Long-Kai Huang

|

Publications by Topic

* indicates equal contributions; † indicates corresponding authors.

Continual Learning

3.	SD-LoRA: Scalable Decoupled Low-Rank Adaptation for Class Incremental Learning Yichen Wu, Hongming Piao, Long-Kai Huang^†, Renzhen Wang, Wanhua Li, Hanspeter Pfister, Deyu Meng, Kede Ma^†, Ying Wei^† In International Conference on Learning Representations (ICLR) , 2025 (Oral)

2.	Mitigating Catastrophic Forgetting in Online Continual Learning by Modeling Previous Task Interrelations Via Pareto Optimization Yichen Wu, Hong Wang, Peilin Zhao, Yefeng Zheng, Ying Wei^†, Long-Kai Huang^† In International Conference on Machine Learning (ICML) , 2024

Meta Continual Learning Revisited: Implicitly Enhancing Online Hessian Approximation via Variance Reduction

Yichen Wu, Long-Kai Huang^†, Renzhen Wang, Deyu Meng, Ying Wei^†
In International Conference on Learning Representations (ICLR) , 2024 (Oral, Outstanding Paper Award Honorable Mention)

Meta Learning

8.	Learning Where to Edit Vision Transformers Yunqiao Yang, Long-Kai Huang^†, Shengzhuang Chen, Kede Ma, Ying Wei^† In Advances in Neural Information Processing Systems (NeurIPS) , 2024

Meta Continual Learning Revisited: Implicitly Enhancing Online Hessian Approximation via Variance Reduction

6.	Secure Out-of-Distribution Task Generalization with Energy-Based Models Shengzhuang Chen, Long-Kai Huang, Jonathan Richard Schwarz, Yilun Du, Ying Wei In Neural Information Processing Systems (NeurIPS) , 2023

5.	Improving Task-Specific Generalization in Few-Shot Learning via Adaptive Vicinal Risk Minimization Long-Kai Huang, Ying Wei In Neural Information Processing Systems (NeurIPS) , 2022

4.	Adversarial Task Up-sampling for Meta-learning Yichen Wu, Long-Kai Huang^†, Ying Wei^† In Neural Information Processing Systems (NeurIPS) , 2022

3.	Functionally Regionalized Knowledge Transfer for Low-Resource Drug Discovery Huaxiu Yao, Ying Wei, Long-Kai Huang, Ding Xue, Junzhou Huang, Zhenhui Jessie Li In Neural Information Processing Systems (NeurIPS) , 2021

2.	Improving Generalization in Meta-learning via Task Augmentation Huaxiu Yao, Long-Kai Huang*, Linjun Zhang, Ying Wei, Li Tian, James Zou, Junzhou Huang, Zhenhui Li In International Conference on Machine Learning* (ICML) , 2021

1.	Accelerate Learning of Deep Hashing With Gradient Attention Long-Kai Huang, Jianda Chen, Sinno Jialin Pan In International Conference on Computer Vision (ICCV) , 2019

Transfer Learning

3.	Concept-wise Fine-tuning Matters in Preventing Negative Transfer Yunqiao Yang, Long-Kai Huang, Ying Wei In International Conference on Computer Vision (ICCV) , 2023

2.	Frustratingly Easy Transferability Estimation Long-Kai Huang , Junzhou Huang, Yu Rong, Qiang Yang, Ying Wei In International Conference on Machine Learning (ICML) , 2022

1.	Fine-Tuning Graph Neural Networks via Graph Topology Induced Optimal Transport Jiying Zhang, Xi Xiao, Long-Kai Huang, Yu Rong, Yatao Bian In International Joint Conference on Artificial Intelligence (IJCAI) , 2022

Model Editing

3.	Steering Protein Language Models Long-Kai Huang, Rongyi Zhu, Bing He, Jianhua Yao In International Conference on Machine Learning (ICML) , 2025

2.	Learning Where to Edit Vision Transformers Yunqiao Yang, Long-Kai Huang^†, Shengzhuang Chen, Kede Ma, Ying Wei^† In Advances in Neural Information Processing Systems (NeurIPS) , 2024

1.	Retaining Beneficial Information from Detrimental Data for Neural Network Repair Long-Kai Huang, Peilin Zhao, Junzhou Huang, Sinno Jialin Pan In Neural Information Processing Systems (NeurIPS) , 2023

Optimization / Generalization

4.	Mitigating Catastrophic Forgetting in Online Continual Learning by Modeling Previous Task Interrelations Via Pareto Optimization Yichen Wu, Hong Wang, Peilin Zhao, Yefeng Zheng, Ying Wei^†, Long-Kai Huang^† In International Conference on Machine Learning (ICML) , 2024

Meta Continual Learning Revisited: Implicitly Enhancing Online Hessian Approximation via Variance Reduction

2.	Improving Generalization in Meta-learning via Task Augmentation Huaxiu Yao, Long-Kai Huang*, Linjun Zhang, Ying Wei, Li Tian, James Zou, Junzhou Huang, Zhenhui Li In International Conference on Machine Learning* (ICML) , 2021

1.	Communication-Efficient Distributed PCA by Riemannian Optimization Long-Kai Huang, Sinno Jialin Pan In International Conference on Machine Learning* (ICML) , 2020

LLMs / ViTs

4.	IBCircuit: Towards Holistic Circuit Discovery with Information Bottleneck Tian Bian, Yifan Niu, Chaohao Yuan, Chengzhi Piao, Bingzhe Wu, Long-Kai Huang, Yu Rong, Tingyang Xu, Hong Cheng, Jia Li In International Conference on Machine Learning (ICML) , 2025

3.	SD-LoRA: Scalable Decoupled Low-Rank Adaptation for Class Incremental Learning Yichen Wu, Hongming Piao, Long-Kai Huang^†, Renzhen Wang, Wanhua Li, Hanspeter Pfister, Deyu Meng, Kede Ma^†, Ying Wei^† In International Conference on Learning Representations (ICLR) , 2025 (Oral)

2.	Parameter and Memory Efficient Pretraining via Low-rank Riemannian Optimization Zhanfeng Mo, Long-Kai Huang, Sinno Jialin Pan In International Conference on Learning Representations (ICLR) , 2025

1.	Learning Where to Edit Vision Transformers Yunqiao Yang, Long-Kai Huang^†, Shengzhuang Chen, Kede Ma, Ying Wei^† In Advances in Neural Information Processing Systems (NeurIPS) , 2024

AI for Science / Biological Language Models

6.	Steering Protein Language Models Long-Kai Huang, Rongyi Zhu, Bing He, Jianhua Yao In International Conference on Machine Learning (ICML) , 2025

5.	Atomas: Hierarchical Adaptive Alignment on Molecule-Text for Unified Molecule Understanding and Generation Yikun Zhang, Geyan Ye, Chaohao Yuan, Bo Han, Long-Kai Huang, Jianhua Yao, Wei Liu, Yu Rong In International Conference on Learning Representations (ICLR) , 2025

4.	Annotation-guided protein design with multi-level domain alignment Chaohao Yuan, Songyou Li, Geyan Ye, Yikun Zhang, Long-Kai Huang, Wenbing Huang, Wei Liu, Jianhua Yao, Yu Rong In Proceedings of ACM SIGKDD Conference on Knowledge Discovery and Data (KDD) , 2025

DrugOOD: Out-of-Distribution Dataset Curator and Benchmark for AI-Aided Drug Discovery–a Focus on Affinity Prediction Problems with Noise Annotation

Yuanfeng Ji, Lu Zhang, Jiaxiang Wu, Bingzhe Wu, Lanqing Li, Long-Kai Huang, Tingyang Xu, Yu Rong, Jie Ren, Ding Xue, Houtim Lai, Wei Liu, Junzhou Huang, Shuigeng Zhou, Ping Luo, Peilin Zhao, Yatao Bian
In Proceedings of the AAAI Conference on Artificial Intelligence (AAAI) , 2023

2.	Functionally Regionalized Knowledge Transfer for Low-Resource Drug Discovery Huaxiu Yao, Ying Wei, Long-Kai Huang, Ding Xue, Junzhou Huang, Zhenhui Jessie Li In Neural Information Processing Systems (NeurIPS) , 2021

1.	Improving Generalization in Meta-learning via Task Augmentation Huaxiu Yao, Long-Kai Huang*, Linjun Zhang, Ying Wei, Li Tian, James Zou, Junzhou Huang, Zhenhui Li In International Conference on Machine Learning* (ICML) , 2021

|

Publications by Topic

Continual Learning

SD-LoRA: Scalable Decoupled Low-Rank Adaptation for Class Incremental Learning

Mitigating Catastrophic Forgetting in Online Continual Learning by Modeling Previous Task Interrelations Via Pareto Optimization

Meta Continual Learning Revisited: Implicitly Enhancing Online Hessian Approximation via Variance Reduction

Meta Learning

Learning Where to Edit Vision Transformers

Meta Continual Learning Revisited: Implicitly Enhancing Online Hessian Approximation via Variance Reduction

Secure Out-of-Distribution Task Generalization with Energy-Based Models

Improving Task-Specific Generalization in Few-Shot Learning via Adaptive Vicinal Risk Minimization

Adversarial Task Up-sampling for Meta-learning

Functionally Regionalized Knowledge Transfer for Low-Resource Drug Discovery

Improving Generalization in Meta-learning via Task Augmentation

Accelerate Learning of Deep Hashing With Gradient Attention

Transfer Learning

Concept-wise Fine-tuning Matters in Preventing Negative Transfer

Frustratingly Easy Transferability Estimation

Fine-Tuning Graph Neural Networks via Graph Topology Induced Optimal Transport

Model Editing

Steering Protein Language Models

Learning Where to Edit Vision Transformers

Retaining Beneficial Information from Detrimental Data for Neural Network Repair

Optimization / Generalization

Mitigating Catastrophic Forgetting in Online Continual Learning by Modeling Previous Task Interrelations Via Pareto Optimization

Meta Continual Learning Revisited: Implicitly Enhancing Online Hessian Approximation via Variance Reduction

Improving Generalization in Meta-learning via Task Augmentation

Communication-Efficient Distributed PCA by Riemannian Optimization

LLMs / ViTs

IBCircuit: Towards Holistic Circuit Discovery with Information Bottleneck

SD-LoRA: Scalable Decoupled Low-Rank Adaptation for Class Incremental Learning

Parameter and Memory Efficient Pretraining via Low-rank Riemannian Optimization

Learning Where to Edit Vision Transformers

AI for Science / Biological Language Models

Steering Protein Language Models

Atomas: Hierarchical Adaptive Alignment on Molecule-Text for Unified Molecule Understanding and Generation

Annotation-guided protein design with multi-level domain alignment

DrugOOD: Out-of-Distribution Dataset Curator and Benchmark for AI-Aided Drug Discovery–a Focus on Affinity Prediction Problems with Noise Annotation

Functionally Regionalized Knowledge Transfer for Low-Resource Drug Discovery

Improving Generalization in Meta-learning via Task Augmentation