AI4GC Lab

Tianqi Liu

About Me

Hi! I'm Tianqi Liu (刘天琦), a first-year M.S. student at AI4GC Lab, Zhejiang University, advised by Shengyu Zhang.

My research focuses on recommender systems and LLM agents — in particular model customization, lightweight on-device deployment, and reinforcement-learning-based refinement. Recently I have grown interested in personalized, user-centric LLM agents and the challenge of proactive interaction in human–agent collaboration.

Selected Papers

ACM MM2025

CHORD: Customizing Hybrid-precision On-device Model for Sequential Recommendation with Device-cloud Collaboration

Tianqi Liu, Kairui Fu, Shengyu Zhang^✉, Wenyan Fan, Zhaocheng Du, Jieming Zhu, Fan Wu, Fei Wu

Paper Blog

Projects

DeskCraft — A benchmark for desktop GUI agents with 538 executable tasks in a live Ubuntu environment, covering professional workflows and human-in-the-loop collaboration. (code)

Experience

I have interned at several industry teams on recommendation systems and code LLMs:

Alibaba Taobao & Tmall Group — 2026.06 – present
Huawei Markov Lab — 2025.08 – 2026.05
Huawei Noah's Ark Lab — 2025.03 – 2025.05

Lab Notes

On-site

Oct 2025

CHORD: Customizing Hybrid-precision On-device Recommendation Models with Device-Cloud Collaboration

CHORD customizes a hybrid-precision on-device recommendation model for each instance, achieving personalized, resource-adaptive deployment in a single forward pass. Accepted to ACM MM 2025.