About

Yikai Wang is a research fellow at the MMLab@NTU, working with Prof. Chen Change Loy, affiliated with S-Lab, Nanyang Technological University, Singapore. He obtained B.S. in Mathematics and Ph.D. in Statistics at Fudan University, advised by Prof. Yanwei Fu. His research interest spans statistical machine learning, computer vision, and foundation models, with a focus on content creation, multi-modality and subset selection.

Links: [Google Scholar] [ORCID] [DBLP] [Github] [Huggingface] [Openreview] [Twitter] [Zhihu]

Always available with yi-kai.wang@outlook.com, please let me know who you are.
My Fudan email is no longer active.

News

[2025.04] I am glad to be invited to serve as an area chair for NeurIPS 2025.
[2025.04] Our work on image inpainting has been selected as a highlight paper by CVPR 2025!
[2025.03] Received a grant from NVIDIA to support my ongoing research!
[2025.02] Our works on image inpainting and visual grounding have been accepted by CVPR 2025. Congrats to Zhenyang, and a big thank you to my co-authors!
[2025.01] Our works on long-trajectory empty street reconstruction and transformer pruning have been accepted by ICLR 2025. Congrats to Jingwei and Yizhuo!
[2024.12] Attending NeurIPS 2024 at Vancouver, Canada.
[2024.11] Our work on fMRI-vision latent alignment has been accepted by TMLR. Congrats to Prof. Qian!
[2024.10] Our work on subject repositioning has been accepted by TMLR!
[2024.09] Our works on lexical visual-language alignment and visual in-context prompt selection have been accepted by NeurIPS 2024. Congrats to Yifan, Chengming and Chen!
[2024.07] I have joined the MMLab@NTU as a postdoc! Looking forward to this new journey!
[2024.07] Our work on consistent fMRI decoding has been accepted by ECCV 2024. Congrats to Jingyang!
[2024.05] I have successfully defended my Ph.D. thesis!

Research

Content Creation:
- Image inpainting: context-stability and color-consistency [ASUKA, CVPR2025(Highlight)], ref-guided inpainting [LeftRefill, CVPR2024], subject repositioning [SEELE, TMLR2024];
- 3D inpainting: long-trajectory empty street reconstruction [StreetUnveiler, ICLR2025];
- Mask completion: amodal segmentation [C2F-Seg, ICCV2023].
Multi-modality:
- Vision-language: visual grounding and reasoning [ReasonGrounder, CVPR2025], lexical alignment [LexVLA, NeurIPS2024];
- Vision-fMRI: consistent fMRI decoding [NeuroPictor, ECCV2024], latent alignment [TMLR2024].
Subset Selection:
- Analysis: false-selection-rate control [Knockoffs-SPR, TPAMI2023], noisy set recovery [ICI, TPAMI2021];
- Application (sparse incidental parameters): out-of-distribution detection [CVPR2024], learning with noisy labels [SPR, CVPR2022], few-shot learning [ICI, CVPR2020];
- Application (other statistical models): network pruning [ICLR2025], in-context-learning [Partial2Global, NeurIPS2024].

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.

Publications

Updated list can be found at Google Scholar.

	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)
	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] [papaer] [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.
	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] Yikai Wang, Yanwei Fu, Xinwei Sun. TPAMI, 2023.
	Scalable Penalized Regression for Noise Detection in Learning with Noisy Labels. [arxiv] [paper] [code] [intro] Yikai Wang, Xinwei Sun, Yanwei Fu. CVPR, 2022.
	How to Trust Unlabeled Data? Instance Credibility Inference for Few-Shot Learning. [arxiv] [paper] [code] [intro] Yikai Wang, Li Zhang, Yuan Yao, Yanwei Fu. TPAMI, 2021.
	Instance Credibility Inference for Few-Shot Learning. [arxiv] [paper] [code] [intro] Yikai Wang, Chengming Xu, Chen Liu, Li Zhang, Yanwei Fu. CVPR, 2020.

Awards

Outstanding Graduates, Shanghai, 2024.
Outstanding Freshmen, Fudan University, 2015.

Education

Ph.D. in Statistics, 2019 - 2024, Fudan University.
B.S. in Mathematics, 2015 - 2019, Fudan University.

Experience

Research Fellow, 2024 - present, Nanyang Technological University, Singapore.

Service

Area chair: NeurIPS 2025;
Reviewer: NeurIPS 2022 (Top reviewer), 2023, 2024; CVPR 2023, 2024, 2025; ICCV 2023, 2025; ICLR 2024, 2025; ECCV 2024; ICML 2023, 2024, 2025; TIP from 2024; TMLR from 2023.
Co-organizer:
- CVPR 2023 tutorial on Few-shot Learning from Meta-Learning, Statistical Understanding to Applications;
- CVPR 2022 tutorial on Sparse Learning in Neural Networks and Robust Statistical Analysis.

Teaching

Neural Network and Deep Learning, TA, 2019-2022 Springs, Fudan University.