, with a mid‑stack alignment objective achieving high concept acquisition with minimal loss to overall performance. The study highlights that unified weights alone are insufficient; the two directions must share a semantic format at the entry point for efficient concept integration.
By Zongyang Qiu, Yihan Wu, Kaixuan Fan, Bo Li, Hui Xiong
arXiv:2608. 19492v1 Announce Type: new Abstract: World models increasingly treat compact multimodal representations as interfaces between perception and physical interaction, yet existing probes do not establish whether different sensors carry the same executable meaning or whether that meaning survives a new action composition.
By Kaizhen Tan, Xin Xu, Siru Tao, Yixiao Li, Hanzhe Hong, Yang Feng, Heqing Du