My research focuses on robot video generation and world models, multimodal large language models, and agent systems. I am interested in building intelligent systems that can understand, predict, and reason about the physical world across modalities.

News

2026.05
As corresponding author, our paper "Evolving Multimodal Models for Physical Dynamics: A Multi-objective Neuroevolution Approach" was accepted by IEEE Transactions on Evolutionary Computation (TEVC), a CAS JCR Tier-1 (双一区) journal. Congrats to all collaborators!
2026.05
Joined Tencent IEG, Lightspeed Studios as a Project Up (青云计划) Research Intern, working on video generation world models.
2026.05
As first author, two papers were accepted to KDD 2026 Research Track. Congrats to all collaborators!
2026.05
As first author, a paper on large-scale spatio-temporal pre-training and post-training is accepted by ICML 2026. Congratulations to all!
2026.04
A paper on the topic of Inference-time Safety Alignment was accepted by ACL 2026.
2026.01
Two papers were accepted to TPAMI. Congrats to all collaborators!
2025.12
Two papers were accepted to AAAI and ICLR. Congrats to all collaborators!
2025.06
As corresponding author, one paper was accepted to ICCV. Congrats to all collaborators!
2025.05
As co-first author, one paper was accepted to ICML. Congrats to all collaborators!
2025.03
As first author, one paper was accepted to KDD. Congrats to all collaborators!
2024.12
As corresponding author, one paper was accepted to ICLR. Congrats to all collaborators!
2024.07
As first author or co-first author, three papers were accepted to NeurIPS. Congrats to all collaborators!
2024.05
As first author, one paper was accepted to KDD. Congrats to all collaborators!
2024.05
As first author, one paper was accepted to ACM MM. Congrats to all collaborators!
2024.05
As first author, one paper was accepted to ICML. Congrats to all collaborators!
2023.12
As first author, two papers were accepted to AAAI. Congrats to all collaborators!
2023.07
As co-first author, one paper was accepted to NeurIPS. Congrats to all collaborators!

Experience

Research Intern, Tencent IEG

May 2026 - Late Sep. 2026

Lightspeed Studios

Research Intern, Tencent CSIG

Aug. 2025 - May. 2026

Tencent Jarvis Lab

Research Intern, Tencent TEG

Aug. 2023 - Jul. 2025

Hunyuan Large Model

Research Collaboration

Weekly Meetings

Research Collaborator — Video Generation

Jun. 2026 - Present

Prof. Ming-Hsuan Yang · UC Merced & Google DeepMind

Recent collaboration: ReCAP, efficient context scheduling for long-horizon video world models.

Research Collaborator — Spatiotemporal Predictive Learning

Dec. 2023 - Jun. 2025

Dr. Xingjian Shi · Ph.D., HKUST · Boson AI (at the time)

Close collaboration on physical spatiotemporal forecasting, including BeamVQ, a metric-guided latent-search framework.

Selected Publications

Google Scholar
Safety-aware rollouts paper figure

Safety-Aware Rollouts with Self-Reflection and Structured Rewards

Huahui Yi, Kun Wang, Haolong Hu, Moayad Aloqaily, Liang Lin, Junhao Dong, Qiankun Li, Xing Fan, Hao Wu, Yang Liu, and Qingsong Wen Corresponding Author
Under Review
ICCV paper figure

Frequency-Aligned Knowledge Distillation for Lightweight Spatiotemporal Forecasting

Yuqi Li, Chuanguang Yang, Hansheng Zeng, Zeyu Dong, Zhulin An, Yongjun Xu, Yingli Tian, and Hao Wu Corresponding Author
ICCV 2025

Service

Selected Awards & Honors

2025
Outstanding Graduate
USTC × Tencent Joint Training Program
2022
National Scholarship Top 1% in China
University of Science and Technology of China
2022
First-Class Scholarship
University of Science and Technology of China

Interests

Basketball

I make time for one to two hours of basketball most days. If you’re free, you’re always welcome to join me for a game!

My favorite moves are fadeaway jumpers and three-pointers. I’ve spent many happy hours playing at USTC’s Gaoxin Campus gym, the basketball gym at Tencent’s Beijing headquarters, and Tsinghua University’s Zijing courts.

A little time on the court.
WeChat
WeChat QR code for Alexander