Skip to content

Author

Yi-Fan Zhan

We have 6 of 26 papers

We haven’t gathered this author’s papers yet. Follow them and we’ll fetch their work.

Not the right person? Other researchers publish under this name.

Preprint Sep 2026

Many Eyes, One World: Feed-Forward 3D Reconstruction from Mixed Cameras

Real-world capture is heterogeneous: perspective, fisheye, and $360^\circ$ panoramic images can coexist within a single reconstruction task, yet most feed-forward 3D reconstruction models assume perspective imagery and a uniform input representation. Recent models handling several camera types are either informed of th...

Qiao-Ge Li, Yi-Fan Zhan, Hai-Jun Yang et al. · 0 citations
Preprint Sep 2026

WorldSculpt: Generating Compositional Worlds from Grounded Videos

This work shows that complex scenes with hundreds of objects can instead be generated compositionally by adapting a strong single-object 3D generative prior to multi-view observations, and introduces UE-MeshyScene, a photorealistic benchmark of densely cluttered scenes with hundreds of objects, per-object annotations,...

Mu-Yao Niu, Ji-Xuan He, Rui-Han Yu et al. · 0 citations
Preprint Aug 2026

AlayaWorld: Interactive Long-Horizon World Modeling - Full Technical Report (v1.1)

The new version of AlayaWorld substantially revise how conditioning signals are represented and integrated into the model, replacing the previous depth-warping-based spatial memory with a streaming 3D point-cache renderer.

AlayaWorld Team Kaipeng Zhang, Chuan-Hao Li, Yi-Fan Zhan et al. · 5 citations · ⚡2
Jul 2026

AlayaWorld: Long-Horizon and Playable Video World Generation

AlayaWorld enables open-ended real-time interaction, allowing users to freely navigate and perform diverse actions such as combat, spell casting, and monster summoning, and the framework unifies the complete development-from data preparation model architecture, model training, inference acceleration, and deployment-wit...

AlayaWorld Team, Kaipeng Zhang, Chuanhao Li et al. · 1 citation
Jul 2026

AlayaWorld: Interactive Long-Horizon World Modeling - Full Technical Report

AlayaWorld is presented, an interactive long-horizon video world model that generates 24-fps video at 540p and 720p and introduces a discrete autoregressive distillation formulation that combines distribution-matching distillation, self-forcing++, and consistency distillation, reducing inference from approximately 30 s...

AlayaWorld Team Kaipeng Zhang, Chuanhao Li, Y. Zhan et al. · 4 citations
Preprint Aug 2026

Alaya-EVOKE: From Linear-Scaling Supervision to Endless World

Alaya-EVOKE (Evoke) addresses both limitations by externalizing persistent world state and redesigning the teacher for long-horizon interactive generation, and achieves state-of-the-art performance on WBench while remaining competitive on VBench-Long and VBench-2.0.

Yuan-Yang Yin, Gongxuan Wang, Yi-Fan Zhan et al. · 11 citations · ⚡4

We use cookies to run the site and, with your consent, for analytics and to show ads. See our Cookie Policy.