World models and simulation
27 notes, newest first. Includes the vault tags world models, simulation.
AD-WM: Action-Discriminative World Models for Counterfactual Model Predictive Control
AD-WM is a joint-embedding world model designed for counterfactual model predictive control. It combines residual latent dynamics with action-recovery regularization so the model preserves action-dependent differences…
Alaya-EVOKE: From Linear-Scaling Supervision to Endless World
The paper presents an interactive video world model that keeps track of a scene's state outside the model itself (an externally stored, camera-indexed memory) so it does not need to hold everything in context, aiming…
DreamX-Phi 1.0: Action-Conditioned Video World Model for Robotic Manipulation
The paper describes a model that, given a starting camera frame, a language instruction, and a planned sequence of robot actions, predicts what the robot's camera would see next, intended to help with robotic…
Better Slots, Better Worlds: Representation Quality & Robustness in Object-Centric World Models
The study investigates the performance of object-centric world models for visual model-predictive control, which enable agents to accomplish tasks through planning. The researchers find that these models perform better…
Better Slots, Better Worlds: Representation Quality & Robustness in Object-Centric World Models
The research focuses on object-centric world models (OCWMs) for artificial intelligence agents. The study compares OCWMs with traditional scene-centric models in terms of representation quality, planning success, and…
IO Factory: Simulating AI-Enabled Influence Campaigns at Scale
The paper introduces IO Factory, an AI framework designed to simulate information and influence campaigns at scale. The framework is designed to handle not just individual language models but also AI swarms, which are…
IO Factory: Simulating AI-Enabled Influence Campaigns at Scale
The authors introduce IO Factory, an AI-driven framework for simulating complex information and influence campaigns at scale. These campaigns involve AI swarms that adapt to platform feedback and disguise organized…
Surgical WAM: A World-Action Model for Data-Efficient Surgical Robot Learning
The study introduces Surgical WAM, a model that uses unlabeled surgical videos for pre-training and then fine-tunes on a fixed number of labeled demonstrations. The goal is to improve the success rate in closed-loop…
BioVLN: A Simulation Platform for Visual Language Navigation in Biomedical Laboratories
Researchers have developed a simulation platform named BioVLN for navigating robotics in biomedical laboratories. The platform focuses on finding the correct position to approach instruments, ensuring safety by…
Concept-Guided Spatial Regularization for World Models in Atari Pong
Researchers evaluate five world model agents in Atari Pong and find inconsistencies and failures in the generated video trajectories. They hypothesize that insufficient modeling of task-critical concepts may contribute…
Concept-Guided Spatial Regularization for World Models in Atari Pong
Researchers evaluate five world model agents in Atari Pong and find failures in the generated video trajectories, such as ball disappearance and incorrect motion. They propose a new method called Concept-Guided Spatial…
Concept-Guided Spatial Regularization for World Models in Atari Pong
Researchers evaluate five different visual world-model agents in Atari Pong and find that their rollouts contain errors such as ball disappearance and incorrect motion. They propose Concept-Guided Spatial…
Digital Pantheon: Simulating and Auditing Coalition Formation with LLM Agents
Researchers present a multi-agent framework using Large Language Models (LLMs) to simulate and audit political coalition formation in elections. The framework combines Supervised Fine-Tuning (SFT), Direct Preference…
Social Simulations: from Agent-Based Modeling to Digital Twins
The text discusses the evolution of social simulation from traditional agent-based modeling to more advanced AI-enhanced simulations and Social Digital Twins, focusing on their methodological foundations, applications…
TerraZero: Procedural Driving Simulation for Zero-Demonstration Self-Play at Scale
TerraZero is a procedural driving simulation developed by researchers to train autonomous driving agents efficiently at scale without the need for real-world data demonstrations. It offers improved speed, realistic…
Formal Mechanisms for Market Stability in Self-Interested Agent Societies: A Marketplace Simulation Study
The study investigates mechanisms to maintain market stability in societies of self-interested agents who tend to defect in repeated social dilemmas. The research uses a multi-agent marketplace simulation with 18 LLM…
Formal Mechanisms for Market Stability in Self-Interested Agent Societies: A Marketplace Simulation Study
The research presented investigates mechanisms that allow societies of self-interested agents to maintain market stability, focusing on a multi-agent marketplace simulation with 18 AI agents. The study identifies…
CARLA-GS: Decoupling Representation, Reasoning, and Physics Simulation for Autonomous Driving Corner-Case Synthesis
Researchers have proposed a new method called CARLA-GS for generating corner cases in autonomous driving simulations that are essential for safety evaluation. The method decouples the visual representation, semantic…
A Definition and Roadmap for World Models
The provided text discusses the concept of 'world models', which are internal simulators used in AI to understand the structure and dynamics of an environment. The authors propose a definition for world models, outline…
Bridging Physical Reasoning and Task Generalization via Visual Action Outcome Reasoning Alignment
Researchers propose a new reward system called VAORA to improve the performance of vision-language models in interactive physical reasoning tasks. The proposed system aims to address two main issues: hallucinated…
GaP: A Graph-as-Policy Multi-Agent Self-Learning Harness For Variational Automation Tasks
The research presents a new coding system called Graph-as-Policy (GaP) for robots to work reliably in commercial and industrial applications. GaP combines interpretable robot programming with the adaptability of…
SenseWalk: Agent-Based Semantic Trajectory Simulation Powered by Large Language Models in Zoned Environments
The paper proposes SenseWalk, an interactive system that uses large language models (LLMs) to simulate semantic trajectories for human movement analysis. The simulation workflow combines LLMs and the social force model…
Self-Evolving World Models for LLM Agent Planning
In this paper, the authors introduce WorldEvolver, a framework for self-evolving world models designed to improve the planning abilities of long-horizon language model agents by offering predictions of action…
Self-Evolving World Models for LLM Agent Planning
The paper introduces a new framework called WorldEvolver for long-horizon agents. This framework improves the accuracy of predictions about action consequences before execution, which is crucial for agents to make…
Adaptive Utility driven Resource Orchestration for Resilient AI (AURORA-AI)
A new framework called AURORA-AI was proposed to manage resources for AI systems that operate under changing conditions. The framework optimizes a global utility that includes factors like predictive performance…
Learning to Fold: prizewinning solution at LeHome Challenge 2026 (1st place online, 2nd offline)
The text describes a prize-winning system for bimanual garment folding from the LeHome Challenge 2026. The system used a reinforcement learning loop to improve a vision-language-action (VLA) policy, placing first in…
World Models in Pieces: Structural Certification for General Agents
The paper proposes a method to evaluate the understanding of an AI agent in a complex world model, focusing on situations where the agent's abilities are specialized. The authors argue that standard guarantees fail to…
