Publications

Yuhang Liu, Tao Li, Zhehao Huang, Zuopeng Yang, Xiaolin Huang (2025). Bi-LoRA: Efficient Sharpness-Aware Minimization for Fine-Tuning Large-Scale Models. In arXiv.

Zhehao Huang, Yuhang Liu, Yixin Lou, Zhengbao He, Mingzhen He, Wenxing Zhou, Tao Li, Kehan Li, Zeyi Huang, Xiaolin Huang (2025). T2I-ConBench: Text-to-Image Benchmark for Continual Post-training. In arXiv.

Zhehao Huang, Xinwen Cheng, Jie Zhang, Jinghao Zheng, Haoran Wang, Zhengbao He, Tao Li, Xiaolin Huang (2025). A Unified Gradient-based Framework for Task-agnostic Continual Learning-Unlearning. In arXiv.

Hanling Tian, Yuhang Liu, Mingzhen He, Zhengbao He, Zhehao Huang, Ruikai Yang, Xiaolin Huang (2025). Simulating Training Dynamics to Reconstruct Training Data from Deep Neural Networks. In ICLR 2025 Poster.

Zhehao Huang, Xinwen Cheng, Jinghao Zheng, Haoran Wang, Zhengbao He, Tao Li, Xiaolin Huang (2024). Unified Gradient-Based Machine Unlearning with Remain Geometry Enhancement. In NeurIPS 2024 Spotlight.

Zhehao Huang, Tao Li, Chenhe Yuan, Yingwen Wu, Xiaolin Huang (2024). Online Continual Learning via Logit Adjusted Softmax. In TMLR 05/2024.

Zhengbao He, Tao Li, Xinwen Cheng, Zhehao Huang, Xiaolin Huang (2024). Towards Natural Machine Unlearning. In TPAMI.

Xinwen Cheng, Zhehao Huang, Xiaolin Huang (2024). Remaining-data-free Machine Unlearning by Suppressing Sample Contribution. In arXiv.

Sizhe Chen, Zhehao Huang, Qinghua Tao, Xiaolin Huang (2023). Query Attack by Multi-Identity Surrogates. In TAI 2023.

Tao Li, Zhehao Huang, Qinghua Tao, Yingwen Wu, Xiaolin Huang (2023). Trainable Weight Averaging: Efficient Training by Optimizing Historical Solutions. In ICLR 2023.