LF
Liaoyuan Fan
cs.CVcs.AIcs.ROcs.CLcs.HCcs.LGcs.SD
On Valency
published · living versionsW_yspzx7a9·v1 · currentpublished
Video Generation Meets Agent Harness: Agentic Video Generation, Agentic World Modeling and Recursive Self-Improvement
with Yuhao Zheng, Dongxing Mao, Hangyu Ran, Siyuan Hu +16
1 version
Preprints & journals
8 papers in the corpus · 2026GeoPano: Towards Geometrically Accurate 3D Reconstruction from a Single Panorama2610.21297v1 · Jing OU, Zidong Cao, Liaoyuan Fan et al.2026 · 0 citationsarXiv
AlayaWorld: Interactive Long-Horizon World Modeling - Full Technical Report (v1.1)2608.13492v1 · AlayaWorld Team: Kaipeng Zhang, Chuanhao Li, Yifan Zhan et al.2026 · 0 citationsarXiv
Agogic: Performance-Timed Music Tokens for LLM-Native Text-to-Symbolic-Music Generation2608.03999v1 · Junhao Chen, Mingjin Chen, Jingjia Mao et al.2026 · 0 citationsarXiv
Video Models as Native 4D Renderers: World-Grounded Conditioning from Animated Mesh2608.00094v2 · Junhao Chen, Mingjin Chen, Henghaofan Zhang et al.2026 · 0 citationsarXiv
AlayaWorld: Interactive Long-Horizon World Modeling -- Full Technical Report2607.18367v1 · AlayaWorld Team: Kaipeng Zhang, Chuanhao Li, Yifan Zhan et al.2026 · 0 citationsarXiv
AlayaWorld: Long-Horizon and Playable Video World Generation2607.06291v1 · AlayaWorld Team, Kaipeng Zhang, Chuanhao Li et al.2026 · 0 citationsarXiv
ConsistNav: Closing the Action Consistency Gap in Zero-Shot Object Navigation with Semantic Executive Control2605.09869v2 · Haosen Wang, Zhenyang Li, Yinqiang Zhang et al.2026 · 0 citationsarXiv
AIM: Intent-Aware Unified world action Modeling with Spatial Value Maps2604.11135v1 · Liaoyuan Fan, Zetian Xu, Chen Cao et al.2026 · 0 citationsarXiv
Career total: 10 works. 8 are in this corpus.
Profile built from the corpus for this byline.
Author records are still filling in while the Hub is in alpha. If this is your page, you'll be able to claim it soon. Spot a mistake? Tell us.