Search papers, labs, and topics across Lattice.
The authors introduce iWorld-Bench, a new benchmark for evaluating interactive world models, focusing on physical interaction capabilities like distance perception and memory. They curated a dataset of 330k video clips and designed an Action Generation Framework to unify evaluation across diverse interaction modalities. Evaluation of 14 existing world models reveals limitations in visual generation, trajectory following, and memory, providing a roadmap for future research.
Current world models struggle with basic physical interaction tasks like distance perception and trajectory following, highlighting a critical gap in their ability to simulate realistic environments.
Achieving Artificial General Intelligence (AGI) requires agents that learn and interact adaptively, with interactive world models providing scalable environments for perception, reasoning, and action. Yet current research still lacks large-scale datasets and unified benchmarks to evaluate their physical interaction capabilities. To address this, we propose iWorld-Bench, a comprehensive benchmark for training and testing world models on interaction-related abilities such as distance perception and memory. We construct a diverse dataset with 330k video clips and select 2.1k high-quality samples covering varied perspectives, weather, and scenes. As existing world models differ in interaction modalities, we introduce an Action Generation Framework to unify evaluation and design six task types, generating 4.9k test samples. These tasks jointly assess model performance across visual generation, trajectory following, and memory. Evaluating 14 representative world models, we identify key limitations and provide insights for future research. The iWorld-Bench model leaderboard is publicly available at iWorld-Bench.com.
