Episode
PhiZero: A World Model Built Around Physical Language
- Podcast
- Daily Paper Cast
- Published
- Aug 1, 2026
- Duration seconds
- 1177
- Processing state
not_requested- Canonical source
- https://share.transistor.fm/s/9e6fc395
Actions
POST https://stenobird.com/v1/public/podcasts/daily-paper-cast-7079649/episodes/phizero-a-world-model-built-around-physical-language/transcription-requests
Idempotently request low-priority transcript generation for this episode.GET https://stenobird.com/podcast/daily-paper-cast-7079649/phizero-a-world-model-built-around-physical-language.md
Read the agent-friendly Markdown representation of this episode resource.
Summary
🤗 Upvotes: 150 | cs.CV Authors: Shuyao Shang, Yuqi Wang, Ruopeng Gao, Xu Chen, Tieniu Tan, Lue Fan, Zhaoxiang Zhang Title: PhiZero: A World Model Built Around Physical Language Arxiv: http://arxiv.org/abs/2607.28624v1 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.