Zhengyang Liang is currently first-year PhD at Singapore Management University, supervised by Prof.Lizi Liao.I used to work as a research intern at Beijing Academic of Artificial Intelligence, supervised by PI.Zheng Liu and PI.Bo Zhao. Dedicated to exploring Video MLLM. Before that, I got my bachelor’s degree at Beijing University of Posts and Telecommunications.

My research interest includes MLLM, self-supervised learning.

✉️ Feel free to contact me with email: chr1ce@foxmail.com

🔥 News

• 2025.07:  🎉🎉 One paper accepted by ACMMM 2025.
• 2025.06:  🎉🎉 Video-XL-2 is released, try it on Video-XL-2.
• 2025.05:  🎉🎉 I will be going to SMU and will become a PhD student in August. Supervised by Prof.Lizi Liao.
• 2025.03:   Three papers have accepted by CVPR 2025. Congratulations to all collaborators.
• 2024.05:   I joined Beijing Academic of Artificial Intelligence as a research intern.
• 2024.07:   I got my bachelor degree from Beijing University of Posts and Telecommunications.
• 2023.12:   I joined Lenovo Research as a research intern.

📝 Publications

Arxiv

Video-XL-2: Towards Very Long-Video Understanding Through Task-Aware KV Sparsification

Minghao Qin^*, Xiangrui Liu^*, Zhengyang Liang^*, Yan Shu, Huaying Yuan, Juenjie Zhou, Shitao Xiao, Bo Zhao, Zheng Liu^✉

Paper|HomePage|Code|Model

ACL 2025

Any Information Is Just Worth One Single Screenshot: Unifying Search With Visualized Information Retrieval

Ze Liu, Zhengyang Liang, Junjie Zhou, Zheng Liu^✉, Defu Lian

Paper|Code|Model|Dataset

CVPR 2025(Oral)

Video-XL: Extra-Long Vision Language Model for Hour-Scale Video Understanding

Yan Shu, Zheng Liu^✉, Peitian Zhang, Minghao Qin, Junjie Zhou, Zhengyang Liang, Tiejun Huang, Bo Zhao^✉

Paper|Code

CVPR 2025

MLVU: A Comprehensive Benchmark for Multi-Task Long Video Understanding

Junjie Zhou^*, Yan Shu^*, Bo Zhao^*, Boya Wu, Zhengyang Liang, Shitao Xiao, Xi Yang, Yongping Xiong, Bo Zhang, Tiejun Huang, Zheng Liu^✉

Paper|Code

CVPR 2025

Unveiling the Ignorance of MLLMs: Seeing Clearly, Answering Incorrectly

Yexin Liu^*, Zhengyang Liang^*, Yueze Wang, Xianfeng Wu, Feilong Tang, Muyang He, Jian Li, Zheng Liu, Harry Yang, Sernam Lim, Bo Zhao^✉

Paper|Code|Dataset

ACMMM 2025

Dynamic Self-adaptive Multiscale Distillation from Pre-trained Multimodal Large Model for Efficient Cross-modal Representation Learning

Zhengyang Liang, Meiyu Liang^✉, Wei Huang, Yawen Li, Zhe Xue

Paper|Code

AAAI 2023

Self-Supervised Multi-Modal Knowledge Graph Contrastive Hashing for Cross-Modal Search

Meiyu Liang, Junping Du^✉, Zhengyang Liang, Yongwang Xing, Wei Huang, Zhe Xue (Finished as first student author)

Paper

🥇 Honors and Awards

• 2023, Honorable Mention of Mathematical Contest in Modeling of America
• 2022, The second prize of China(First prize of Beijing) of Mathematical Contest in Modeling of China

📖 Educations

• 2020.09 - 2024.07, Bachelor, Beijing University of Posts and Telecommunications.
• 2025.08 - Now, Ph.D, Singapore Management University.

💻 Internships

• 2024.05 - 2025.05, Beijing Academic of Artificial Intelligence, Beijing.
• 2023.12 - 2024.04, Lenovo Research, Beijing.