Yikai Wang is a Postdoctoral Research Fellow at the MMLab@NTU, working with Prof. Chen Change Loy, affiliated with S-Lab, Nanyang Technological University, Singapore. He obtained his Ph.D. in Statistics at Fudan University in 2024, advised by Prof. Yanwei Fu. Prior to this, He completed B.S. in Mathematics at Fudan University in 2019. His research spans statistical machine learning, computer vision, and foundation models, with a focus on content creation, multi-modal models and sample selection. |
Always available with yi-kai.wang@outlook.com, please let me know who you are.
My Fudan email is no longer active.
Filling Right Canvas based on Left Reference through Generalized Text-to-Image Diffusion Model. |
|
Advancing Image Inpainting: From Versatility to Consistency. |
|
Clean Sample Selection Algorithms with Statistical Sparsity Analysis. |
|
Few-shot Learning by Statistical Methods. |
|
Sparse Learning for Noisy Data Detection. |
FaceSketches-HairStyle40 for sketch2face generation. |
Arranged by topic and in chronological order. Updated list can be found at Google Scholar. (*): equal contribution; (†): corresponding author(s).
Repositioning the Subject within Image. |
|
LeftRefill: Filling Right Canvas based on Left Reference through Generalized Text-to-Image Diffusion Model. |
|
Coarse-to-Fine Amodal Segmentation with Shape Prior. |
|
3D StreetUnveiler with Semantic-Aware 2DGS. |
|
Towards Context-Stable and Visual-Consistent Image Inpainting. |
|
Entity-Level Text-Guided Image Manipulation. |
Unified Lexical Representation for Interpretable Visual-Language Alignment. |
|
NeuroPictor: Refining fMRI-to-Image Reconstruction via Multi-individual Pretraining and Multi-level Modulation. |
|
LEA: Learning Latent Embedding Alignment Model for fMRI Decoding and Encoding. |
Towards Global Optimal Visual In-Context Learning Prompt Selection. |
|
Test-Time Linear Out-of-Distribution Detection. |
|
Knockoffs-SPR: Clean Sample Selection in Learning with Noisy Labels. |
|
Scalable Penalized Regression for Noise Detection in Learning with Noisy Labels. |
|
How to Trust Unlabeled Data? Instance Credibility Inference for Few-Shot Learning. |
|
Instance Credibility Inference for Few-Shot Learning. |
FFD Augmentor: Towards Few-Shot Oracle Character Recognition from Scratch. |
|
An Embarrassingly Simple Baseline to One-Shot Learning. |
You are the -th visitor :)
Hosted on GitHub Pages.
Theme modified from minimal and Jonbarron.