Scholar
Ziheng Jiang
Google Scholar ID: tuRCeekAAAAJ
Research Scientist, ByteDance
Citations & Impact
Citations
4,400
H-index
19
i10-index
23
Publications
20
Co-authors
0
Publications
Resume
Academic Achievements
- Ziheng's work has been cited more than 4000 times. Some selected papers include:
- - MegaScale: Scaling Large Language Model Training to More Than 10,000 GPUs (2024)
- - MegaScale-Infer: Serving Mixture-of-Experts at Scale with Disaggregated Expert Parallelism (2025)
- - Understanding Stragglers in Large Model Training Using What-if Analysis (2025)
- - Comet: Fine-grained Computation-communication Overlapping for Mixture-of-Experts (2025)
- - TileLink: Generating Efficient Compute-Communication Overlapping Kernels using Tile-Centric Primitives (2025)
- - FLUX: Fast Software-based Communication Overlap On GPUs Through Kernel Fusion (Preprint, 2024)
- - Characterizing Structural Regularities of Labeled Data in Overparameterized Models (ICML, 2021)
- - Learning to optimize tensor programs (NIPS, 2018)
- - TVM: An Automated End-to-End Optimizing Compiler for Deep Learning (OSDI, 2018)
- - Efficient Deep Learning Inference on Edge Devices (MLSys, 2018)
Research Experience
- Heavily involved in projects such as MegaScale, Apache TVM, and Apache MXNet.
Education
- Ph.D. from the Paul G. Allen School of Computer Science & Engineering at the University of Washington, advised by Luis Ceze and Tianqi Chen; Bachelor’s degree from Fudan University, where he was a member of Fudan NLP Lab, working with Xipeng Qiu and Zheng Zhang.
Background
- Ziheng works on large language model (LLM) systems at ByteDance, focusing on scaling and optimizing LLM training and inference. His research interests include Machine Learning Systems and Large Language Models.