Tag
本文提出 VIGOR-his 十年跨度跨视角数据集及 CrossTimeEdit 模型，将历史街景生成重构为编辑任务，基于 FLUX.2[Klein] 4B 通过 SFT 与多奖励 RL（Flow-GRPO + GDPO）训练，在指令对齐、背景保持与物理合理性三项指标上较基线提升 17.12%。
A training-free framework for spatial reasoning from egocentric videos that enables revisiting conclusions through synthesized novel-view videos generated from predicted 3D geometry.
CIPER is a unified transformer framework that jointly performs city-scale retrieval and precise 3-DoF pose estimation from cross-view images, overcoming limitations of cascade pipelines.