Song Lai

Biography

I am a third-year Ph.D. student in the Department of Computer Science at City University of Hong Kong, and a member of the Optima Group, advised by Prof. Qingfu Zhang and Prof. Gaofeng Meng. I received my M.Eng. and B.Eng. degrees from Beihang University.

My research focuses on continual learning, multi-objective optimization, and multimodal learning in open and dynamic environments.

Publications

* denotes equal contribution. Selected first-author and co-first-author papers are listed first.

1. Beyond Myopic Alignment: Lookahead Optimization for Online Class-Incremental Learning.
   Song Lai, Zhe Zhao, Fei Zhu, Ji Cheng, Xi Lin, Qingfu Zhang, Gaofeng Meng.
   IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2026. CCF-A
2. Reinforcement Fine-Tuning Naturally Mitigates Forgetting in Continual Post-Training.
   Song Lai*, Haohan Zhao*, Rong Feng, Changyi Ma, Wenzhuo Liu, Hongbo Zhao, Xi Lin, Dong Yi, Qingfu Zhang, Hongbin Liu, Gaofeng Meng, Fei Zhu.
   International Conference on Machine Learning (ICML), 2026. CCF-A
3. Gradient-Guided Epsilon Constraint Method for Online Continual Learning.
   Song Lai*, Changyi Ma*, Fei Zhu, Zhe Zhao, Xi Lin, Gaofeng Meng, Qingfu Zhang.
   Advances in Neural Information Processing Systems (NeurIPS), 2025. CCF-A
4. Pareto Continual Learning: Preference-Conditioned Learning and Adaption for Dynamic Stability-Plasticity Trade-off.
   Song Lai, Zhe Zhao, Fei Zhu, Xi Lin, Qingfu Zhang, Gaofeng Meng.
   AAAI Conference on Artificial Intelligence (AAAI), 2025. CCF-A
5. EchoMEN: Combating Data Imbalance in Ejection Fraction Regression via Multi-expert Network.
   Song Lai, Mingyang Zhao, Zhe Zhao, Shi Chang, Xiaohua Yuan, Hongbin Liu, Qingfu Zhang, Gaofeng Meng.
   Medical Image Computing and Computer Assisted Intervention (MICCAI), 2024. Oral CCF-B
6. When Pulling Fails: Understanding and Alleviating SDF Collapse in Sparse Freehand Ultrasound Reconstruction.
   Jiuan Chen*, Song Lai*, Mingyang Zhao, Gaofeng Meng.
   International Joint Conference on Artificial Intelligence (IJCAI), 2026. CCF-B
7. Fast Radiance Field Reconstruction from Sparse Inputs.
   Song Lai, Linyan Cui, Jihao Yin.
   Pattern Recognition, 2025. SCI Q1
8. Lookahead-GCG: Improving Multi-Model Gradient-Based Jailbreaking Attacks via Nesterov Momentum.
   Rong Feng, Haohan Zhao, Shiqin Tang, Geng Liu, Song Lai, Meng Wang, Shuxin Zhuang, Yuqi Zha, Changyi Ma, Runsheng Yu.
   International Conference on Machine Learning (ICML), 2026. CCF-A
9. Offline Multi-Objective Bandits: From Logged Data to Pareto-Optimal Policies.
   Ji Cheng, Song Lai, Shunyu Yao, Bo Xue.
   AAAI Conference on Artificial Intelligence (AAAI), 2026. Oral CCF-A
10. From Memorization to Creation: Evaluating the Cognitive Depth of LLM-Generated Educational Questions.
    Xiaolong Wang, Zhe Zhao, Song Lai, Chaoli Zhang, Zijie Geng, Yu Tong, Ye Wei, Qingsong Wen.
    ACM SIGKDD Conference on Knowledge Discovery and Data Mining (KDD), 2026. CCF-A
11. Breaking Long-Tailed Learning Bottlenecks: A Controllable Paradigm with Hypernetwork-Generated Diverse Experts.
    Zhe Zhao, Haibin Wen, Zikang Wang, Pengkun Wang, Fanfu Wang, Song Lai, Qingfu Zhang, Yang Wang.
    Advances in Neural Information Processing Systems (NeurIPS), 2024. Spotlight CCF-A
12. Two Fists, One Heart: Multi-Objective Optimization Based Strategy Fusion for Long-tailed Learning.
    Zhe Zhao, Pengkun Wang, Haibin Wen, Wei Xu, Song Lai, Qingfu Zhang, Yang Wang.
    International Conference on Machine Learning (ICML), 2024. CCF-A
13. MMDFND: Multi-modal Multi-Domain Fake News Detection.
    Yu Tong, Weihai Lu, Zhe Zhao, Song Lai, Tong Shi.
    ACM International Conference on Multimedia (ACM MM), 2024. CCF-A