I am a tenure-track assistant professor in the Computer Science Department at University of Houston. I received my Ph.D. degree in Computer Engineering from Indiana University in May 2024, where I was a member of the HiPDAC group working on building efficient and scalable deep learning system and advised by Prof. Dingwen Tao. I have extensive industry research experience and have participated in multiple research projects at laboratories such as Microsoft Research, Meta Reality Labs, and Argonne National Laboratory.

My research focuses on the following directions:

• Efficient machine learning systems (training/inference on parallel/distributed/heterogeneous hardware)
• Effective efficiency algorithms (model compression, data efficiency, parameter-efficient tuning, etc.)
• Large-scale DL/AI applications (Large Language Model, Agent, Image/Video Generation, DLRM, etc.)

I am currently not recruiting new Ph.D. students. Thank you for your interest.

Recent Publications

• Zhenghui Guo, Yuanbin Man, Junyuan Sheng, Bowen Lin, Ahmed Ahmed, Bo Jiang, Boyuan Zhang, Miao Yin, Sian Jin, Omprakash Gnawali, Chengming Zhang*. “Event-VStream: Event-Driven Real-Time Understanding for Long Video Streams.” CVPR 2026 Findings.
• Boyuan Zhang, Ding Zhou, Yafan Huang, Shihui Song, Hao Feng, Jinda Jia, Chengming Zhang, Zhi Zhang. “Near-Zero Cost KV Cache Compression for Large Language Model Inference.” IEEE IPDPS 2026.
• Boyuan Zhang, Luanzheng Guo, Jiannan Tian, Jinyang Liu, Daoce Wang, Chengming Zhang, Bo Fang, Fengguang Song, Jan Strube, Nathan R. Tallent, Dingwen Tao. “Accelerating AI Compression through Lightweight Lossless Encoding and Pipelined Workflows.” IEEE IPDPS 2026.
• Aristeidis Tsaris, Chengming Zhang, Xiao Wang, Junqi Yin, Siyan Liu, Moetasim Ashfaq, Ming Fan, Jong-Youl Choi, Mohamed Wahib, Dan Lu, Prasanna Balaprakash, Feiyi Wang. “Sequence Length Scaling in Vision Transformers for Scientific Images on Frontier.” International Journal of High Performance Computing Applications (IJHPCA), 2026.

(* corresponding author)

News

• [06/2026] Our paper “Event-VStream: Event-Driven Real-Time Understanding for Long Video Streams” appears in CVPR 2026 Findings.
• [05/2026] Two papers on KV cache compression for LLM inference and on accelerating AI compression appear in IEEE IPDPS 2026.
• [05/2026] Our paper on sequence length scaling of Vision Transformers for scientific images on Frontier is published in IJHPCA.
• [06/2025] Our paper “AdaCM²: On Understanding Extremely Long-Term Video with Adaptive Cross-Modality Memory Reduction” appears in CVPR 2025.
• [09/2024] I joined the University of Houston as a tenure-track assistant professor.