Scholar
Le Xu
Google Scholar ID: uFyE-AQAAAAJ
Bytedance
Citations & Impact
Citations
268
H-index
8
i10-index
7
Publications
20
Co-authors
0
Resume (English only)
Academic Achievements
- Preprints include 'PolyServe: Efficient Multi-SLO Serving at Scale' among others; published works such as 'StitchLLM: Serving LLMs, One Block at a Time' (ACL 25), which explores fine-grained layer stitching for resource-efficient LLM serving.
Research Experience
- Spent 1.5 years at Bytedance initiating the AIBrix project. Previously, was a Postdoc Researcher of Computer Science at UT Austin, working with Prof. Aditya Akella. Recipient of CIFellow 2021, supported by both the National Science Foundation (NSF) and Computing Research Association (CRA).
Education
- Ph.D. in Computer Science from the University of Illinois at Urbana Champaign in December 2021, advised by Indranil Gupta; M.S. in Computer Science from the same university in May 2015, also advised by Indranil Gupta; B.S. in Math and Computer Science from the same institution in May 2013.
Background
- Currently a research associate at the University of Edinburgh, working with Prof. Luo Mai. Ongoing projects explore the intersections of AI models and applications with emerging AI accelerators. Research mainly focuses on all aspects of resource-efficiency in computer systems.
Miscellany
- Occasionally writes about recent thinking and interesting works read on his blog, always looking for thoughts and feedback.
Co-authors