X
Xiaohuan Zhou
Researcher at Beijing University of Posts and Telecommunications
Publications - 7
Citations - 919
Xiaohuan Zhou is an academic researcher from Beijing University of Posts and Telecommunications. The author has contributed to research in topics: Computer science & Engineering. The author has an hindex of 2, co-authored 2 publications receiving 451 citations.
Papers
More filters
Proceedings ArticleDOI
xDeepFM: Combining Explicit and Implicit Feature Interactions for Recommender Systems
TL;DR: A novel Compressed Interaction Network (CIN), which aims to generate feature interactions in an explicit fashion and at the vector-wise level and is named eXtreme Deep Factorization Machine (xDeepFM), which is able to learn certain bounded-degree feature interactions explicitly and can learn arbitrary low- and high-order feature interactions implicitly.
Proceedings ArticleDOI
xDeepFM: Combining Explicit and Implicit Feature Interactions for Recommender Systems
TL;DR: Wang et al. as mentioned in this paper proposed a Compressed Interaction Network (CIN), which aims to generate feature interactions in an explicit fashion and at the vector-wise level.
Journal ArticleDOI
ONE-PEACE: Exploring One General Representation Model Toward Unlimited Modalities
TL;DR: One-PEACE as mentioned in this paper is a highly extensible model with 4B parameters that can seamlessly align and integrate representations across vision, audio, and language modalities, which can capture fine-grained details within modalities concurrently.
Journal ArticleDOI
OFASys: A Multi-Modal Multi-Task Learning System for Building Generalist Models
Jinze Bai,Rui Men,Huanming Yang,Xuancheng Ren,Kai-fung Edward Dang,Yichang Zhang,Xiaohuan Zhou,Peng Wang,Sinan Tan,Andrew Yang,Zeyu Cui,Yu Han,Shuai Bai,Wenhang Ge,Jianxin Ma,Junyang Lin,Jingren Zhou,Chang Zhou +17 more
TL;DR: OFA-Sys as mentioned in this paper is a generalist model learning system, built on top of a declarative task interface named multi-modal instruction, which can handle text, image, speech, video, and motion data.
Journal ArticleDOI
MMSpeech: Multi-modal Multi-task Encoder-Decoder Pre-training for Speech Recognition
TL;DR: The authors proposed a multi-modal multi-task encoder-decoder pre-training framework for Mandarin automatic speech recognition (MMSpeech), which employs both unlabeled speech and text data.