Assistant Professor · SUAT

Songlin Dong

董松林

Assistant Professor (副高), Ph.D. Supervisor

Faculty of Computility Microelectronics (算力微电子学院)
Shenzhen University of Advanced Technology (SUAT)

My research focuses on continual learning, multimodal large language models, and embodied AI. I received my Ph.D. from Xi'an Jiaotong University (2025) and joined SUAT the same year. I have published 10+ papers at top venues (CVPR, AAAI, ICCV, ECCV) and 12+ journal papers (TNNLS, TMM, TCSVT).

1,500+
Citations
40+
Publications
20+
Top Conf. Papers
2
Invention Patents
Continual Learning Multimodal LLMs Embodied AI Class-Incremental Learning Vision-Language Models Knowledge Transfer Anti-Forgetting
01

Recent News

2026.3
New Paper 实验室共有两篇论文分别被中科院一区期刊 IEEE Transactions on Circuits and Systems for Video Technology 和 Pattern Recognition 录用 .
2026.3
New Paper 实验室共有三篇论文被 CVPR 2026 接收 .
2025.11
New Paper 实验室共有一篇论文被 AAAI 2026 接收 .
2025.01
New Joined Shenzhen University of Advanced Technology (SUAT) as Assistant Professor in the Faculty of Computility Microelectronics (算力微电子学院).
02

Selected Publications

* denotes equal contribution. Full list on Google Scholar and DBLP.   corresponding author.

2026
CVPR 2026
Is Parameter Isolation Better for Prompt-Based Continual Learning?
Jiangyang Li, Chenhao Ding, Songlin Dong, Qiang Wang, JianChao Zhao, Yuhang He, Yihong Gong
2026
CVPR 2026
ReMoT: Reinforcement Learning with Motion Contrast Triplets
Cong Wang, Zeyu Guo, Songlin Dong
2026
CVPR 2026 Finding
Trajectory-Diversity-Driven Robust Vision-and-Language Navigation
Jiangyang Li, Chenhao Ding, Songlin Dong, Qiang Wang, JianChao Zhao, Yuhang He, Yihong Gong
2026
AAAI 2026
Shared & Domain Self-Adaptive Experts with Frequency-Aware Discrimination for Continual Test-Time Adaptation
Songlin Dong et al.
2025
ACL Findings 2025
SuLoRA: Subspace Low-Rank Adaptation for Parameter-Efficient Fine-Tuning
Chenhao Ding, Jiangyang Li, Songlin Dong, Xinyuan Gao, Yuhang He, Yihong Gong
2025
AAAI 2025
DualCP: Rehearsal-Free Domain-Incremental Learning via Dual-Level Concept Prototype
Qiang Wang, Yuhang He, Songlin Dong, Xiang Song, Jizhou Han, Haoyu Luo, Yihong Gong
2025
IEEE T-CSVT 2025
CEAT: Continual Expansion and Absorption Transformer for Non-Exemplar Class-Incremental Learning
Songlin Dong, Xinyuan Gao, Yuhang He, Zhengdong Zhou, Alex C. Kot, Yihong Gong
2025
IEEE T-MM 2025
Analogical Augmentation and Significance Analysis for Online Task-Free Continual Learning
Songlin Dong, Yingjie Chen, Yuhang He, Yuhan Jin, Alex C. Kot, Yihong Gong
2023
ICCV 2023
Knowledge Restore and Transfer for Multi-Label Class-Incremental Learning
Songlin Dong, Haoyu Luo, Yuhang He, Xing Wei, Jie Cheng, Yihong Gong
2023
CVPR 2023
DKT: Diverse Knowledge Transfer Transformer for Class Incremental Learning
Xinyuan Gao, Yuhang He, Songlin Dong, Jie Cheng, Xing Wei, Yihong Gong
2024
AAAI 2024
Non-exemplar Domain Incremental Object Detection via Learning Domain Bias
Xiang Song, Yuhang He, Songlin Dong, Yihong Gong
2023
IEEE T-NNLS 2023
Model Behavior Preserving for Class-Incremental Learning
Yu Liu, Xiaopeng Hong, Xiaoyu Tao, Songlin Dong, Jingang Shi, Yihong Gong
2021
AAAI 2021
Few-Shot Class-Incremental Learning via Relation Knowledge Distillation
Songlin Dong, Xiaopeng Hong, Xiaoyu Tao, Xinyuan Chang, Xing Wei, Yihong Gong
2020
CVPR 2020
Few-Shot Class-Incremental Learning
Xiaoyu Tao, Xiaopeng Hong, Xinyuan Chang, Songlin Dong, Xing Wei, Yihong Gong
03

Academic Service

Conference Reviewing

  • CVPR (2022–2025)
  • ICCV (2023–2025)
  • ECCV (2022–2024)
  • NeurIPS (2023–2025)
  • AAAI (2022–2025)
  • ACMMM (2022–2024)

Journal Reviewing

  • IEEE Transactions on Neural Networks and Learning Systems (TNNLS)
  • IEEE Transactions on Multimedia (TMM)
  • IEEE Transactions on Circuits and Systems for Video Technology (TCSVT)
  • Pattern Recognition
  • IEEE Transactions on Medical Imaging (T-MI)
04

Prospective Students

I am actively looking for Ph.D. students, Master students, Research Assistants, and Research Interns who are passionate about AI research in continual learning, multimodal LLMs, and embodied intelligence.


If you are interested in joining my group at SUAT, please send me an email at [email protected] with your CV, transcripts, and a brief description of your research interests. Strong mathematical background and programming skills are preferred.


SUAT is located in Shenzhen, one of China's most dynamic innovation hubs, with close ties to the Chinese Academy of Sciences and leading tech companies.

05

Contact

Office
Faculty of Computility Microelectronics (算力微电子学院)
Shenzhen University of Advanced Technology
No. 1 Gongchang Road, Guangming District, Shenzhen
Institutional Page