I am currently a first year Ph.D. student at Computer Science Department of Carnegie Mellon University and honorably
advised by Professor Zhihao Jia. Prior to that, I received my Master's degree in Robotics
at Carnegie Mellon University where I was honorably advised by Professor
Changliu Liu. I received my B.S.
degree in CS at Renmin University of China where I was honorably advised by Professor
Qin Jin.
My current research interests lie in the realm of MLSys.
Interests. Machine Learning System
Projects
-
SpecInfer: Accelerating Generative LLM Serving with Speculative Inference and Token Tree Verification
[pdf]
LLM inference serving system.
-
GradSign: Model Performance Inference with Theoretical Insights
[pdf]
[code]
We propose GradSign, an accurate, simple, and flexible metric for model performance inference with theoretical insights.
-
Spatio-Temporal Graph Dual-Attention Network for Multi-Agent Prediction and Tracking
[pdf]
Effective understanding of the environment and accurate trajectory prediction of surrounding dynamic obstacles are indispensable for intelligent mobile systems (like autonomous vehicles and social robots) to achieve safe and high-quality planning when they navigate in highly interactive and crowded scenarios. Due to the existence of frequent interactions and uncertainty in the scene evolution, it is desired for the prediction system to enable relational reasoning on different entities and provide a distribution of future trajectories for each agent. In this paper, we propose a generic generative neural system (called Social-WaGDAT) for multi-agent trajectory prediction, which makes a step forward to explicit interaction modeling by incorporating relational inductive biases with a dynamic graph representation and leverages both trajectory and scene context information. We also employ an efficient kinematic constraint layer applied to vehicle trajectory prediction which not only ensures physical feasibility but also enhances model performance.
Publications
-
GradSign: Model Performance Inference with Theoretical Insights, In Proceedings of ICLR 2022 main conference
Zhihao Zhang, Zhihao Jia
-
Spatio-Temporal Graph Dual-Attention Network for Multi-Agent Prediction and Tracking, IEEE Transactions on Intelligent Transportation Systems
Jiachen Li, Hengbo Ma, Zhihao Zhang, Masayoshi Tomizuka
Preprint
-
SpecInfer: Accelerating Generative LLM Serving with Speculative Inference and Token Tree Verification
Xupeng Miao*, Gabriele Oliaro*, Zhihao Zhang*, Xinhao Cheng, Zeyu Wang, Rae Ying Yee Wong, Zhuoming Chen, Daiyaan Arfeen, Reyna Abhyankar, Zhihao Jia
-
Communication Bounds for the Distributed Expert Problem, under review
with Zhihao Jia, Qi Pang, David Woodruff, Wenting Zheng
Teaching
-
2019, TA, Multimedia technology, RUC
-
2022 Spring, TA for 15-849, Machine Learning System, CMU
Miscellaneous. Music Production