InfiniteWorld is a new benchmark that pairs physical‑reasoning questions with simulator videos whose physical parameters are systematically altered, allowing researchers to test whether models rely on visual evidence or on familiar physics. The benchmark’s generation pipeline connects simulation, scene screening, paired video translation, question construction, and input checks, and it includes five tasks—law identification, parameter estimation, temporal reasoning, analytic counterfactual comparison, and law induction. Evaluation across five matched input settings (text‑only, ordered, shuffled observations) reveals that video‑language models often default to Earth‑normal physics, showing strong accuracy on normal questions but poor recognition of altered dynamics. "whyItMatters":"The benchmark provides a measurable way to separate visual evidence from familiar physics, exposing persistent biases in current video‑language models toward Earth‑normal rules."
arXiv:2610.08791v1 Announce Type: new Abstract: Video world models can produce visually convincing yet physically inconsistent sequences, raising concerns about their reliability for prediction and p...
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.
Embodied intelligence and world models require video understanding systems to go beyond recognizing objects and actions and develop an understanding of physical regularities. However, despite their strong performance on general video understanding tasks, current video-language models still struggle to reliably determine whether an observed event conforms to specific physical laws.
arXiv:2607. 10190v1 Announce Type: cross Abstract: Video-language models (VLMs) have achieved remarkable performance on video understanding and visual question answering, yet they remain unreliable in reasoning about physical plausibility, where understanding object interactions, causal dynamics, and fundamental physical principles is essential.
arXiv:2605.04515v2 Announce Type: replace Abstract: Video Large Language Models (Video-LLMs) excel in general video understanding but often base physical judgments on event expectations rather than o...
arXiv:2608. 04575v1 Announce Type: cross Abstract: Reliable physical reasoning from video requires understanding how objects move, interact, and respond to interventions.
PhysiCalWorld introduces a method for calibrating action‑conditioned world models to instance‑specific physics by encoding an exploratory interaction clip into a compact physics descriptor token. This token grounds future predictions in the actual physical behavior of a scene without requiring fine‑tuning or explicit physics labels, and can be reused across rollouts with minimal compute overhead. Experiments across four diverse environments demonstrate significant improvements in rollout prediction accuracy and visual planning success, while the learned descriptors form a physically structured latent space that generalizes beyond the training physics ranges.
Video generation models are increasingly capable of producing realistic videos, but they still struggle to generate videos that follow basic physical laws. Compounding this is a lack of reliable granular evaluation methods for localizing and specifying physical law violations in videos.
arXiv:2610. 32177v1 Announce Type: new Abstract: Humans reason about the physical world by flexibly combining different forms of inference as a problem unfolds.
The paper introduces a new benchmark for vision‑language models that tests their ability to decide whether to answer a physics question immediately or to request additional experimental evidence. Each problem presents one measurement image and four possible physical worlds defined by two masses and two values of another property; the model must either stop and answer or choose the cheapest experiment that resolves the question. Across six open models and 144 parameter sets, the models almost always repeat the same action even when the optimal choice changes, and only a single model gets both decisions correct on 5.9% of cases.
arXiv:2609.39135v1 Announce Type: new Abstract: Physical reasoning from video requires inferring latent physical properties and dynamics beyond direct observation. Direct VLM inference remains unreli...
arXiv:2610.19823v1 Announce Type: new Abstract: Text-to-video (T2V) generation models can produce visually realistic videos that nevertheless violate the physical consequences implied by the prompt a...