# STRIKE: Learning Visual State Transitions for Physical World Modeling

arXiv: https://arxiv.org/abs/2610.09514 · HTML: https://mlsanity.com/paper/2610.09514/

## Key facts

- No citing papers in the map yet (data through 7 Oct 2026).
- Placed in Video-generation world models and simulators, one of 11 directions in World models.
- Builds on 19 of its 48 references that are in the map.
- First posted on arXiv 7 Oct 2026.

## Placed in

- World models / [Video-generation world models and simulators](https://mlsanity.com/wm/video-generation-world-models-and-simulators/)

## Builds on (most cited first, 19 of 19)

- [RoFormer: Enhanced Transformer with Rotary Position Embedding](https://mlsanity.com/paper/2104.09864/) (2021)
- [Wan: Open and Advanced Large-Scale Video Generative Models](https://mlsanity.com/paper/2503.20314/) (2025)
- [Qwen3-VL Technical Report](https://mlsanity.com/paper/2511.21631/) (2025)
- [CogVideoX: Text-to-Video Diffusion Models with An Expert Transformer](https://mlsanity.com/paper/2408.06072/) (2024)
- [Qwen-Image Technical Report](https://mlsanity.com/paper/2508.02324/) (2025)
- [LTX-Video: Realtime Video Latent Diffusion](https://mlsanity.com/paper/2501.00103/) (2024)
- [RoboTwin 2.0: A Scalable Data Generator and Benchmark with Strong Domain Randomization for Robust Bimanual Robotic Manipulation](https://mlsanity.com/paper/2506.18088/) (2025)
- [Visual Foresight: Model-Based Deep Reinforcement Learning for Vision-Based Robotic Control](https://mlsanity.com/paper/1812.00568/) (2018)
- [World Simulation with Video Foundation Models for Physical AI](https://mlsanity.com/paper/2511.00062/) (2025)
- [Open-Sora 2.0: Training a Commercial-Level Video Generation Model in 200k](https://mlsanity.com/paper/2503.09642/) (2025)
- [Cosmos 3: Omnimodal World Models for Physical AI](https://mlsanity.com/paper/2606.02800/) (2026)
- [WorldArena: A Unified Benchmark for Evaluating Perception and Functional Utility of Embodied World Models](https://mlsanity.com/paper/2602.08971/) (2026)
- [KeyWorld: Key Frame Reasoning Enables Effective and Efficient World Models](https://mlsanity.com/paper/2509.21027/) (2025)
- [DreamWorld: Unified World Modeling in Video Generation](https://mlsanity.com/paper/2603.00466/) (2026)
- [Physics-IQ Verified](https://mlsanity.com/paper/2606.18943/) (2026)
- [LaMo: Self-Supervised Latent Motion Priors for Physical Realism in Video Generation](https://mlsanity.com/paper/2605.23878/) (2026)
- [CausalMotion: Structured Physical Reasoning as Keyframe and Trajectory Guidance for Training-Free Video Generation](https://mlsanity.com/paper/2606.14317/) (2026)
- [Motion Forcing: A Decoupled Framework for Robust Video Generation in Motion Dynamics](https://mlsanity.com/paper/2603.10408/) (2026)
- [SKIP: Sparse Keyframe Interpolation Paradigm for Efficient Embodied World Models](https://mlsanity.com/paper/2606.00664/) (2026)

## Abstract (arXiv)

Physical world modeling requires predicting how interactions change a scene, not merely generating coherent motion. We propose STRIKE, a framework that separates visual state transition learning from dense video generation. We construct event-aligned supervision by extracting observed states from training videos and pairing them with transition descriptions and temporal offsets. An image-based transition model learns to predict the next scene configuration from the current image, a local transition specification, and elapsed time. At inference, a pretrained vision-language planner predicts time transition specifications, and recursive application of the learned transition model produces a sequence of future visual states. A separately trained dynamic model then generates the complete rollout conditioned on these states and their temporal locations. Experiments on Physics-IQ Verified, PhyGenBench, Pisa-Experiments, and RoboTwin2.0 show improvements of STRIKE over the corresponding video-backbone baselines in benchmark measures of physical consistency and manipulation-video fidelity. These results support learned visual state transitions as an effective intermediate representation for physical world modeling.