About

Yikai Wang is a postdoctoral researcher at Meta, where he works with Prof. Tao Xiang on advancing vision and generative modeling techniques. Prior to joining Meta, he was a research fellow at MMLab@NTU, Nanyang Technological University, under the guidance of Prof. Chen Change Loy, focusing on structural modeling for image generation. He received his Ph.D. in Statistics and B.Sc. in Mathematics from Fudan University, advised by Prof. Yanwei Fu, where he built a strong foundation in generative computer vision and statistical machine learning.
His research explores the role of structured generative intelligence, developing models that can generate, interact with, and interpret the world in a controllable, actionable, and scientifically grounded manner. The unstructured processing in current models often limits their reliability in complex domains such as physical environments, robotic control, and neural cognition. His work addresses these challenges by incorporating hierarchical, spatial, and semantic structures into AI systems, helping them transition from passive visual generators to more interactive and reliable models.
His long-term goal is to build general-purpose embodied and cognitive generative systems. He aims to develop AI that is not only capable of realistic simulation, but also actionable, interpretable, and grounded in the physical world.

I am always open to academic discussions and collaboration. Please feel free to reach out via yi-kai.wang@outlook.com. Please let me know who you are.
Note: My previous institutional emails from NTU and Fudan are no longer active.

News


Research

Papers

Aligned Stable Inpainting: Mitigating Unwanted Object Insertion and Preserving Color Consistency
[arxiv]
Yikai Wang*, Junqiu Yu*, Chenjie Cao, Xiangyang Xue, Yanwei Fu.
Preprint, 2026.

The Pictorial Cortex: Zero-Shot Cross-Subject fMRI-to-Image Reconstruction via Compositional Latent Modeling.
[arxiv]
Jingyang Huo, Yikai Wang, Yanwei Fu, Jianfeng Feng.
Preprint, 2026.

ActiveVLA: Injecting Active Perception into Vision-Language-Action Models for Precise 3D Robotic Manipulation.
[arxiv] [paper] [code] [data] [intro]
Zhenyang Liu, Yongchong Gu, Yikai Wang, Xiangyang Xue, Yanwei Fu.
CVPR, 2026.

Next Visual Granularity Generation.
[arxiv] [paper] [code] [intro] [简介]
Yikai Wang, Zhouxia Wang, Zhonghua Wu, Qingyi Tao, Kang Liao, Chen Change Loy.
ICLR, 2026.

Thinking with Camera: A Unified Multimodal Model for Camera-Centric Understanding and Generation.
[arxiv] [paper] [code] [intro] [简介]
Kang Liao, Size Wu, Zhonghua Wu, Linyi Jin, Chao Wang, Yikai Wang, Fei Wang, Wei Li, Chen Change Loy.
ICLR, 2026.

Spatial-Temporal Aware Visuomotor Diffusion Policy Learning.
[arxiv] [paper] [code] [intro]
Zhenyang Liu, Yikai Wang, Kuanning Wang, Longfei Liang, Xiangyang Xue, Yanwei Fu.
ICCV, 2025.

Towards Enhanced Image Inpainting: Mitigating Unwanted Object Insertion and Preserving Color Consistency.
[arxiv] [paper] [full-size PDF] [code & MISATO dataset] [intro] [demo: Youtube, Bilibili]
Yikai Wang*, Chenjie Cao*, Junqiu Yu*, Ke Fan, Xiangyang Xue, Yanwei Fu.
CVPR, 2025. (Highlight, 13.5% of accepted papers)

ReasonGrounder: LVLM-Guided Hierarchical Feature Splatting for Open-Vocabulary 3D Visual Grounding and Reasoning.
[arxiv] [paper] [code & dataset] [intro]
Zhenyang Liu, Yikai Wang, Sixiao Zheng, Tongying Pan, Longfei Liang, Yanwei Fu, Xiangyang Xue.
CVPR, 2025.

Adaptive Pruning of Pretrained Transformer via Differential Inclusions.
[arxiv] [paper] [code]
Yizhuo Ding, Ke Fan, Yikai Wang, Xinwei Sun, Yanwei Fu.
ICLR, 2025.

3D StreetUnveiler with Semantic-aware 2DGS - a simple baseline.
[arxiv] [paper] [code] [intro]
Jingwei Xu, Yikai Wang, Yiqun Zhao, Yanwei Fu, Shenghua Gao.
ICLR, 2025.

Repositioning the Subject within Image.
[arxiv] [paper] [full-size PDF] [code & ReS dataset] [intro] [demo: Youtube, Bilibili]
Yikai Wang, Chenjie Cao, Ke Fan, Qiaole Dong, Yifan Li, Xiangyang Xue, Yanwei Fu.
TMLR, 2024. (J2C Certification, 10% of accepted papers)

LEA: Learning Latent Embedding Alignment Model for fMRI Decoding and Encoding.
[arxiv] [paper] [code]
Xuelin Qian*, Yikai Wang*, Xinwei Sun, Yanwei Fu, Xiangyang Xue, Jianfeng Feng.
TMLR, 2024.

Unified Lexical Representation for Interpretable Visual-Language Alignment.
[arxiv] [paper] [code] [intro]
Yifan Li, Yikai Wang, Yanwei Fu, Dongyu Ru, Zheng Zhang, Tong He.
NeurIPS, 2024.

Towards Global Optimal Visual In-Context Learning Prompt Selection.
[arxiv] [paper] [code] [intro]
Chengming Xu*, Chen Liu*, Yikai Wang, Yuan Yao, Yanwei Fu.
NeurIPS, 2024.

NeuroPictor: Refining fMRI-to-Image Reconstruction via Multi-individual Pretraining and Multi-level Modulation.
[arxiv] [paper] [code] [intro]
Jingyang Huo*, Yikai Wang*, Yun Wang*, Xuelin Qian, Chong Li, Yanwei Fu, Jianfeng Feng.
ECCV, 2024.

LeftRefill: Filling Right Canvas based on Left Reference through Generalized Text-to-Image Diffusion Model.
[arxiv] [paper] [code] [intro]
Chenjie Cao, Yunuo Cai, Qiaole Dong, Yikai Wang, Yanwei Fu.
CVPR, 2024.

Test-Time Linear Out-of-Distribution Detection.
[paper] [code]
Ke Fan*, Tong Liu*, Xingyu Qiu, Yikai Wang, Lian Huai, Zeyu Shangguan, Shuang Gou, Fengjian Liu, Yuqian Fu, Yanwei Fu, Xingqun Jiang.
CVPR, 2024.

Coarse-to-Fine Amodal Segmentation with Shape Prior.
[arxiv] [paper] [code] [intro]
Jianxiong Gao, Xuelin Qian, Yikai Wang, Tianjun Xiao, Tong He, Zheng Zhang, Yanwei Fu.
ICCV, 2023.

Knockoffs-SPR: Clean Sample Selection in Learning with Noisy Labels.
[arxiv] [paper] [code] [intro] [简介]
Yikai Wang*, Yanwei Fu*, Xinwei Sun.
TPAMI, 2023.

Scalable Penalized Regression for Noise Detection in Learning with Noisy Labels.
[arxiv] [paper] [code] [intro] [简介]
Yikai Wang, Xinwei Sun, Yanwei Fu.
CVPR, 2022.

How to Trust Unlabeled Data? Instance Credibility Inference for Few-Shot Learning.
[arxiv] [paper] [code] [intro] [简介]
Yikai Wang, Li Zhang, Yuan Yao, Yanwei Fu.
TPAMI, 2021.

Instance Credibility Inference for Few-Shot Learning.
[arxiv] [paper] [code] [intro] [简介]
Yikai Wang, Chengming Xu, Chen Liu, Li Zhang, Yanwei Fu.
CVPR, 2020.

Talks

Filling Right Canvas based on Left Reference through Generalized Text-to-Image Diffusion Model.
[slides] [Bilibili video (in Chinese, starts at 1:18:40)]
Oral presentation at Pre-CVPR@Shanghai, 2024.05.

Advancing Image Inpainting: From Versatility to Consistency.
[slides]
S-Lab at Nanyang Technological University, 2024.04.

Clean Sample Selection Algorithms with Statistical Sparsity Analysis.
[slides]
EML Munich Group at Technical University of Munich, 2024.03;
MLCV Group at Institute of Science and Technology Austria, 2024.04.

Few-shot Learning by Statistical Methods.
[slides]
CVPR 2023 tutorial, 2023.06:
Few-shot Learning from Meta-Learning, Statistical Understanding to Applications.

Sparse Learning for Noisy Data Detection.
[Youtube][Bilibili][slides]
CVPR 2022 tutorial, 2022.06:
Sparse Learning in Neural Networks and Robust Statistical Analysis.

Grants and Awards

Timeline

Service

Teaching

You are the Counters-th visitor :)
Hosted on GitHub Pages. Theme modified from minimal and Jonbarron.