EDELINE: Enhancing Memory in Diffusion-based World Models via Linear-Time Sequence Modeling

NeurIPSSpotlight2025

Authors
Jia-Hua Lee, Bor-Jiun Lin, Wei-Fang Sun, Chun-Yi Lee
Venue
NeurIPS 2025
Track
Spotlight

TL;DR

World models represent a promising approach for training reinforcement learning agents with significantly improved sample efficiency…

Opening excerpt from the authors’ abstract. source

Read the paper

Topics

reinforcement learning world model diffusion memory agent

Related NeurIPS papers

← All NeurIPS 2025 Spotlight papers · Browse the whole archive