Weihao Yu (余伟浩)

Weihao Yu

  • PhD student at LV Lab, National University of Singapore (NUS)
  • Supervisor: Prof. Xinchao Wang
  • Research interests: Computer Vision, NLP, Multimodal AI
  • Languages: Teochew, Mandarin, English, C, Python
  • Emails: weihaoyu6@gmail.com   weihaoyu@u.nus.edu
  • Links: [Google Scholar] [GitHub] [LinkedIn] [X (Twitter)]
  • Weihao Yu is currently a PhD student at NUS and was a research intern at Amazon AWS AI Lab, Microsoft Azure AI, and Sea AI Lab. His work MetaFormer proposes the hypothesis "MetaFormer is actually what you need" to challenge the common belief "Attention is all you need", and builds an extremely simple model PoolFormer to verify it. He, fortunately, received academic awards such as Snap Research Fellowship and Google TRC Researcher Spotlight.
  • I'm currently on the job market and would appreciate any job recommendations suitable for me. Thank you!

Publication

Google Scholar

MambaOut: Do We Really Need Mamba for Vision?
Weihao Yu, Xinchao Wang
arXiv:2405.07992 [Code] Star
MM-Vet: Evaluating Large Multimodal Models for Integrated Capabilities
Weihao Yu*, Zhengyuan Yang*, Linjie Li, Jianfeng Wang, Kevin Lin, Zicheng Liu, Xinchao Wang, Lijuan Wang
ICML 2024 [Code] Star
InceptionNeXt: When Inception Meets ConvNeXt
Weihao Yu, Pan Zhou, Shuicheng Yan, Xinchao Wang
CVPR 2024 [Code] Star
MetaFormer Baselines for Vision
Weihao Yu, Chenyang Si, Pan Zhou, Mi Luo, Yichen Zhou, Jiashi Feng, Shuicheng Yan, Xinchao Wang
TPAMI 2024 [Synced News (in Chinese)] [Code] Star (SOTA without novel token mixer)
MetaFormer Is Actually What You Need for Vision
Weihao Yu, Mi Luo, Pan Zhou, Chenyang Si, Yichen Zhou, Xinchao Wang, Jiashi Feng, Shuicheng Yan
CVPR 2022 (Oral) [Marktechpost News] [QbitAI News (in Chinese)] [Code] Star
Inception Transformer
Chenyang Si*, Weihao Yu*, Pan Zhou, Yichen Zhou, Xinchao Wang, Shuicheng Yan
NeurIPS 2022 (Oral) [Code] Star
Tokens-to-Token ViT: Training Vision Transformers from Scratch on ImageNet
Li Yuan, Yunpeng Chen, Tao Wang, Weihao Yu, Yujun Shi, Zihang Jiang, Francis EH Tay, Jiashi Feng, Shuicheng Yan
ICCV 2021 [Code] Star
LV-BERT: Exploiting Layer Variety for BERT
Weihao Yu, Zihang Jiang, Fei Chen, Qibin Hou, Jiashi Feng
Findings of ACL 2021 [Code] Star
ConvBERT: Improving BERT with Span-based Dynamic Convolution
Zihang Jiang*, Weihao Yu*, Daquan Zhou, Yunpeng Chen, Jiashi Feng, Shuicheng Yan
NeurIPS 2020 (Spotlight) [Code] Star
ReClor: A Reading Comprehension Dataset Requiring Logical Reasoning
Weihao Yu*, Zihang Jiang*, Yanfei Dong, Jiashi Feng
ICLR 2020 [Project] [Code] Star
Heterogeneous Graph Learning for Visual Commonsense Reasoning
Weijiang Yu, Jingwen Zhou, Weihao Yu, Xiaodan Liang, Nong Xiao
NeurIPS 2019 (Spotlight) [Code] Star
Knowledge-Embedded Routing Network for Scene Graph Generation
Tianshui Chen*, Weihao Yu*, Riquan Chen, Liang Lin
CVPR 2019 [Code] Star
Deep Reasoning with Knowledge Graph for Social Relationship Understanding
Zhouxia Wang*, Tianshui Chen*, Jimmy Ren, Weihao Yu, Hui Cheng, Liang Lin
IJCAI 2018 [Code] Star
Propagation of Airy Gaussian Vortex Beams in Uniaxial Crystals
Weihao Yu, Ruihuang Zhao, Fu Deng, Jiayao Huang, Chidao Chen, Xiangbo Yang, Yanping Zhao, Dongmei Deng
Chin. Phys. B, 2016