Ge Li

Full Professor, Shenzhen Graduate School, Peking University

Joined

February 2020

Names

Ge Li (Preferred)

Emails

****@ece.pku.edu.cn (Confirmed)

****@pku.edu.cn (Confirmed)

Personal Links

Homepage

DBLP

ORCID

Career & Education History

Full Professor

Shenzhen Graduate School, Peking University (pku.edu.cn)

2015 – Present

Advisors, Relations & Conflicts

Coauthor

Shan Liu

2020 – 2023

Expertise

multimedia information processing

Present

point cloud processing and compression

Present

3D modeling

Present

Publications

Modality-Balanced Decoupling Alignment for Text-Video Retrieval
Feng Wang, Ruyang Liu, Xinpeng Liu, Shiqiang Long, Ge Li
- ICLR 2026 Conference Withdrawn Submission
- Readers: Everyone
Content-Rich AIGC Video Quality Assessment via Intricate Text Alignment and Motion-Aware Consistency
Shangkun Sun, Xiaoyu Liang, Bowen Qu, Ge Li, Wei Gao
- Submitted to ICLR 2026
- Readers: Everyone
Polysemous Language Gaussian Splatting via Matching-based Mask Lifting
Jiayu Ding, Xinpeng Liu, Zhiyi Pan, Shiqiang Long, Ge Li
- ICLR 2026 Conference Withdrawn Submission
- Readers: Everyone
ST-LLM: Large Language Models Are Effective Temporal Learners
Ruyang Liu, Chen Li, Haoran Tang, Yixiao Ge, Ying Shan, Ge Li
- OpenReview Archive Direct Upload
- Readers: Everyone
RAP: Efficient Text-Video Retrieval with Sparse-and-Correlated Adapter
Meng Cao, Haoran Tang, Jinfa Huang, Jinpeng Li, Can Zhang, Ruyang Liu, Long Chen, Xiaodan Liang, Li Yuan, Ge Li
- OpenReview Archive Direct Upload
- Readers: Everyone
MUSE: Mamba is Efficient Multi-scale Learner for Text-video Retrieval
Haoran Tang, Meng Cao, Jinfa Huang, Ruyang Liu, Jinpeng Li, Ge Li, Xiaodan Liang
- OpenReview Archive Direct Upload
- Readers: Everyone
SoftSignSGD(S3): An Enhanced Optimize for Practical DNN Training and Loss Spikes Minimization Beyond Adam
Hanyang Peng, Shuang Qin, Fangqing Jiang, Yue Yu, Hui Wang, Ge Li
- Submitted to ICLR 2025
- Readers: Everyone
Distribution Guidance Network for Weakly Supervised Point Cloud Semantic Segmentation
Zhiyi Pan, Wei Gao, Shan Liu, Ge Li
- NeurIPS 2024 poster
- Readers: Everyone
ROI-Guided Point Cloud Geometry Compression Towards Human and Machine Vision
Liang Xie, Wei Gao, Huiming Zheng, Ge Li
- MM2024 Poster
- Readers: Everyone
ViewPCGC: View-Guided Learned Point Cloud Geometry Compression
Huiming Zheng, Wei Gao, Zhuozhen Yu, Tiesong Zhao, Ge Li
- MM2024 Poster
- Readers: Everyone

View all 26 publications

Co-Authors

View all 58 co-authors