---

I'm an associate professor in Beijing University of Posts and Telecommunications (BUPT). I received my doctoral and bachelor degrees from Peking University in 2020 and 2015, co-advised by Prof. Gang Huang and Prof. Xuanzhe Liu.

I always look for highly self-motivated undergraduates and graduates. Please directly send your CV to me if you find my research interesting.

---

Research

I work on systems software, with focus on resource-constrained platforms like edge clouds, smartphones, IoTs, and satellites.

• Resource-efficient AI (especially LLM) systems - to support state-of-the-art deep learning models inference and training on smartphones, wearables, and IoTs, etc. Here are my personal opinions (drafted in Jul. 2023, outdated but lazy to update now) on how LLM is transforming our research, a survey on resource-efficient LLM and multimodal foundation models , as well as a paper list for it.
  

• Satellite Platform and Computing - we take satellites as the next-generation platform that will carry exciting applications that are unaffordable on the ground. What differentiates us from others is that we have our own satellite platform in orbit!

---

Projects

Our team is passionate about building open-sourced systems that can benefit others.

• mllm - a fast and lightweight multimodal LLM inference engine for mobile devices.

• RROS - a dual-kernel, Rust-based OS for satellites or other scenarios that need both real-time and general-purpose abilities. RROS = RTOS (Rust) + Linux (C). RROS has been sent into space already!

• E2E Federated Learning - an end-to-end federated learning prototype across smartphones.

• FedAdapter - a parameter-efficient federated learning framework.

• Mandheling - an on-device training engine with Qualcomm Hexagon DSP.

• Hotpot - a cute dog feeding project that lasts decades.