DMWM: Dual-Mind World Model with Long-Term Imagination

NeurIPSSpotlight2025

Authors
Lingyi Wang, Rashed Shelim, Walid Saad, Naren Ramakrishnan
Venue
NeurIPS 2025
Track
Spotlight

TL;DR

Imagination in world models is crucial for enabling agents to learn long-horizon policy in a sample-efficient manner…

Opening excerpt from the authors’ abstract. source

Read the paper

Topics

world model efficient agent

Related NeurIPS papers

← All NeurIPS 2025 Spotlight papers · Browse the whole archive