About

I am a 4th year Ph.D. candidate at Institute for AI Industry Research (AIR), Tsinghua University, advised by Prof. Yunxin Liu（刘云新） and working closely with Prof. Ting Cao（曹婷）. Prior to this, I received my B.E. degree from Department of Electronic Engineering, Tsinghua University in 2022.

I am interested in on-device and physical AI, and currently focused on algorithm-system co-design toward generalist embodied agents. My previous works are focused on inference system efficiency:

• OxyGen: unified KV cache management for multi-task VLA inference.
• Vec-LUT (MobiSys 2026): LUT-based mpGeMM kernel for ultra-low-bit LLM inference.
• FlexNN (MobiCom 2024): memory-adaptive DNN inference on edge devices.

I am looking for opportunities in Embodied AI & LLM Infra.

Feel free to email me: lixiangy22@mails.tsinghua.edu.cn.

News

• [Mar. 2026] "OxyGen: Unified KV Cache Management for Vision-Language-Action Models under Multi-Task Parallelism" released. Paper / Code
• [Mar. 2026] "Vec-LUT: Vector Table Lookup for Parallel Ultra-Low-Bit LLM Inference on Edge Devices" accepted to MobiSys 2026. Paper / Code / Model
• [Aug. 2025] "An Empirical Study of LLM Reasoning Ability Under Strict Output Length Constraint" accepted to EMNLP 2025. Paper / Page
• [Jul. 2025] "Squeezer: Efficient Multi-DNN Inference for Edge Video Analytics via Cross-Model Scheduling" accepted to TMC. Paper
• [Nov. 2024] Presented FlexNN at MobiCom 2024, Washington D.C. Paper / Code / Slides
• [Apr. 2024] FlexNN awarded 4 badges in artifact evaluation. Code
• [Jan. 2024] "Personal LLM Agents: Insights and Survey about the Capability, Efficiency and Security" released. Paper / Page
• [Nov. 2023] "FlexNN: Efficient and Adaptive DNN Inference on Memory-Constrained Edge Devices" accepted to MobiCom 2024. Paper

Experiences

Awards

• 清华之友-智能产业研究院清智奖学金, 2025.12
• 清华之友-济宁英才奖学金, 2024.11

Internship

• ByteDance, Big Data (Serverless/FaaS) Infrastructure Development, 2021.06–2021.09

Teaching Assistant

• Tsinghua University, Computer Program Design (undergraduate), 2025 Spring & Summer
• Tsinghua University, Basic Music Theory and Vocal Practice, 2023 Fall

Others

• EESAST (清华大学电子工程系学生科协), 2019.07–2022.06