Zhixiang Wang | 汪智祥

I am building and co-leading Alaya Lab with Kaipeng Zhang. I work on programmable world models driven by structured states, such as G-buffers (AlayaRenderer, AlayaRenderer-Flash) and 3D proxies (PWM, PROWBench).

Previously, I was a Research Scientist at CyberAgent AI Lab. I earned my PhD from the University of Tokyo in 2024 under the guidance of Shin'ichi Satoh. I completed my Master's degree at National Taiwan University in 2020, where I worked with Yung-Yu Chuang. I also interned with Shree Nayar's team at Snap Research and at SONY AI. Earlier, I worked on robotics as an undergraduate with Zexiang Li's and Yangsheng Xu's teams. I work closely with Jia-Bin Huang, Yu-Lun Liu, Ming-Hsuan Yang, Yinqiang Zheng, Jian Wang, and Jinwei Gu.

Email Twitter Scholar LinkedIn

Research

Recent / Earlier

Programmable World Model

Zheng-Hui Huang^* Guixu Lin^* Jiacheng Lin Yi-Chuan Huang Ruihan Yu Muyao Niu Siqi Yang Yu-Lun Liu Yung-Yu Chuang Kaipeng Zhang^† Zhixiang Wang^†

arXiv 2026

project page paper code

PROWBench: Do Video Models Render What the Program Specifies?

Zheng-Hui Huang^* Guixu Lin^* Yu-Ju Tsai Jian-Kai Zhu Fengbo Lan Yu-Lun Liu Yung-Yu Chuang Kaipeng Zhang Zhixiang Wang

arXiv 2026

project page paper code

AlayaWorld: Long-Horizon and Playable Video World Generation

AlayaWorld Team

arXiv 2026

project page paper intro report code model video

Generative World Renderer at the Speed of Play

Guixu Lin Zheng-Hui Huang Siqi Yang Ming-Hsuan Yang Kaipeng Zhang Zhixiang Wang^†

arXiv 2026

project page paper code playable demo

Generative World Renderer

Zheng-Hui Huang Zhixiang Wang^† Jiaming Tan Ruihan Yu Yidan Zhang Bo Zheng Yu-Lun Liu Yung-Yu Chuang Kaipeng Zhang

arXiv 2026

project page paper code demo video

OuroWorld: Bringing Any 3D World Alive as Diverse, Endlessly Looping 3D Cinemagraphs

You-Zhe Xie Ting-Wei Chou Yu-Hsuan Li Kaipeng Zhang Zhixiang Wang^† Yu-Lun Liu^†

arXiv 2026

project page paper code dataset video

EditHero: A Benchmark for Long-Horizon Part-Level 3D Editing and Vibe Modeling

Ruihan Yu^* Yu-Ju Tsai^* Muyao Niu Runyi Li Lian Fu Hanqing Liu Zheng-Hui Huang Yonghao Yu Sho Kuno Ming-Hsuan Yang^† Kaipeng Zhang^† Zhixiang Wang^†

arXiv 2026

project page paper code dataset

KaiNinja: Extending Native 3D Generators to the Part Level

Ruihan Yu Lian Fu Muyao Niu Zheng-Hui Huang Yu-Ju Tsai Sho Kuno Fengbo Lan Yonghao Yu Erwin Wu Ming-Hsuan Yang Kaipeng Zhang Zhixiang Wang

arXiv 2026

project page paper code

WorldSculpt: Generating Compositional Worlds from Grounded Videos

Muyao Niu Jixuan He Ruihan Yu Lian Fu Yonghao Yu Zheng-Hui Huang Yifan Zhan Fengbo Lan Yongtao Ge Yinqiang Zheng Kaipeng Zhang^† Zhixiang Wang^†

arXiv 2026

project page paper code model ComfyUI dataset

YoCausal: How Far is Video Generation from World Model? A Causality Perspective

You-Zhe Xie^* Yu-Hsuan Li^* Jie-Ying Lee Kaipeng Zhang Yu-Lun Liu^† Zhixiang Wang^†

arXiv 2026

project page paper code dataset video

Position: The Systemic Lack of Agency in Visual Reasoning

Yizhao Huang^* Haoyang Chen^* Shiqin Wang^* Pohsun Huang^* Jiayuan Li Haoyuan Du Yandong Shi Zheng Wang^† Zhixiang Wang^†

ICML 2026

project page paper code

Stream-DiffVSR: Low-Latency Streamable Video Super-Resolution via Auto-Regressive Diffusion

Hau-Shiang Shiu Chin-Yang Lin Zhixiang Wang Chi-Wei Hsiao Po-Fan Yu Yu-Chih Chen Yu-Lun Liu

Oral · ECCV 2026

project page code huggingface ComfyUI paper

Reflection Separation from a Single Image via Joint Latent Diffusion

Zheng-Hui Huang Zhixiang Wang^† Yu-Lun Liu Yung-Yu Chuang

CVPR 2026

project page paper code model

Subjective Camera 1.0: Bridging Human Cognition and Visual Reconstruction through Sequence-Aware Sketch-Guided Diffusion

Haoyang Chen Dongfang Sun Caoyuan Ma Shiqin Wang Kewei Zhang Zheng Wang^† Zhixiang Wang^†

ICCV 2025

paper

KaoLRM: Repurposing Pre-trained Large Reconstruction Models for Parametric 3D Face Reconstruction

Qingtian Zhu Xu Cao Zhixiang Wang Yinqiang Zheng Takafumi Taketomi

3DV 2025

paper code

𝙎𝙚𝙠𝙖𝙞: A Video Dataset towards World Exploration

Zhen Li Chuanhao Li Xiaofeng Mao Shaoheng Lin Ming Li Shitian Zhao Zhaopan Xu Xinyue Li Yukang Feng Jianwen Sun Zizhen Li Fanrui Zhang Jiaxin Ai Zhixiang Wang Yuwei Wu Tong He Jiangmiao Pang Yu Qiao Yunde Jia Kaipeng Zhang

NeurIPS 2025

project page paper data code

Foundation Model Insights and a Multi-model Approach for Superior Fine-grained One-shot Subset Selection

Zhijing Wan Zhixiang Wang Zheng Wang Xin Xu Shin'ichi Satoh

Oral · ICML 2025

paper code

DiffIR2VR-Zero: Zero-Shot Video Restoration with Diffusion-based Image Restoration Models

Chang-Han Yeh Chin-Yang Lin Zhixiang Wang Chi-Wei Hsiao Ting-Hsuan Chen Yu-Lun Liu

arXiv 2024

project page paper code demo

Matting by Generation

Zhixiang Wang Baiang Li Jian Wang Yu-Lun Liu Jinwei Gu Yung-Yu Chuang Shin'ichi Satoh

SIGGRAPH 2024

project page paper slides supp

DisCO: Portrait Distortion Correction with Perspective-Aware 3D GANs

Zhixiang Wang Yu-Lun Liu Jia-Bin Huang Shin'ichi Satoh Sizhuo Ma Guru Krishnan Jian Wang

IJCV 2024

project page paper code US patent

Revisiting Adversarial Patches for Designing Camera-Agnostic Attacks against Person Detection

Hui Wei* Zhixiang Wang* Kewei Zhang Jiaqi Hou Yuanwei Liu Hao Tang Zheng Wang

NeurIPS 2024

project page paper code

HumanNeRF-SE: A Simple yet Effective Approach to Animate HumanNeRF with Diverse Poses

Caoyuan Ma Yu-Lun Liu Zhixiang Wang Wu Liu Xinchen Liu Zheng Wang

CVPR 2024

project page arxiv code

Contributing Dimension Structure of Deep Feature for Coreset Selection

Zhijing Wan Zhixiang Wang Yuran Wang Zheng Wang Hongyuan Zhu Shin'ichi Satoh

AAAI 2024

paper code poster csur survey

Rethinking Video Frame Interpolation from Shutter Mode Induced Degradation

Xiang Ji Zhixiang Wang Zhihang Zhong Yinqiang Zheng

ICCV 2023

paper code benchmark data video results

Single Image Deblurring with Row-dependent Blur Magnitude

Xiang Ji Zhixiang Wang Shin'ichi Satoh Yinqiang Zheng

ICCV 2023

paper code benchmark data slides

Beyond Domain Gap: Exploiting Subjectivity in Sketch-Based Person Retrieval

Kejun Lin Zhixiang Wang^† Zheng Wang^† Yinqiang Zheng Shin'ichi Satoh

MM 2023

paper code data

HOTCOLD Block: Fooling Thermal Infrared Detectors with a Novel Wearable Design

Hui Wei* Zhixiang Wang* Xuemei Jia Yinqiang Zheng Hao Tang Shin'ichi Satoh Zheng Wang

Oral · AAAI 2023

paper arxiv code tpami survey

Neural Global Shutter: Learn to Restore Video from a Rolling Shutter Camera with Global Reset Feature

Zhixiang Wang Xiang Ji Jia-Bin Huang Shin'ichi Satoh Xiao Zhou Yinqiang Zheng

CVPR 2022

project page paper code opendatalab poster video (6 min)

Both Style and Fog Matter: Cumulative Domain Adaptation for Semantic Foggy Scene Understanding

Xianzheng Ma Zhixiang Wang Yacheng Zhan Yinqiang Zheng Zheng Wang Dengxin Dai Chia-Wen Lin

Oral · CVPR 2022

paper leaderboard video (5min)

Domain-Specific Mappings for Generative Adversarial Style Transfer

Hsin-Yu Chang Zhixiang Wang Yung-Yu Chuang

ECCV 2020

project page paper code slides more results video (6min)

Learning to Reduce Dual-level Discrepancy for Infrared-Visible Person Re-identification

Zhixiang Wang Zheng Wang Yinqiang Zheng Yung-Yu Chuang Shin'ichi Satoh

CVPR 2019

paper poster ijcai survey

Polarimetric Camera Calibration Using an LCD Monitor

Zhixiang Wang Yinqiang Zheng Yung-Yu Chuang

CVPR 2019

paper code calibration pattern cvpr poster iccp poster

Product

Gear Zero

Chat with your friends, and the game gets made along the way. Describe a game together, and Gear plans it, builds it, and turns each conversation into a playable version in minutes.

try it

Synthetic World

Rewrite any story and watch the world react. AI residents live in alternate timelines: they post, argue, form relationships, remember what happened, and make their own decisions.

try it

Media Coverage

News & Blogs IGN Japan, Sina Finance, National Post, South China Morning Post, Xinhua, Metaphysic AI
Podcasts & Videos IGN Japan interview, Stefan 3D AI, Podcast 1, Podcast 2, Curious Refuge
X (Twitter) @_akhaliq (1, 2, 3, 4, 5), @HuggingPapers (1, 2, 3), @dreamingtulpa (1, 2), @wildmindai (1, 2), @TheTuringPost, @arankomatsuzaki, @Gradio, @RituWithAI, @aisearchio, @yongyuanxi
Community Japan Computer Vision Study Group

Activities

Area Chair NeurIPS'25 (), ICLR'26, CVPR'26, ICML'26, ICLR'27, CVPR'27
Editorial
- Action Editor, Transactions on Machine Learning Research
- IJCV Special Issue on Audio-Visual Generation 2027 (Guest Editor)
- IJCV Special Issue on Responsible Imaging 2026 (Lead Guest Editor)
- IJCV Special Issue on Audio-Visual Generation 2025 (Guest Editor)
Reviewer TPAMI, IJCV, SIGGRAPH / SIGGRAPH Asia, CVPR, ICCV (), ECCV, NeurIPS, ICLR, ICML, AAAI, IJCAI, ICMR ()
Organizer
Exhibition Tokyo Game Show 2026, Makuhari Messe (Alaya Lab)
Invited Presentation
- 2025 Wuhan University - Generative Factorization: Towards See Invisible World
- 2024 ECCV Doctoral Consortium - Neural Cameras (fail to make the presentation due to visa issue)
- 2024 University of Tokyo - How to Present Your Novelty?
- 2024 MIRU - Matting by Generation
- 2024 SONY - Image Factorization and Manipulation with Generative Regularizations
- 2024 International Workshop on Human-Centered Vision and Media Technologies - Neural Cameras
- 2023 National Yang Ming Chiao Tung University - Generative Image Restoration
- 2023 CVPR Tutorial - New Trends with Combination of Hardware Features and Deep Learning
- 2022 MIRU - Neural Global Shutter
Thesis
- PhD Thesis Presentation
- Master Thesis Presentation

Zhixiang Wang | 汪智祥

News

Research

Programmable World Model

PROWBench: Do Video Models Render What the Program Specifies?

AlayaWorld: Long-Horizon and Playable Video World Generation

Generative World Renderer at the Speed of Play

Generative World Renderer

OuroWorld: Bringing Any 3D World Alive as Diverse, Endlessly Looping 3D Cinemagraphs

EditHero: A Benchmark for Long-Horizon Part-Level 3D Editing and Vibe Modeling

KaiNinja: Extending Native 3D Generators to the Part Level

WorldSculpt: Generating Compositional Worlds from Grounded Videos

YoCausal: How Far is Video Generation from World Model? A Causality Perspective

Position: The Systemic Lack of Agency in Visual Reasoning

Stream-DiffVSR: Low-Latency Streamable Video Super-Resolution via Auto-Regressive Diffusion

Reflection Separation from a Single Image via Joint Latent Diffusion

Subjective Camera 1.0: Bridging Human Cognition and Visual Reconstruction through Sequence-Aware Sketch-Guided Diffusion

KaoLRM: Repurposing Pre-trained Large Reconstruction Models for Parametric 3D Face Reconstruction

𝙎𝙚𝙠𝙖𝙞: A Video Dataset towards World Exploration

Foundation Model Insights and a Multi-model Approach for Superior Fine-grained One-shot Subset Selection

DiffIR2VR-Zero: Zero-Shot Video Restoration with Diffusion-based Image Restoration Models

Matting by Generation

DisCO: Portrait Distortion Correction with Perspective-Aware 3D GANs

Revisiting Adversarial Patches for Designing Camera-Agnostic Attacks against Person Detection

HumanNeRF-SE: A Simple yet Effective Approach to Animate HumanNeRF with Diverse Poses

Contributing Dimension Structure of Deep Feature for Coreset Selection

Rethinking Video Frame Interpolation from Shutter Mode Induced Degradation

Single Image Deblurring with Row-dependent Blur Magnitude

Beyond Domain Gap: Exploiting Subjectivity in Sketch-Based Person Retrieval

HOTCOLD Block: Fooling Thermal Infrared Detectors with a Novel Wearable Design

Neural Global Shutter: Learn to Restore Video from a Rolling Shutter Camera with Global Reset Feature

Both Style and Fog Matter: Cumulative Domain Adaptation for Semantic Foggy Scene Understanding

Domain-Specific Mappings for Generative Adversarial Style Transfer

Learning to Reduce Dual-level Discrepancy for Infrared-Visible Person Re-identification

Polarimetric Camera Calibration Using an LCD Monitor

Product

Gear Zero

Synthetic World

Media Coverage

Activities