Yuyang Yin

Yuyang Yin 尹雨阳

I am currently a third year Ph.D student at Beijing Jiaotong University (BJTU), advised by Prof. Yuchao Wei. I work closely with Prof. Atlas (Zhangyang) Wang at the University of Texas at Austin and Prof. Yikai Wang at Beijing Normal University. Currently, I am a research intern in the Tencent Hunyuan3D World Model group, lead by Chunchao Guo, advised by Dr. Tengfei Wang and Dr. Chenjie Cao.

yuyangyin@bjtu.edu.cn Google Scholar

Research Interests

  1. Scene Generation in World Models. Unifying large-scale 3D scene reconstruction and generation to build explorable, persistent worlds with consistent geometry and appearance.
  2. Agentic 3D Worlds. Composing multi-modal foundation models into agentic systems that perceive, plan, generate, and edit 3D worlds for games, video creation, and virtual production.

Education

Ph.D · Beijing Jiaotong University 2023 – present

B.S. · Beijing Jiaotong University 2019 – 2023

Social Work

Reviewer for CVPR, ICML, NeurIPS, ICLR, ECCV, etc.

Main Publications

PanoWorld-X
PanoWorld-X: Generating Explorable Panoramic Worlds via Sphere-Aware Video Diffusion
Yuyang Yin, HaoXiang Guo, Fangfu Liu, Mengyu Wang, Hanwen Liang, Eric Li, Yikai Wang, Xiaojie Jin, Yao Zhao, Yunchao Wei
Panoramic Video Generation ICML 2026 Spotlight
Project Paper
Diffusion4D
Diffusion4D: Fast Spatial-temporal Consistent 4D Generation via Video Diffusion Models
Hanwen Liang*, Yuyang Yin*, Dejia Xu, Hanxue Liang, Zhangyang Wang, Konstantinos N. Plataniotis, Yao Zhao, Yunchao Wei
4D Generation NeurIPS 2024
Project Paper Github …
4DGen
4DGen: Grounded 4D Content Generation with Spatial-temporal Consistency
Yuyang Yin*, Dejia Xu*, Zhangyang Wang, Yao Zhao, Yunchao Wei
4D Generation Arxiv 2023.12
Project Paper Github …
CLE Diffusion
CLE Diffusion: Controllable Light Enhancement Diffusion Model
Yuyang Yin, Dejia Xu, Chuangchuang Tan, Ping Liu, Yao Zhao, Yunchao Wei
Image Enhancement MM 2023
Project Paper Github …

Under Review

3D Agent Scene for Previsualization
Anonymous Authors
3D Scene / Previsualization Under Review
A 3D-world-centric framework for generative previsualization that turns ideas into an editable, persistent scene for film, game, and design workflows, enabling fast yet controllable iteration from concept to production.
World Scene Generation and Reconstruction
Anonymous Authors
3D World / Panorama Under Review
A unified single-panorama-to-3D-world system that turns one panoramic image into an explorable 3D scene with consistent geometry and appearance, supporting immersive content creation and world simulation from very limited visual capture.

Technical Reports

HY-World 2.0

HY-World 2.0: A Multimodal World Model Framework for 3D World Generation, Reconstruction and Interaction

Tencent HY-World Team

World Model Project
Matrix-3D

Matrix-3D: Omnidirectional Explorable 3D World Generation

Skywork AI

Panorama Video Generation / 3D World Project

Other Publications

Martian World Models
Martian World Models: Controllable Video Synthesis with Physically Accurate 3D Reconstructions
Longfei Li, Zhiwen Fan, Wenyan Cong, Xinhang Liu, Yuyang Yin, Matt Foutter, Panwang Pan, Chenyu You, Yue Wang, Zhangyang Wang, Yao Zhao, Marco Pavone, Yunchao Wei
World Model / 3D Reconstruction NeurIPS 2026
Project Paper Github
StereoWorld
StereoWorld: Geometry-Aware Monocular-to-Stereo Video Generation
Ke Xing, Xiaojie Jin, Longfei Li, Yuyang Yin, Hanwen Liang, Guixun Luo, Chen Fang, Jue Wang, Konstantinos N. Plataniotis, Yao Zhao, Yunchao Wei
Stereo Video Generation CVPR 2026
Project Paper Github
ClassDiffusion
ClassDiffusion: More Aligned Personalization Tuning with Explicit Class Guidance
Jiannan Huang, Jun Hao Liew, Hanshu Yan, Yuyang Yin, Yao Zhao, Humphrey Shi, Yunchao Wei
Image Generation ICLR 2025
Project Paper Github
CLIP-GS
CLIP-GS: Unifying Vision-Language Representation with 3D Gaussian Splatting
Siyu Jiao, Haoye Dong, Yuyang Yin, Zequn Jie, Yinlong Qian, Yao Zhao, Humphrey Shi, Yunchao Wei
3D Understanding ICCV 2025
Paper
TiP4GEN
TiP4GEN: Text to Immersive Panorama 4D Scene Generation
Ke Xing, Hanwen Liang, Dejia Xu, Yuyang Yin, Konstantinos N. Plataniotis, Yao Zhao, Yunchao Wei
Panoramic Video Generation MM 2025
Project Paper

Industrial Experience

Tencent Hunyuan3D
2025.12 – present
Topic: World Model. Lead by Chunchao Guo, advised by Dr. Tengfei Wang and Dr. Chenjie Cao.
Skywork 昆仑万维
2025.01 – 2025.07 · Beijing, China (Remote)
Topic: Panoramic Video Generation. Worked with Dr. HaoXiang Guo, as part of Matrix-3D.
Alkaid 瑶光未来
2024.02 – 2024.12 · Beijing, China
A startup focused on AI tools for art and entertainment. Topic: Video/3D Generation. Worked with Dr. Yupeng Chen.
Agency for Science, Technology and Research (A*STAR)
2023.01 – 2023.08 · Singapore
Topic: Image Generation. Worked with Prof. Ping Liu.