Search Results for author: Zhicai Wang

Found 7 papers, 4 papers with code

Flatband-Induced Itinerant Ferromagnetism in RbCo$_2$Se$_2$

no code implementations11 Mar 2021 Jianwei Huang, Zhicai Wang, Hongsheng Pang, Han Wu, Huibo Cao, Sung-Kwan Mo, Avinash Rustagi, A. F. Kemper, Meng Wang, Ming Yi, R. J. Birgeneau

$A$Co$_2$Se$_2$ ($A$=K, Rb, Cs) is a homologue of the iron-based superconductor, $A$Fe$_2$Se$_2$.

Superconductivity Materials Science

Parameterization of Cross-Token Relations with Relative Positional Encoding for Vision MLP

1 code implementation15 Jul 2022 Zhicai Wang, Yanbin Hao, Xingyu Gao, Hao Zhang, Shuo Wang, Tingting Mu, Xiangnan He

They use token-mixing layers to capture cross-token interactions, as opposed to the multi-head self-attention mechanism used by Transformers.

Backdoor Defense via Deconfounded Representation Learning

1 code implementation CVPR 2023 Zaixi Zhang, Qi Liu, Zhicai Wang, Zepu Lu, Qingyong Hu

The other clean model dedicates to capturing the desired causal effects by minimizing the mutual information with the confounding representations from the backdoored model and employing a sample-wise re-weighting scheme.

Backdoor Attack backdoor defense +1

Bi-directional Distribution Alignment for Transductive Zero-Shot Learning

1 code implementation CVPR 2023 Zhicai Wang, Yanbin Hao, Tingting Mu, Ouxiang Li, Shuo Wang, Xiangnan He

It is well-known that zero-shot learning (ZSL) can suffer severely from the problem of domain shift, where the true and learned data distributions for the unseen classes do not match.

Zero-Shot Learning

Generate What You Prefer: Reshaping Sequential Recommendation via Guided Diffusion

1 code implementation NeurIPS 2023 Zhengyi Yang, Jiancan Wu, Zhicai Wang, Xiang Wang, Yancheng Yuan, Xiangnan He

Scrutinizing previous studies, we can summarize a common learning-to-classify paradigm -- given a positive item, a recommender model performs negative sampling to add negative items and learns to classify whether the user prefers them or not, based on his/her historical interaction sequence.

Denoising Sequential Recommendation

DiffsFormer: A Diffusion Transformer on Stock Factor Augmentation

no code implementations5 Feb 2024 Yuan Gao, Haokun Chen, Xiang Wang, Zhicai Wang, Xue Wang, Jinyang Gao, Bolin Ding

Our research demonstrates the efficacy of leveraging AIGS and the DiffsFormer architecture to mitigate data scarcity in stock forecasting tasks.

Enhance Image Classification via Inter-Class Image Mixup with Diffusion Model

no code implementations28 Mar 2024 Zhicai Wang, Longhui Wei, Tan Wang, Heyu Chen, Yanbin Hao, Xiang Wang, Xiangnan He, Qi Tian

Text-to-image (T2I) generative models have recently emerged as a powerful tool, enabling the creation of photo-realistic images and giving rise to a multitude of applications.

Cannot find the paper you are looking for? You can Submit a new open access paper.