When Generative Models Act as Simulators
cs.LG, cs.AI
Submitted: 2026-10-09
Updated: 2026-10-09
Code: https://github.com/SevanBrodjian/generative-models-as-simulators
License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
Terminology
Sources
- Genie: Generative Interactive Environments
- MetaOthello: A Controlled Study of Multiple World Models in Transformers
- The Invisible Hand of Physics: When Video Diffusion Models Know More Than They Show
- Linear Latent World Models in Simple Transformers: A Case Study on Othello-GPT
- Probing into Camera Control of Video Models
- Interpreting Physics in Video World Models
- Emergent World Models and Latent Variable Estimation in Chess-Playing Language Models
- What Does it Mean for a Neural Network to Learn a "World Model"?
- Low-Rank Dynamics-Effective Latent Carriers for Counterfactual Rollout in Learned World Models
- GenEx: Generating an Explorable World
- Cosmos-Transfer1: Conditional World Generation with Adaptive Multimodal Control
- MotionCtrl: A Unified and Flexible Motion Controller for Video Generation
- Adding Conditional Control to Text-to-Image Diffusion Models
- PhysDreamer: Physics-Based Interaction with 3D Objects via Video Generation
- What Do World Models Learn in RL? Probing Latent Representations in Learned Environment Simulators
- Representation Engineering: A Top-Down Approach to AI Transparency
Related papers
- Polynomial-Augmented Neural Networks (PANNs) with Weak Orthogonality Constraints for Enhanced Function and PDE Approximation
- AIRL-S: Unifying Reinforcement Learning and Search-Based Test-Time Scaling via Adversarial Inverse Reinforcement Learning
- Transformers as Bayesian In-Context Experimenters: Smoothness-Adaptive Efficient ATE Estimation
- Convergence issues in Relational Concept Analysis based on AOC-posets
- Beliefs Beyond Posteriors: The Predictive Cost of ELBO Binding
- Understanding Diffusion Models via Ratio-Based Function Approximation with SignReLU Networks