CV

Education

• Ph.D. in Computer Science and Engineering, Hong Kong University of Science and Technology
  • Advisor: Prof. Kai Chen
• M.Phil. in Computer Software and Theory, Institute of Software, Chinese Academy of Sciences
  • Advisors: Prof. Yunquan Zhang and Dr. Guoping Long
• B.Eng. in Computer Science and Technology, Huazhong University of Science and Technology

Intern/Work Experience

• 2024.4 – Present: Senior R&D Engineer (HY Team)
  • Technology and Engineering Group, Tencent
• 2020.6 – 2022.3: Research Intern (Industry-Academia Collaboration via WHAT Lab)
  • WeChat Search, Tencent
• 2019.9 – 2020.1: Research Intern and Project Co-ordinator (Mentored by Prof. Kai Chen)
  • Pengcheng Lab (PCL), Shenzhen
• 2015.9 – 2016.9: Research Intern and Project Co-ordinator (Mentored by Prof. Kai Chen)
  • Clustar (clustar.ai) — Federated Learning Accelerating
• 2014.7 – 2015.9: Full-time Software Engineer
  • Headquarter, Bank of China
• 2014.4 – 2014.6: Research Intern（Mentored by Wenzhi Liu, under Dr. Kai Yu）
  • IDL, Baidu
• 2013.8 – 2013.10: Intern (Mentored by Zhen Wang, under Dr. Wensong Zhang)
  • Core System, Taobao (Alibaba)
• 2013.5 – 2013.7: Research Intern(Mentored by Prof. Yi Xu, under Prof. Yuan Xie)
  • AMD China Research

Projects and Collaborations

• Central Software Institute, Huawei: Divide-and-Shuffle Synchronization (HKUST-Enterprise Collaboration)
• WeChat, Tencent: Learn to Label (HKUST-Enterprise Collaboration)
• PCL and Clustar: Federated Learning Accelerating (HKUST-Enterprise Collaboration)

Publications

Exploiting Student Parallelism for Low-latency GPU Inference of BERT-like Models in Online Services

Weiyan Wang, Yilun Jin, Yiming Zhang, Victor Junqiu Wei, Han Tian, Li Chen, Jinbao Xue, Yangyu Tao, Di Wang, Kai Chen. "Exploiting Student Parallelism for Low-latency GPU Inference of BERT-like Models in Online Services." KDD 2025.

HunyuanImage-3.0: A Powerful Native Multimodal Model for Image Generation

Tencent Hunyuan Team (including Weiyan Wang). "HunyuanImage-3.0: A Powerful Native Multimodal Model for Image Generation." Technical Report, 2025.

HunyuanVideo-1.5: A Leading Lightweight Video Generation Model

Tencent Hunyuan Team (including Weiyan Wang). "HunyuanVideo-1.5: A Leading Lightweight Video Generation Model." Technical Report, 2025.

Surge Phenomenon in Optimal Learning Rate and Batch Size Scaling

Shuaipeng Li, Penghao Zhao, Hailin Zhang, Samm Sun, Hao Wu, Dian Jiao, Weiyan Wang, Chengjun Liu, Zheng Fang, Jinbao Xue, Yangyu Tao, Bin Cui, Di Wang. "Surge Phenomenon in Optimal Learning Rate and Batch Size Scaling." NeurIPS 2024.

HunyuanVideo: A Systematic Framework For Large Video Generative Models

Tencent Hunyuan Team (including Weiyan Wang). "HunyuanVideo: A Systematic Framework For Large Video Generative Models." Technical Report, 2024.

Prometheus: Out-of-distribution Fluid Dynamics Modeling with Disentangled Graph ODE

Hao Wu, Huiyuan Wang, Kun Wang, Weiyan Wang, Changan Ye, Yangyu Tao, Chong Chen, Xian-Sheng Hua, Xiao Luo. "Prometheus: Out-of-distribution Fluid Dynamics Modeling with Disentangled Graph ODE." ICML 2024.

BeamVQ: Beam Search with Vector Quantization to Mitigate Data Scarcity in Physical Spatiotemporal Forecasting

Weiyan Wang, Xingjian Shi, Ruiqi Shu, Yuan Gao, Rui Ray Chen, Kun Wang, Fan Xu, Jinbao Xue, Shuaipeng Li, Yangyu Tao, Di Wang, Hao Wu, Xiaomeng Huang. "BeamVQ: Beam Search with Vector Quantization to Mitigate Data Scarcity in Physical Spatiotemporal Forecasting." Technical Report, 2024.

Hunyuan-DiT: A Powerful Multi-Resolution Diffusion Transformer with Fine-Grained Chinese Understanding

Tencent Hunyuan Team (including Weiyan Wang). "Hunyuan-DiT: A Powerful Multi-Resolution Diffusion Transformer with Fine-Grained Chinese Understanding." Technical Report, 2024.

Multi-task Learning Based Keywords Weighted Siamese Model for Semantic Retrieval

Mengmeng Kuang, Zhenhong Chen, Weiyan Wang (Corresponding), Lie Kang, Qiang Yan, Min Tang, Penghui Hao. "Multi-task Learning Based Keywords Weighted Siamese Model for Semantic Retrieval." PAKDD 2023.

MDP: Model Decomposition and Parallelization of Vision Transformer for Distributed Edge Inference

Weiyan Wang, Yiming Zhang, Yilun Jin, Han Tian, Li Chen. "MDP: Model Decomposition and Parallelization of Vision Transformer for Distributed Edge Inference." IEEE MSN.

Addressing Network Bottlenecks with Divide-and-Shuffle Synchronization for Distributed DNN Training

Weiyan Wang, Cengguang Zhang, Liu Yang, Kai Chen, Kun Tan. "Addressing Network Bottlenecks with Divide-and-Shuffle Synchronization for Distributed DNN Training." IEEE INFOCOM 2022.

Multi-Objective Congestion Control

Yiqing Ma, Han Tian, Xudong Liao, Junxue Zhang, Weiyan Wang, Kai Chen, Xin Jin. "Multi-Objective Congestion Control." EuroSys 2022.

Efficient Two-stage Label Noise Reduction for Retrieval-based Tasks

Mengmeng Kuang, Weiyan Wang, Zhenhong Chen, Lie Kang, Qiang Yan. "Efficient Two-stage Label Noise Reduction for Retrieval-based Tasks." WSDM 2022.

Enabling Edge-Cloud Video Analytics for Robotics Applications

Yiding Wang, Weiyan Wang, Duowen Liu, Xin Jin, Junchen Jiang, Kai Chen. "Enabling Edge-Cloud Video Analytics for Robotics Applications." IEEE INFOCOM 2021.

Domain-specific Communication Optimization for Distributed DNN Training

Hao Wang, Jingrong Chen, Xinchen Wan, Han Tian, Jiacheng Xia, Gaoxiong Zeng, Weiyan Wang, Kai Chen, Wei Bai, Junchen Jiang. "Domain-specific Communication Optimization for Distributed DNN Training." Preprint, 2020.

Quantifying the Performance of Federated Transfer Learning

Qinghe Jing, Weiyan Wang, Junxue Zhang, Han Tian, Kai Chen. "Quantifying the Performance of Federated Transfer Learning." IJCAI FL Workshop, 2019. Best Student Paper.

Rethinking Transport Layer Design for Distributed Machine Learning

Jiacheng Xia, Gaoxiong Zeng, Junxue Zhang, Weiyan Wang, Wei Bai, Junchen Jiang, Kai Chen. "Rethinking Transport Layer Design for Distributed Machine Learning." APNet 2019.

Bridging the Edge-Cloud Barrier for Real-time Advanced Vision Analytics

Yiding Wang, Weiyan Wang, Junxue Zhang, Junchen Jiang, Kai Chen. "Bridging the Edge-Cloud Barrier for Real-time Advanced Vision Analytics." HotCloud 2019.

Integrating User and Agent Models: A Deep Task-Oriented Dialogue System

Weiyan Wang, Yuxiang Wu, Yu Zhang, Zhongqi Lu, Kaixiang Mo, Qiang Yang. "Integrating User and Agent Models: A Deep Task-Oriented Dialogue System." Preprint, 2017.

Parallelization and Performance Optimization on Face Detection Algorithm with OpenCL: A Case Study

Weiyan Wang, Yunquan Zhang, Shengen Yan, Ying Zhang, Haipeng Jia. "Parallelization and Performance Optimization on Face Detection Algorithm with OpenCL: A Case Study." Tsinghua Science and Technology.

CLSIFT: An Optimization Study of the Scale Invariance Feature Transform on GPUs

Weiyan Wang, Yunquan Zhang, Guoping Long, Shengen Yan, Haipeng Jia. "CLSIFT: An Optimization Study of the Scale Invariance Feature Transform on GPUs." HPCC 2013.

Accelerating Viola-Jones Face Detection Algorithm on GPUs

Haipeng Jia, Yunquan Zhang, Weiyan Wang, Jianliang Xu. "Accelerating Viola-Jones Face Detection Algorithm on GPUs." HPCC 2012.

Professional Services

• 2025    NeurIPS Reviewer
• 2025    Journal Reviewer: Performance Evaluation, Sensor, and Electronics
• 2025    KDD Commendable Reviewer
• 2023    Globalcom Workshop AINextGenWN Reviewer
• 2022    ICNCIT Reviewer
• 2020    Sigcomm Artifact Reviewer
• 2013–2018    CSDN OpenCL Forum Moderator
• 2011–2013    OpenCV Code Contributor

Teaching

• Teaching Assistant, COMP 1021 (Introduction to Computer Science), HKUST, Spring & Fall 2016, Spring 2017
• Teaching Assistant, MSBD 6000B (Deep Learning), HKUST, Fall 2017
• Lecturer, Deep Learning Workshop: Diving into CNN, HKSAIR-HKUST, 2019 (slides)
• Chapter Contributor, book Transfer Learning, Cambridge University Press

Skills

• Large-scale distributed training (Deepspeed, FSDP, Megatron-LM, verl)
• GPU programming (CUDA, OpenCL)
• ML systems co-design (training efficiency, inference optimization)
• Programming: Python, C/C++, CUDA