PhiZero: A World Model Built Around Physical Language

• URL: http://arxiv.org/abs/2607.28624v1
• Date: Thu, 30 Jul 2026 17:59:46 GMT
• Title: PhiZero: A World Model Built Around Physical Language
• Abstract summary: PhiZero is a physical world model built around physical language.<n>It infers future world evolution as a physical-language sequence and then renders the inferred transitions into videos.<n>We show its potential for realistic and interactive world modeling, fine-grained action-conditioned simulation, and zero-shot motion transfer.
• Score: 50.268271884186845
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: We introduce PhiZero, a physical world model built around physical language, a compact discrete representation of world-state transitions. Existing physical world models typically predict future videos directly in pixel space, leaving the underlying world dynamics implicit within high-dimensional visual predictors. Motivated by humans' ability to abstract predictive structure from visual experience and organize it in natural language for explicit reasoning, we learn physical language from in-the-wild videos through self-supervision and use it to explicitly reason about how the physical world evolves. Accordingly, PhiZero adopts a reason-then-render paradigm: it first infers future world evolution as a physical-language sequence and then renders the inferred transitions into videos. Extensive experiments across generation and understanding benchmarks validate the ability of PhiZero to model physically coherent world evolution. We further show its potential for realistic and interactive world modeling, fine-grained action-conditioned simulation, and zero-shot motion transfer.

Related papers

• Code as Worlds: Agentic Discovery of Executable World Representations for Physical Reasoning [79.29811222102721]
  We introduce Code-as-World, a paradigm that represents physical worlds through executable world representations.<n>By expressing physical composition, dynamic evolution, and visual appearance as executable code, Code-as-World provides a compact, quantitatively grounded, and controllable abstraction of the physical world.<n>We use verified executable worlds to provide scalable physical supervision for training vision-language models on quantitative physical reasoning.
  arXiv  Detail & Related papers  (2026-08-27T17:57:25Z)
• Code World Model: Coding Agent as World Brain [51.31807545747191]
  We introduce Code World Model, a framework that separates world evolution from visual realization.<n>A coding agent serves as the world brain, reasoning about events and their consequences.<n>To connect executable state with visual generation, we introduce a proxy representation that encodes frame-wisetemporal constraints into a proxy video.
  arXiv  Detail & Related papers  (2026-08-26T15:37:33Z)
• WorldString: Actionable World Representation [29.267308971639682]
  We propose WorldString, a neural architecture capable of modeling the state manifold of real-world objects by learning directly from point clouds or RGB-D video streams.<n>WorldString acts as a foundational building block for physical world models; thus, we name it WorldString. Sweetly, its fully differentiable structure seamlessly enables future integration with policy learning and neural dynamics.
  arXiv  Detail & Related papers  (2026-05-18T17:58:51Z)
• PAN: A World Model for General, Interactable, and Long-Horizon World Simulation [49.805071498152536]
  We introduce PAN, a general, interactable, and long-horizon world model.<n>It predicts future world states through high-quality video simulation conditioned on history and natural language actions.<n>Experiments show that PAN achieves strong performance in action-conditioned world simulation, long-horizon forecasting, and simulative reasoning.
  arXiv  Detail & Related papers  (2025-11-12T07:20:35Z)
• WoW: Towards a World omniscient World model Through Embodied Interaction [83.43543124512719]
  Authentic physical intuition of the world model must be grounded in extensive, causally rich interactions with the real world.<n>We present WoW, a generative world model trained on 2 million robot interaction trajectories.<n>We establish WoWBench, a new benchmark focused on physical consistency and causal reasoning in video.
  arXiv  Detail & Related papers  (2025-09-26T17:59:07Z)
• Morpheus: Benchmarking Physical Reasoning of Video Generative Models with Real Physical Experiments [55.56181322973467]
  We introduce Morpheus, a benchmark for evaluating video generation models on physical reasoning.<n>It features 80 real-world videos capturing physical phenomena, guided by conservation laws.<n>Our findings reveal that even with advanced prompting and video conditioning, current models struggle to encode physical principles.
  arXiv  Detail & Related papers  (2025-04-03T15:21:17Z)

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.