マスクから世界へ：世界モデル構築のための実践ガイド
From Masks to Worlds: A Hitchhiker's Guide to World Models
初期のマスクモデルから統一アーキテクチャ、対話型生成モデル、記憶拡張システムへと至る世界モデル構築の道筋を、生成・対話・記憶の3要素に焦点を当てて解説する。
著者: Jinbin Bai, Yu Lei, Hecong Wu, Yuchen Zhu, Shufan Li, Yi Xin, Xiangtai Li, Molei Tao, Aditya Grover, Ming-Hsuan Yang
分類: cs.LG
原文アブストラクト
This is not a typical survey of world models; it is a guide for those who want to build worlds. We do not aim to catalog every paper that has ever mentioned a ``world model". Instead, we follow one clear road: from early masked models that unified representation learning across modalities, to unified architectures that share a single paradigm, then to interactive generative models that close the action-perception loop, and finally to memory-augmented systems that sustain consistent worlds over time. We bypass loosely related branches to focus on the core: the generative heart, the interactive loop, and the memory system. We show that this is the most promising path towards true world models.