action-conditioned

Echo-Memory presents a controlled study of memory mechanisms in action-conditioned world models, revealing that memory structure and capacity significantly impact open-domain return performance beyond replay fidelity. The study introduces a matched evaluation protocol and finds that raw context and state-space recurrence are strong mechanisms.

MiraBench is a hierarchical benchmark for evaluating action-conditioned reliability in robotic world models, assessing physics adherence, action-following fidelity, and optimism bias across 12 model configurations.

MultiWorld is a unified framework for multi-agent multi-view video world modeling that achieves accurate control of multiple agents while maintaining multi-view consistency through a Multi-Agent Condition Module and Global State Encoder.