|
|
2026年期刊论文和会议论文
|
[1]
|
Yuhang Liu, Tao Li, Zhehao Huang, Zuopeng Yang, Xiaolin Huang: Bi-LoRA: Efficient sharpness-aware minimization for fine-tuning large-scale models, in proceedings of International Conference on Learning Representations (ICLR), Rio de Janeiro, Brazil, pp. 1-10, 2026
|
|
[2]
|
Xinwen Cheng, Zhehao Huang, Wenxing Zhou, Zhengbao He, Ruikai Yang, Yingwen Wu, Xiaolin Huang: Remaining-data-free machine unlearning by suppressing sample contribution, in proceedings of International Conference on Learning Representations (ICLR), Rio de Janeiro, Brazil, pp. 1-10, 2026
|
|
[3]
|
Zhehao Huang, Yuhang Liu, Baijiong Lin, Yixin Lou, Zhengbao He, Hanling Tian, Tao Li, Xiaolin Huang: RAIN-Merging: A gradient-free method to enhance instruction following in large reasoning models with preserved thinking format, in proceedings of International Conference on Learning Representations (ICLR), Rio de Janeiro, Brazil, pp. 1-10, 2026
|
2025年期刊论文和会议论文
|
[2]
|
Hanling Tian, Yuhang Liu, Mingzhen He, Zhengbao He, Zhehao Huang, Ruikai Yang, Xiaolin Huang: Simulating training dynamics to reconstruct training data from deep neural networks, in proceedings of International Conference on Learning Representations (ICLR), Singapore, pp. 1-9, 2025
|
2024年期刊论文和会议论文
|
[2]
|
Zhehao Huang, Xinwen Cheng, Jinghao Zheng, Haoran Wang, Zhengbao He, Tao Li, Xiaolin Huang: Unified gradient-based machine unlearning with Remain geometry enhancement, in proceedings of Neural Information Processing Systems (NeurIPS), Vancouver, Canada, pp. 1-9, 2024
|
2023年期刊论文和会议论文
|
[1]
|
Tao Li, Lei Tan, Zhehao Huang, Qinghua Tao, Yipeng Liu, Xiaolin Huang: Low Dimensional Trajectory Hypothesis is True: DNNs can be Trained in Tiny Subspaces, IEEE Transactions on Pattern Analysis and Machine Intelligence, 45(3): 3411-3420, 2023
|
|
[2]
|
Sizhe Chen, Zhehao Huang, Qinghua Tao, Xiaolin Huang: Query attack by multi-identity surrogates, IEEE Transactions on Artificial Intelligence, 1-9, 2023
|
|
[3]
|
Tao Li, Zhehao Huang, Qinghua Tao, Yingwen Wu, Xiaolin Huang: Trainable weight averaging: Efficient training by optimizing historical solutions, in proceedings of International Conference on Learning Representations (ICLR), Kigali, Rwanda, pp. 1-9, 2023
|
2022年期刊论文和会议论文
|
[1]
|
Sizhe Chen, Zhehao Huang, Qinghua Tao, Yingwen Wu, Cihang Xie, Xiaolin Huang: Adversarial Attack on Attackers: Post-Process to Mitigate Black-Box Score-Based Query Attacks, in proceedings of Neural Information Processing Systems (NeurIPS), New Orleans, USA, pp. 1-9, 2022
|
|
