> Paper: Physically Native World Models: A Hamiltonian Perspective on Generative World Modeling > Authors: Sen Cui, Jingheng Ma > arXiv: 2605.00412 | 2026-04-29
1. AI That Knows Pixels, Not Physics
Imagine an AI predicting the next frame of a video.
Problems with existing world models:
- They only observe pixel changes
- They do not understand the underlying physical laws
- Their predictions can violate physics:
- A ball passing through a wall
- Objects vanishing from existence
- Violations of energy conservation
- A mathematical framework for classical mechanics
- Describes systems via energy (the Hamiltonian)
- Predicts system evolution
- Guarantees energy conservation
- The rates of change of position q and momentum p are determined by the Hamiltonian H
- Elegant, general, and conserving
- It captures the underlying laws of the physical world
- Energy conservation → predictions cannot "create something from nothing"
- Reversibility → understanding causality
- Structure → better generalization
- The world model's internal representation = physical state
- The evolution rule = Hamilton's equations
- Prediction = physics simulation
- The generation process is constrained by energy conservation
- Physically impossible scenarios cannot appear
- Predictions are more reliable
- 2D video, 3D scenes, and implicit representations
- All unified under one physical framework
- No longer separate
- The model's internal states correspond to physical quantities
- Position, velocity, energy
- Interpretable and debuggable
- Traditional world models = learning physics from videos (like an infant)
- Physically native models = born knowing physics (like a physicist)
- The latter starts from a higher point and learns better
- They need countless videos to learn that "balls fall"
- Human infants do not need that much
- Because we are born with physical intuition
- Purely data-driven models may fail on scenarios absent from training data
- Physics priors aid generalization
- Violating common sense
- Dangerous in robotics and autonomous driving
- Physical consistency is required
- Physics priors provide strong inductive biases
- Good performance with less data
- Like human infants
- No physically impossible predictions
- Safer in critical applications
- Verifiable
- The model's "thinking" corresponds to physical quantities
- Understandable by humans
- Easy to debug
- Nature follows concise mathematical laws
- Understanding these laws = understanding nature
- AI understanding physics = AI understanding the world
Three separate research routes: 1. 2D video generation — focused on visual future synthesis 2. 3D scene models — focused on spatial reconstruction 3. JEPA-style implicit models — focused on representation learning
But all three are missing one key element: physics.
2. Hamiltonian Mechanics: The Mathematical Heart of the Physical World
What is Hamiltonian mechanics?
Core equations:
Why is it suited to world models?
3. Physically Native World Models
The paper proposes:
> World models should have physics built in as a prior, rather than learning physics purely from data.
Technical approach:
1. Hamiltonian structure
2. Energy constraints
3. Cross-modal unification
4. Physically interpretable
Analogy:
4. Why Do Physics Priors Matter So Much?
Problems with purely data-driven models:
Low sample efficiency:
Poor generalization:
Unphysical predictions:
Advantages of being physics-native:
Sample efficiency:
Reliable predictions:
Interpretable:
5. A Feynman-Style Judgment: Physics Is the Language of Nature
Feynman said:
> "The laws of physics are the grammar of nature."
Applied to world models:
> "If a world model does not understand physics, it is like learning a language without learning grammar — it can say many words, but nothing truly meaningful. Physics priors let world models speak 'nature's language'."
This reflects a core belief of physics:
6. Takeaways
If you are building world models or prediction systems, ask yourself:
1. "Does my model have physics priors built in?" 2. "Do predictions obey physical conservation laws?" 3. "Can physical structure improve sample efficiency and generalization?" 4. "Is Hamiltonian mechanics applicable to my scenario?"
The core insight of this paper: a world model should not just be a pixel predictor — it should be a physics simulator.
When AI has physics "common sense" built in, it can make reasonable predictions in scenarios it has never seen, just like humans. In the future of embodied intelligence, being physics-native may be the key step from "looking intelligent" to "actually intelligent."
In the art of predicting the world, physics is the oldest and most profound teacher.