Yinghao Tang

I am a second year Ph.D. student in Computer Science at Zhejiang University under the supervision of Wei Chen in VAI group. I received my B.Eng. degree from Sichuan University, where I was advised by Mingjie Tang in IDS lab. My research explores "AI for Visual Communication", focusing on how to use artificial intelligence to communicate information in ways that are not only efficient but also aesthetically expressive and visually engaging. Outside my main research, I love tinkering with AI infra infrastructure and system design (side passion😊).

PUBLICATIONS

SCORPIO: Serving the Right Requests at the Right Time for Heterogeneous SLOs in LLM Inference

Yinghao Tang, Tingfeng Lan, Xiuqi Huang, Hui Lu, Wei Chen

Preprint 2025Paper

An SLO-oriented LLM serving system that maximizes system goodput and SLO attainment by exploiting SLO heterogeneity through adaptive scheduling across admission control, queue management, and batch selection.

Exploring Multimodal Prompt for Visualization Authoring with Large Language Models

Zhen Wen, Luoxuan Weng, Yinghao Tang, Runjin Zhang, Yuxin Liu, Bo Pan, Minfeng Zhu, Wei Chen

Preprint 2025Paper

A novel approach to visualization authoring using multimodal prompts with large language models.

DataLab: A Unified Platform for LLM-Powered Business Intelligence

Luoxuan Weng, Yinghao Tang, Yingchaojie Feng, Zhuo Chang, Ruiqin Chen, Haozhe Feng, Chen Hou, Danqing Huang, Yang Li, Huaming Rao, Haonan Wang, Canshi Wei, Xiaofeng Yang, Yuhui Zhang, Yifeng Zheng, Xiuqi Huang, Minfeng Zhu, Yuxin Ma, Bin Cui, Peng Chen, Wei Chen

ICDE 2025Paper

a unified BI platform that integrates a one-stop LLM-based agent framework with a augmented computational notebook interface.

DLRover-RM: Resource Optimization for Deep Recommendation Models Training in the Cloud

Qinlong Wang, Tingfeng Lan, Yinghao Tang, Bo Sang, Ziling Huang, Yiheng Du, Haitao Zhang, Jian Sha, Hui Lu, Yuanchun Zhou, others

VLDB 2024Paper

An efficient resource management system for training deep recommendation models in cloud environments.

MixLoRA: Enhancing Large Language Models Fine-Tuning with LoRA-based Mixture of Experts

Dengchun Li, Yingzi Ma, Naizheng Wang, Zhengmao Ye, Zhiyuan Cheng, Yinghao Tang, Yan Zhang, Lei Duan, Jie Zuo, Cal Yang, Mingjie Tang

Preprint 2024Paper

A novel approach to fine-tune large language models using LoRA-based mixture of experts, improving efficiency and performance.

MISC

Except for academics, I keep the habits of reading and exercising, including swimming and working out. I love music, especially R&B and Hip-Hop 🎧. My favorite artists are Tyler, The Creator and Frank Ocean. One of my favorite quotes from `White Ferrari` by Frank Ocean is:

Mind Over Matter is magic, I do magic.