Chengru Song

Principal Researcher, AI Platform, Kuaishou- 快手科技

Joined

July 2019

Names

Chengru Song

Emails

****@126.com (Confirmed)

****@kuaishou.com (Confirmed)

****@gmail.com (Confirmed)

Personal Links

DBLP

Career & Education History

Principal Researcher

AI Platform, Kuaishou- 快手科技 (kuaishou.com)

2020 – 2026

MS student

Automation, Tsinghua University, Tsinghua University (tsinghua.edu.cn)

2012 – 2015

Undergrad student

Automation, Tsinghua University, Tsinghua University (tsinghua.edu.cn)

2008 – 2012

Advisors, Relations & Conflicts

Coworker

Jianchao Tan

2021 – 2024

PhD Advisor

Changshui Zhang

2012 – 2015

Expertise

AI Infrastructure

2020 – Present

Computational Advertising

2015 – 2020

Publications

Decoding at the Speed of Thought: Harnessing Parallel Decoding of Lexical Unit for LLMs
Chenxi Sun, Hongzhi Zhang, Zijia Lin, Jingyuan Zhang, Fuzheng Zhang, Zhongyuan Wang, Bin Chen, Chengru Song, Di ZHANG, Yue Yu, Deyi Xiong
- OpenReview Archive Direct Upload
- Readers: Everyone
Video-LaVIT: Unified Video-Language Pre-training with Decoupled Visual-Motional Tokenization
Yang Jin, Zhicheng Sun, Kun Xu, Kun Xu, Liwei Chen, Hao Jiang, Quzhe Huang, Chengru Song, Yuliang Liu, Di ZHANG, Yang Song, Kun Gai, Yadong MU
- ICML 2024 Oral
- Readers: Everyone
Unified Language-Vision Pretraining in LLM with Dynamic Discrete Visual Tokenization
Yang Jin, Kun Xu, Kun Xu, Liwei Chen, Chao Liao, Jianchao Tan, Quzhe Huang, Bin CHEN, Chengru Song, dai meng, Di ZHANG, Wenwu Ou, Kun Gai, Yadong MU
- ICLR 2024 poster
- Readers: Everyone
MaskFusion: Feature Augmentation for Click-Through Rate Prediction via Input-adaptive Mask Fusion
Chao Liao, Jianchao Tan, Jiyuan Jia, Yi Guo, Chengru Song
- Published: 01 Feb 2023, Last Modified: 27 Feb 2023
- ICLR 2023 poster
- Readers: Everyone
Deep Interest Network for Click-Through Rate Prediction
Guorui Zhou, Xiaoqiang Zhu, Chengru Song, Ying Fan, Han Zhu, Xiao Ma, Yanghui Yan, Junqi Jin, Han Li, Kun Gai
- 2018 (modified: 12 Nov 2022)
- KDD 2018
- Readers: Everyone

Co-Authors

View all 35 co-authors

Chengru Song

Names

Emails

Personal Links

Career & Education History

Advisors, Relations & Conflicts

Expertise

Publications

Decoding at the Speed of Thought: Harnessing Parallel Decoding of Lexical Unit for LLMs

Video-LaVIT: Unified Video-Language Pre-training with Decoupled Visual-Motional Tokenization

Unified Language-Vision Pretraining in LLM with Dynamic Discrete Visual Tokenization

MaskFusion: Feature Augmentation for Click-Through Rate Prediction via Input-adaptive Mask Fusion

Deep Interest Network for Click-Through Rate Prediction

Co-Authors