Preprint · 2026
Learning to Factorize and Adapt: A Versatile Approach Toward Universal Spatio-Temporal Foundation Models ↗
Siru Zhong, Junjie Qiu, Yangyu Wu, Yiqiu Liu, Yuanpeng He, Zhongwen Rao, Bin Yang, Chenjuan Guo, Hao Xu, Yuxuan Liang
Junjie Qiu
Memory modeling / Sequence modeling / Physical AI
I’m a first-year Ph.D. student at HKUST (Guangzhou), advised by Prof. Yuxuan Liang. I study memory modeling for physical AI.
I’m interested in how past experiences shape an agent’s future behavior and decisions through memory, and how we can shape that influence. My work spans temporal pretraining, multimodal video generation, and memory mechanisms for long-form storytelling.
RESEARCH INTERESTS
Beyond the cycle of success and failure ↗Memory for long-horizon understanding, decisions and action.
01
Selected work
01 / VIDEO SYSTEMS
From scripts to feedback: AI video production
Designed video-agent architecture using narrative memory, checks and targeted correction for cross-shot consistency.
ByFusion · LuckyShort ↗
02 / TEMPORAL MODELSUniversal temporal pretraining
Designed and pretrained UTP to study temporal representations that transfer across domains.
FactoST-v2 ↗
02
Blog
Why do robots need memory?
A missing cup offers a way into memory and the next action.
All notes ↗03
Experience
ByFusion · LuckyShort+
Architect · AI Video Generation
Led video-agent architecture for AI short-drama production, connecting long-form planning, narrative memory, controllable generation, and feedback on visual consistency.
Hong Kong University of Science and Technology (Guangzhou)+
Research Assistant · Temporal Modeling
Designed and pretrained temporal models for cross-domain forecasting, with variable-length context, quantile prediction, and efficient downstream adaptation.
Huawei · 2012 Laboratories+
Research Intern · Temporal Modeling
Adapted pretrained temporal models to Ascend and evaluated them against reproduced baselines on telecommunications and power forecasting datasets.
SUSTech · Center for Computational Science and Engineering+
Intern · High-Performance Computing
Benchmarked and commissioned HPC nodes, then used MPI profiling to optimize the interconnect topology of four newly installed nodes, reducing MPI communication time by approximately 20%.
04
Publications
NeurIPS 2025
Learning to Factorize Spatio-Temporal Foundation Models ↗
Siru Zhong, Junjie Qiu, Yangyu Wu, Xingchen Zou, Zhongwen Rao, Bin Yang, Chenjuan Guo, Hao Xu, Yuxuan Liang
Education
Sep. 2026 — Present
Hong Kong University of Science and Technology (Guangzhou)
Ph.D. in Intelligent Transportation
Advised by Prof. Yuxuan Liang
Sep. 2021 — Jul. 2025
Southern University of Science and Technology
B.S. in Data Science and Big Data Technology
GPA 3.89/4.00 · Rank 4/53 (top 10%)
Outstanding Graduate; Outstanding Undergraduate Thesis; Top Ten Graduate Award, Shude Residential College